{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/question-answering/papers/ran/2","list_of":"/task/question-answering","task":"Question Answering","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":2,"pages_in_order":13,"rows_per_page":100,"rows":[101,200],"of":1274,"counts":{"archive_papers_tagged":10817,"with_a_code_link":4171,"where_syntology_ran_a_sample":1274,"not_listed_spam_title":0,"listed":10817,"listed_where_code_ran":1274,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1073,"every_run_a_failure_of_syntologys_instrument":201,"listed_with_a_run_with_no_instrument_failure":1073,"listed_every_run_a_failure_of_syntologys_instrument":201,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/question-answering/papers/ran/1","prev":"/task/question-answering/papers/ran/1","next":"/task/question-answering/papers/ran/3","papers":[{"url":"/paper/ualign-leveraging-uncertainty-estimations-for","slug":"ualign-leveraging-uncertainty-estimations-for","title":"UAlign: Leveraging Uncertainty Estimations for Factuality Alignment on Large Language Models","date":"2024-12-16","arxiv_id":"2412.11803","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":13,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/ualign-leveraging-uncertainty-estimations-for#ran","syntology_url":"https://syntology.ai/paper/2412.11803","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.11803"}},"official":{"repos":["amourwaltz/ualign"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/visual-instruction-tuning-with-500x-fewer","slug":"visual-instruction-tuning-with-500x-fewer","title":"LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering","date":"2024-12-16","arxiv_id":"2412.12359","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/visual-instruction-tuning-with-500x-fewer#ran","syntology_url":"https://syntology.ai/paper/2412.12359","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.12359"}},"official":{"repos":["bibisbar/LLaVA-Steering"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/deepseek-vl2-mixture-of-experts-vision","slug":"deepseek-vl2-mixture-of-experts-vision","title":"DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding","date":"2024-12-13","arxiv_id":"2412.10302","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":3,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/deepseek-vl2-mixture-of-experts-vision#ran","syntology_url":"https://syntology.ai/paper/2412.10302","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.10302"}},"official":{"repos":["deepseek-ai/deepseek-vl2"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-a-multimodal-large-language-model","slug":"towards-a-multimodal-large-language-model","title":"Towards a Multimodal Large Language Model with Pixel-Level Insight for Biomedicine","date":"2024-12-12","arxiv_id":"2412.09278","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/towards-a-multimodal-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2412.09278","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.09278"}},"official":{"repos":["shawnhuang497/medplib"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/doe-1-closed-loop-autonomous-driving-with","slug":"doe-1-closed-loop-autonomous-driving-with","title":"Doe-1: Closed-Loop Autonomous Driving with Large World Model","date":"2024-12-12","arxiv_id":"2412.09627","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/doe-1-closed-loop-autonomous-driving-with#ran","syntology_url":"https://syntology.ai/paper/2412.09627","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.09627"}},"official":{"repos":["wzzheng/doe"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/characterbox-evaluating-the-role-playing","slug":"characterbox-evaluating-the-role-playing","title":"CharacterBox: Evaluating the Role-Playing Capabilities of LLMs in Text-Based Virtual Worlds","date":"2024-12-07","arxiv_id":"2412.05631","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/characterbox-evaluating-the-role-playing#ran","syntology_url":"https://syntology.ai/paper/2412.05631","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.05631"}},"official":{"repos":["paitesanshi/characterbox"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/glm-4-voice-towards-intelligent-and-human","slug":"glm-4-voice-towards-intelligent-and-human","title":"GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot","date":"2024-12-03","arxiv_id":"2412.02612","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/glm-4-voice-towards-intelligent-and-human#ran","syntology_url":"https://syntology.ai/paper/2412.02612","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.02612"}},"official":{"repos":["thudm/glm-4-voice"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/graphotter-evolving-llm-based-graph-reasoning","slug":"graphotter-evolving-llm-based-graph-reasoning","title":"GraphOTTER: Evolving LLM-based Graph Reasoning for Complex Table Question Answering","date":"2024-12-02","arxiv_id":"2412.01230","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":12,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/graphotter-evolving-llm-based-graph-reasoning#ran","syntology_url":"https://syntology.ai/paper/2412.01230","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.01230"}},"official":{"repos":["jding0521/graphotter"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/lscenellm-enhancing-large-3d-scene","slug":"lscenellm-enhancing-large-3d-scene","title":"LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual Preferences","date":"2024-12-02","arxiv_id":"2412.01292","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":4,"n_instrument":6,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":11,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/lscenellm-enhancing-large-3d-scene#ran","syntology_url":"https://syntology.ai/paper/2412.01292","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.01292"}},"official":{"repos":["Hoyyyaard/LSceneLLM"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/cold-causal-reasoning-in-closed-daily","slug":"cold-causal-reasoning-in-closed-daily","title":"COLD: Causal reasOning in cLosed Daily activities","date":"2024-11-29","arxiv_id":"2411.19500","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":1,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cold-causal-reasoning-in-closed-daily#ran","syntology_url":"https://syntology.ai/paper/2411.19500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.19500"}},"official":{"repos":["Exploration-Lab/COLD"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tqa-bench-evaluating-llms-for-multi-table","slug":"tqa-bench-evaluating-llms-for-multi-table","title":"TQA-Bench: Evaluating LLMs for Multi-Table Question Answering with Scalable Context and Symbolic Extension","date":"2024-11-29","arxiv_id":"2411.19504","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tqa-bench-evaluating-llms-for-multi-table#ran","syntology_url":"https://syntology.ai/paper/2411.19504","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.19504"}},"official":{"repos":["relaxed-system-lab/tqa-bench"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/videollm-knows-when-to-speak-enhancing-time","slug":"videollm-knows-when-to-speak-enhancing-time","title":"VideoLLM Knows When to Speak: Enhancing Time-Sensitive Video Comprehension with Video-Text Duet Interaction Format","date":"2024-11-27","arxiv_id":"2411.17991","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/videollm-knows-when-to-speak-enhancing-time#ran","syntology_url":"https://syntology.ai/paper/2411.17991","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.17991"}},"official":{"repos":["yellow-binary-tree/mmduet"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/cross-modal-information-flow-in-multimodal","slug":"cross-modal-information-flow-in-multimodal","title":"Cross-modal Information Flow in Multimodal Large Language Models","date":"2024-11-27","arxiv_id":"2411.18620","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/cross-modal-information-flow-in-multimodal#ran","syntology_url":"https://syntology.ai/paper/2411.18620","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.18620"}},"official":{"repos":["FightingFighting/cross-modal-information-flow-in-MLLM"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/g3d-lf-generalizable-3d-language-feature","slug":"g3d-lf-generalizable-3d-language-feature","title":"g3D-LF: Generalizable 3D-Language Feature Fields for Embodied Tasks","date":"2024-11-26","arxiv_id":"2411.17030","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/g3d-lf-generalizable-3d-language-feature#ran","syntology_url":"https://syntology.ai/paper/2411.17030","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.17030"}},"official":{"repos":["MrZihan/g3D-LF"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/atomr-atomic-operator-empowered-large","slug":"atomr-atomic-operator-empowered-large","title":"AtomR: Atomic Operator-Empowered Large Language Models for Heterogeneous Knowledge Reasoning","date":"2024-11-25","arxiv_id":"2411.16495","repositories_listed":1,"syntology":{"n":13,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":13,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/atomr-atomic-operator-empowered-large#ran","syntology_url":"https://syntology.ai/paper/2411.16495","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.16495"}},"official":{"repos":["THU-KEG/AtomR"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/augmenting-multimodal-llms-with-self","slug":"augmenting-multimodal-llms-with-self","title":"Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question Answering","date":"2024-11-25","arxiv_id":"2411.16863","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/augmenting-multimodal-llms-with-self#ran","syntology_url":"https://syntology.ai/paper/2411.16863","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.16863"}},"official":{"repos":["aimagelab/reflectiva"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/videoespresso-a-large-scale-chain-of-thought","slug":"videoespresso-a-large-scale-chain-of-thought","title":"VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection","date":"2024-11-22","arxiv_id":"2411.14794","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/videoespresso-a-large-scale-chain-of-thought#ran","syntology_url":"https://syntology.ai/paper/2411.14794","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.14794"}},"official":{"repos":["hshjerry/videoespresso"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/gmai-vl-gmai-vl-5-5m-a-large-vision-language","slug":"gmai-vl-gmai-vl-5-5m-a-large-vision-language","title":"GMAI-VL & GMAI-VL-5.5M: A Large Vision-Language Model and A Comprehensive Multimodal Dataset Towards General Medical AI","date":"2024-11-21","arxiv_id":"2411.14522","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gmai-vl-gmai-vl-5-5m-a-large-vision-language#ran","syntology_url":"https://syntology.ai/paper/2411.14522","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.14522"}},"official":{"repos":["uni-medical/gmai-vl"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/teaching-vlms-to-localize-specific-objects","slug":"teaching-vlms-to-localize-specific-objects","title":"Teaching VLMs to Localize Specific Objects from In-context Examples","date":"2024-11-20","arxiv_id":"2411.13317","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/teaching-vlms-to-localize-specific-objects#ran","syntology_url":"https://syntology.ai/paper/2411.13317","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.13317"}},"official":{"repos":["sivandoveh/iploc"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mc-llava-multi-concept-personalized-vision","slug":"mc-llava-multi-concept-personalized-vision","title":"MC-LLaVA: Multi-Concept Personalized Vision-Language Model","date":"2024-11-18","arxiv_id":"2411.11706","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mc-llava-multi-concept-personalized-vision#ran","syntology_url":"https://syntology.ai/paper/2411.11706","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.11706"}},"official":{"repos":["arctanxarc/mc-llava"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/llava-o1-let-vision-language-models-reason","slug":"llava-o1-let-vision-language-models-reason","title":"LLaVA-CoT: Let Vision Language Models Reason Step-by-Step","date":"2024-11-15","arxiv_id":"2411.10440","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/llava-o1-let-vision-language-models-reason#ran","syntology_url":"https://syntology.ai/paper/2411.10440","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.10440"}},"official":{"repos":["PKU-YuanGroup/LLaVA-CoT"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/the-limited-impact-of-medical-adaptation-of","slug":"the-limited-impact-of-medical-adaptation-of","title":"The Limited Impact of Medical Adaptation of Large Language and Vision-Language Models","date":"2024-11-13","arxiv_id":"2411.08870","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/the-limited-impact-of-medical-adaptation-of#ran","syntology_url":"https://syntology.ai/paper/2411.08870","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.08870"}},"official":{"repos":["taekb/eval-medical-dapt"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/controllable-context-sensitivity-and-the-knob","slug":"controllable-context-sensitivity-and-the-knob","title":"Controllable Context Sensitivity and the Knob Behind It","date":"2024-11-11","arxiv_id":"2411.07404","repositories_listed":1,"syntology":{"n":24,"n_ran":16,"n_constructed":0,"n_ran_checked":16,"n_instrument":0,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":16,"n_pointer_only":24,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/controllable-context-sensitivity-and-the-knob#ran","syntology_url":"https://syntology.ai/paper/2411.07404","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.07404"}},"official":{"repos":["kdu4108/context-vs-prior-finetuning"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":16,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/self-training-meets-consistency-improving","slug":"self-training-meets-consistency-improving","title":"Self-Training Meets Consistency: Improving LLMs' Reasoning With Consistency-Driven Rationale Evaluation","date":"2024-11-10","arxiv_id":"2411.06387","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":11,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/self-training-meets-consistency-improving#ran","syntology_url":"https://syntology.ai/paper/2411.06387","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.06387"}},"official":{"repos":["jaehyeoklee-119/crest"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/scidqa-a-deep-reading-comprehension-dataset","slug":"scidqa-a-deep-reading-comprehension-dataset","title":"SciDQA: A Deep Reading Comprehension Dataset over Scientific Papers","date":"2024-11-08","arxiv_id":"2411.05338","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":10,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/scidqa-a-deep-reading-comprehension-dataset#ran","syntology_url":"https://syntology.ai/paper/2411.05338","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.05338"}},"official":{"repos":["yale-nlp/scidqa"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/end-to-end-navigation-with-vision-language","slug":"end-to-end-navigation-with-vision-language","title":"End-to-End Navigation with Vision Language Models: Transforming Spatial Reasoning into Question-Answering","date":"2024-11-08","arxiv_id":"2411.05755","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/end-to-end-navigation-with-vision-language#ran","syntology_url":"https://syntology.ai/paper/2411.05755","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.05755"}},"official":{"repos":["Jirl-upenn/VLMnav"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/delift-data-efficient-language-model","slug":"delift-data-efficient-language-model","title":"DELIFT: Data Efficient Language model Instruction Fine Tuning","date":"2024-11-07","arxiv_id":"2411.04425","repositories_listed":1,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/delift-data-efficient-language-model#ran","syntology_url":"https://syntology.ai/paper/2411.04425","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.04425"}},"official":{"repos":["agarwalishika/delift"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/medical-adaptation-of-large-language-and","slug":"medical-adaptation-of-large-language-and","title":"Medical Adaptation of Large Language and Vision-Language Models: Are We Making Progress?","date":"2024-11-06","arxiv_id":"2411.04118","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/medical-adaptation-of-large-language-and#ran","syntology_url":"https://syntology.ai/paper/2411.04118","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.04118"}},"official":{"repos":["taekb/eval-medical-dapt"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/benchmarking-multimodal-retrieval-augmented","slug":"benchmarking-multimodal-retrieval-augmented","title":"Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent","date":"2024-11-05","arxiv_id":"2411.02937","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/benchmarking-multimodal-retrieval-augmented#ran","syntology_url":"https://syntology.ai/paper/2411.02937","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.02937"}},"official":{"repos":["alibaba-nlp/omnisearch"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/rationale-guided-retrieval-augmented","slug":"rationale-guided-retrieval-augmented","title":"Rationale-Guided Retrieval Augmented Generation for Medical Question Answering","date":"2024-11-01","arxiv_id":"2411.00300","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/rationale-guided-retrieval-augmented#ran","syntology_url":"https://syntology.ai/paper/2411.00300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00300"}},"official":{"repos":["dmis-lab/rag2"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/right-this-way-can-vlms-guide-us-to-see-more","slug":"right-this-way-can-vlms-guide-us-to-see-more","title":"Right this way: Can VLMs Guide Us to See More to Answer Questions?","date":"2024-11-01","arxiv_id":"2411.00394","repositories_listed":1,"syntology":{"n":17,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":13,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 13 unverified","sample_list":"/paper/right-this-way-can-vlms-guide-us-to-see-more#ran","syntology_url":"https://syntology.ai/paper/2411.00394","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00394"}},"official":{"repos":["LeoLee7/Directional_guidance"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":13,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/latent-paraphrasing-perturbation-on-layers","slug":"latent-paraphrasing-perturbation-on-layers","title":"Latent Paraphrasing: Perturbation on Layers Improves Knowledge Injection in Language Models","date":"2024-11-01","arxiv_id":"2411.00686","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/latent-paraphrasing-perturbation-on-layers#ran","syntology_url":"https://syntology.ai/paper/2411.00686","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00686"}},"official":{"repos":["krafton-ai/LaPael"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/show-me-what-and-where-has-changed-question","slug":"show-me-what-and-where-has-changed-question","title":"Show Me What and Where has Changed? Question Answering and Grounding for Remote Sensing Change Detection","date":"2024-10-31","arxiv_id":"2410.23828","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":1,"n_instrument":6,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/show-me-what-and-where-has-changed-question#ran","syntology_url":"https://syntology.ai/paper/2410.23828","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.23828"}},"official":{"repos":["like413/vista"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/autobench-v-can-large-vision-language-models","slug":"autobench-v-can-large-vision-language-models","title":"AutoBench-V: Can Large Vision-Language Models Benchmark Themselves?","date":"2024-10-28","arxiv_id":"2410.21259","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/autobench-v-can-large-vision-language-models#ran","syntology_url":"https://syntology.ai/paper/2410.21259","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.21259"}},"official":{"repos":["wad3birch/AutoBench-V"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/not-all-heads-matter-a-head-level-kv-cache","slug":"not-all-heads-matter-a-head-level-kv-cache","title":"Not All Heads Matter: A Head-Level KV Cache Compression Method with Integrated Retrieval and Reasoning","date":"2024-10-25","arxiv_id":"2410.19258","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/not-all-heads-matter-a-head-level-kv-cache#ran","syntology_url":"https://syntology.ai/paper/2410.19258","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.19258"}},"official":{"repos":["fyyfu/headkv"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/large-language-models-reflect-the-ideology-of","slug":"large-language-models-reflect-the-ideology-of","title":"Large Language Models Reflect the Ideology of their Creators","date":"2024-10-24","arxiv_id":"2410.18417","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/large-language-models-reflect-the-ideology-of#ran","syntology_url":"https://syntology.ai/paper/2410.18417","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.18417"}},"official":{"repos":["aida-ugent/llm-ideology-analysis"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/graphusion-a-rag-framework-for-knowledge","slug":"graphusion-a-rag-framework-for-knowledge","title":"Graphusion: A RAG Framework for Knowledge Graph Construction with a Global Perspective","date":"2024-10-23","arxiv_id":"2410.17600","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/graphusion-a-rag-framework-for-knowledge#ran","syntology_url":"https://syntology.ai/paper/2410.17600","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.17600"}},"official":{"repos":["irenezihuili/graphusion"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/longrag-a-dual-perspective-retrieval","slug":"longrag-a-dual-perspective-retrieval","title":"LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answering","date":"2024-10-23","arxiv_id":"2410.18050","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/longrag-a-dual-perspective-retrieval#ran","syntology_url":"https://syntology.ai/paper/2410.18050","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.18050"}},"official":{"repos":["qingfei1/longrag"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/progressive-compositionality-in-text-to-image","slug":"progressive-compositionality-in-text-to-image","title":"Progressive Compositionality In Text-to-Image Generative Models","date":"2024-10-22","arxiv_id":"2410.16719","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/progressive-compositionality-in-text-to-image#ran","syntology_url":"https://syntology.ai/paper/2410.16719","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.16719"}},"official":{"repos":["evansh666/evogen"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/multichartqa-benchmarking-vision-language","slug":"multichartqa-benchmarking-vision-language","title":"MultiChartQA: Benchmarking Vision-Language Models on Multi-Chart Problems","date":"2024-10-18","arxiv_id":"2410.14179","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multichartqa-benchmarking-vision-language#ran","syntology_url":"https://syntology.ai/paper/2410.14179","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14179"}},"official":{"repos":["zivenzhu/multi-chart-qa"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/paths-over-graph-knowledge-graph-enpowered","slug":"paths-over-graph-knowledge-graph-enpowered","title":"Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoning","date":"2024-10-18","arxiv_id":"2410.14211","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/paths-over-graph-knowledge-graph-enpowered#ran","syntology_url":"https://syntology.ai/paper/2410.14211","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14211"}},"official":null}},{"url":"/paper/a-little-human-data-goes-a-long-way","slug":"a-little-human-data-goes-a-long-way","title":"A Little Human Data Goes A Long Way","date":"2024-10-17","arxiv_id":"2410.13098","repositories_listed":1,"syntology":{"n":17,"n_ran":15,"n_constructed":0,"n_ran_checked":15,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":0,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/a-little-human-data-goes-a-long-way#ran","syntology_url":"https://syntology.ai/paper/2410.13098","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13098"}},"official":{"repos":["dhananjayashok/littlehumandata"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/measuring-free-form-decision-making","slug":"measuring-free-form-decision-making","title":"Measuring Free-Form Decision-Making Inconsistency of Language Models in Military Crisis Simulations","date":"2024-10-17","arxiv_id":"2410.13204","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/measuring-free-form-decision-making#ran","syntology_url":"https://syntology.ai/paper/2410.13204","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13204"}},"official":{"repos":["aashrivastava/llmwargaminginconsistency"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/remember-retrieve-and-generate-understanding","slug":"remember-retrieve-and-generate-understanding","title":"RAP: Retrieval-Augmented Personalization for Multimodal Large Language Models","date":"2024-10-17","arxiv_id":"2410.13360","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":10,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/remember-retrieve-and-generate-understanding#ran","syntology_url":"https://syntology.ai/paper/2410.13360","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13360"}},"official":{"repos":["hoar012/rap-mllm"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/worldcuisines-a-massive-scale-benchmark-for","slug":"worldcuisines-a-massive-scale-benchmark-for","title":"WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines","date":"2024-10-16","arxiv_id":"2410.12705","repositories_listed":1,"syntology":{"n":17,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/worldcuisines-a-massive-scale-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2410.12705","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.12705"}},"official":{"repos":["worldcuisines/worldcuisines"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/meta-chunking-learning-efficient-text","slug":"meta-chunking-learning-efficient-text","title":"Meta-Chunking: Learning Text Segmentation and Semantic Completion via Logical Perception","date":"2024-10-16","arxiv_id":"2410.12788","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/meta-chunking-learning-efficient-text#ran","syntology_url":"https://syntology.ai/paper/2410.12788","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.12788"}},"official":{"repos":["IAAR-Shanghai/Meta-Chunking"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/videgothink-assessing-egocentric-video","slug":"videgothink-assessing-egocentric-video","title":"VidEgoThink: Assessing Egocentric Video Understanding Capabilities for Embodied AI","date":"2024-10-15","arxiv_id":"2410.11623","repositories_listed":1,"syntology":{"n":17,"n_ran":16,"n_constructed":0,"n_ran_checked":13,"n_instrument":3,"n_unverified":1,"n_honours":3,"n_violates":1,"n_no_contract":9,"n_pointer_only":5,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 3 honoured, 1 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/videgothink-assessing-egocentric-video#ran","syntology_url":"https://syntology.ai/paper/2410.11623","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.11623"}},"official":null}},{"url":"/paper/kblam-knowledge-base-augmented-language-model","slug":"kblam-knowledge-base-augmented-language-model","title":"KBLaM: Knowledge Base augmented Language Model","date":"2024-10-14","arxiv_id":"2410.10450","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/kblam-knowledge-base-augmented-language-model#ran","syntology_url":"https://syntology.ai/paper/2410.10450","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10450"}},"official":{"repos":["microsoft/KBLaM"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/will-llms-replace-the-encoder-only-models-in","slug":"will-llms-replace-the-encoder-only-models-in","title":"Will LLMs Replace the Encoder-Only Models in Temporal Relation Classification?","date":"2024-10-14","arxiv_id":"2410.10476","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/will-llms-replace-the-encoder-only-models-in#ran","syntology_url":"https://syntology.ai/paper/2410.10476","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10476"}},"official":{"repos":["brownfortress/llms-trc"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-foundation-models-for-3d-vision-how","slug":"towards-foundation-models-for-3d-vision-how","title":"Towards Foundation Models for 3D Vision: How Close Are We?","date":"2024-10-14","arxiv_id":"2410.10799","repositories_listed":2,"syntology":{"n":29,"n_ran":20,"n_constructed":0,"n_ran_checked":19,"n_instrument":1,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":19,"n_pointer_only":1,"phrase":"20 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/towards-foundation-models-for-3d-vision-how#ran","syntology_url":"https://syntology.ai/paper/2410.10799","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10799"}},"official":{"repos":["princeton-vl/uniqa-3d"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/longmemeval-benchmarking-chat-assistants-on","slug":"longmemeval-benchmarking-chat-assistants-on","title":"LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory","date":"2024-10-14","arxiv_id":"2410.10813","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/longmemeval-benchmarking-chat-assistants-on#ran","syntology_url":"https://syntology.ai/paper/2410.10813","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10813"}},"official":{"repos":["xiaowu0162/longmemeval"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/temporalbench-benchmarking-fine-grained","slug":"temporalbench-benchmarking-fine-grained","title":"TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models","date":"2024-10-14","arxiv_id":"2410.10818","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/temporalbench-benchmarking-fine-grained#ran","syntology_url":"https://syntology.ai/paper/2410.10818","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10818"}},"official":{"repos":["mu-cai/TemporalBench"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/synthetic-knowledge-ingestion-towards","slug":"synthetic-knowledge-ingestion-towards","title":"Synthetic Knowledge Ingestion: Towards Knowledge Refinement and Injection for Enhancing Large Language Models","date":"2024-10-12","arxiv_id":"2410.09629","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/synthetic-knowledge-ingestion-towards#ran","syntology_url":"https://syntology.ai/paper/2410.09629","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.09629"}},"official":{"repos":["intuit-ai-research/knowledge-infused-ai"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/retriever-and-memory-towards-adaptive-note","slug":"retriever-and-memory-towards-adaptive-note","title":"Retriever-and-Memory: Towards Adaptive Note-Enhanced Retrieval-Augmented Generation","date":"2024-10-11","arxiv_id":"2410.08821","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/retriever-and-memory-towards-adaptive-note#ran","syntology_url":"https://syntology.ai/paper/2410.08821","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08821"}},"official":{"repos":["thunlp/adaptive-note"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/stableprompt-automatic-prompt-tuning-using","slug":"stableprompt-automatic-prompt-tuning-using","title":"StablePrompt: Automatic Prompt Tuning using Reinforcement Learning for Large Language Models","date":"2024-10-10","arxiv_id":"2410.07652","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":9,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/stableprompt-automatic-prompt-tuning-using#ran","syntology_url":"https://syntology.ai/paper/2410.07652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07652"}},"official":{"repos":["kmc0207/Stableprompt"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/voxelprompt-a-vision-language-agent-for","slug":"voxelprompt-a-vision-language-agent-for","title":"VoxelPrompt: A Vision-Language Agent for Grounded Medical Image Analysis","date":"2024-10-10","arxiv_id":"2410.08397","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/voxelprompt-a-vision-language-agent-for#ran","syntology_url":"https://syntology.ai/paper/2410.08397","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08397"}},"official":{"repos":["dalcalab/voxel"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-temporal-modeling-of-video-llms-via","slug":"enhancing-temporal-modeling-of-video-llms-via","title":"Enhancing Temporal Modeling of Video LLMs via Time Gating","date":"2024-10-08","arxiv_id":"2410.05714","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":1,"n_pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/enhancing-temporal-modeling-of-video-llms-via#ran","syntology_url":"https://syntology.ai/paper/2410.05714","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.05714"}},"official":{"repos":["lavi-lab/tg-vid"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/teochat-a-large-vision-language-assistant-for","slug":"teochat-a-large-vision-language-assistant-for","title":"TEOChat: A Large Vision-Language Assistant for Temporal Earth Observation Data","date":"2024-10-08","arxiv_id":"2410.06234","repositories_listed":1,"syntology":{"n":9,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":5,"n_honours":2,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/teochat-a-large-vision-language-assistant-for#ran","syntology_url":"https://syntology.ai/paper/2410.06234","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.06234"}},"official":{"repos":["ermongroup/teochat"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/llaca-multimodal-large-language-continual","slug":"llaca-multimodal-large-language-continual","title":"Large Continual Instruction Assistant","date":"2024-10-08","arxiv_id":"2410.10868","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/llaca-multimodal-large-language-continual#ran","syntology_url":"https://syntology.ai/paper/2410.10868","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10868"}},"official":{"repos":["jingyangqiao/coin"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/differential-transformer","slug":"differential-transformer","title":"Differential Transformer","date":"2024-10-07","arxiv_id":"2410.05258","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/differential-transformer#ran","syntology_url":"https://syntology.ai/paper/2410.05258","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.05258"}},"official":{"repos":["microsoft/unilm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/mc-cot-a-modular-collaborative-cot-framework","slug":"mc-cot-a-modular-collaborative-cot-framework","title":"MC-CoT: A Modular Collaborative CoT Framework for Zero-shot Medical-VQA with LLM and MLLM Integration","date":"2024-10-06","arxiv_id":"2410.04521","repositories_listed":1,"syntology":{"n":15,"n_ran":15,"n_constructed":0,"n_ran_checked":15,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":15,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mc-cot-a-modular-collaborative-cot-framework#ran","syntology_url":"https://syntology.ai/paper/2410.04521","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.04521"}},"official":{"repos":["thomaswei-cn/MC-CoT"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/famma-a-benchmark-for-financial-domain","slug":"famma-a-benchmark-for-financial-domain","title":"FAMMA: A Benchmark for Financial Domain Multilingual Multimodal Question Answering","date":"2024-10-06","arxiv_id":"2410.04526","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/famma-a-benchmark-for-financial-domain#ran","syntology_url":"https://syntology.ai/paper/2410.04526","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.04526"}},"official":{"repos":["famma-bench/bench-script"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/adaptive-question-answering-enhancing","slug":"adaptive-question-answering-enhancing","title":"Adaptive Question Answering: Enhancing Language Model Proficiency for Addressing Knowledge Conflicts with Source Citations","date":"2024-10-05","arxiv_id":"2410.04241","repositories_listed":0,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adaptive-question-answering-enhancing#ran","syntology_url":"https://syntology.ai/paper/2410.04241","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.04241"}},"official":null}},{"url":"/paper/fastadasp-multitask-adapted-efficient","slug":"fastadasp-multitask-adapted-efficient","title":"FastAdaSP: Multitask-Adapted Efficient Inference for Large Speech Language Model","date":"2024-10-03","arxiv_id":"2410.03007","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/fastadasp-multitask-adapted-efficient#ran","syntology_url":"https://syntology.ai/paper/2410.03007","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.03007"}},"official":{"repos":["yichen14/fastadasp"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/bridging-context-gaps-leveraging-coreference","slug":"bridging-context-gaps-leveraging-coreference","title":"Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understanding","date":"2024-10-02","arxiv_id":"2410.01671","repositories_listed":0,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":10,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/bridging-context-gaps-leveraging-coreference#ran","syntology_url":"https://syntology.ai/paper/2410.01671","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.01671"}},"official":null}},{"url":"/paper/a-hitchhikers-guide-to-fine-grained-face","slug":"a-hitchhikers-guide-to-fine-grained-face","title":"A Hitchhikers Guide to Fine-Grained Face Forgery Detection Using Common Sense Reasoning","date":"2024-10-01","arxiv_id":"2410.00485","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/a-hitchhikers-guide-to-fine-grained-face#ran","syntology_url":"https://syntology.ai/paper/2410.00485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.00485"}},"official":{"repos":["NickyFot/HitchhikersGuide"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/world-to-code-multi-modal-data-generation-via","slug":"world-to-code-multi-modal-data-generation-via","title":"World to Code: Multi-modal Data Generation via Self-Instructed Compositional Captioning and Filtering","date":"2024-09-30","arxiv_id":"2409.20424","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/world-to-code-multi-modal-data-generation-via#ran","syntology_url":"https://syntology.ai/paper/2409.20424","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.20424"}},"official":{"repos":["foundation-multimodal-models/world2code"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/t2vs-meet-vlms-a-scalable-multimodal-dataset","slug":"t2vs-meet-vlms-a-scalable-multimodal-dataset","title":"T2Vs Meet VLMs: A Scalable Multimodal Dataset for Visual Harmfulness Recognition","date":"2024-09-29","arxiv_id":"2409.19734","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":11,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/t2vs-meet-vlms-a-scalable-multimodal-dataset#ran","syntology_url":"https://syntology.ai/paper/2409.19734","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.19734"}},"official":{"repos":["nctu-eva-lab/vhd11k"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/cotkr-chain-of-thought-enhanced-knowledge","slug":"cotkr-chain-of-thought-enhanced-knowledge","title":"CoTKR: Chain-of-Thought Enhanced Knowledge Rewriting for Complex Knowledge Graph Question Answering","date":"2024-09-29","arxiv_id":"2409.19753","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cotkr-chain-of-thought-enhanced-knowledge#ran","syntology_url":"https://syntology.ai/paper/2409.19753","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.19753"}},"official":{"repos":["wuyike2000/CoTKR"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/does-rag-introduce-unfairness-in-llms","slug":"does-rag-introduce-unfairness-in-llms","title":"Does RAG Introduce Unfairness in LLMs? Evaluating Fairness in Retrieval-Augmented Generation Systems","date":"2024-09-29","arxiv_id":"2409.19804","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/does-rag-introduce-unfairness-in-llms#ran","syntology_url":"https://syntology.ai/paper/2409.19804","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.19804"}},"official":{"repos":["elviswxy/rag_fairness"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/mediconfusion-can-you-trust-your-ai","slug":"mediconfusion-can-you-trust-your-ai","title":"MediConfusion: Can you trust your AI radiologist? Probing the reliability of multimodal medical foundation models","date":"2024-09-23","arxiv_id":"2409.15477","repositories_listed":2,"syntology":{"n":28,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":16,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":28,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 16 unverified","sample_list":"/paper/mediconfusion-can-you-trust-your-ai#ran","syntology_url":"https://syntology.ai/paper/2409.15477","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.15477"}},"official":{"repos":["mshahabsepehri/mediconfusion","AIF4S/MediConfusion"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":16,"ran_from_kinds":["official"]}}},{"url":"/paper/remembr-building-and-reasoning-over-long","slug":"remembr-building-and-reasoning-over-long","title":"ReMEmbR: Building and Reasoning Over Long-Horizon Spatio-Temporal Memory for Robot Navigation","date":"2024-09-20","arxiv_id":"2409.13682","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":10,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/remembr-building-and-reasoning-over-long#ran","syntology_url":"https://syntology.ai/paper/2409.13682","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.13682"}},"official":{"repos":["NVIDIA-AI-IOT/remembr"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/language-models-learn-to-mislead-humans-via","slug":"language-models-learn-to-mislead-humans-via","title":"Language Models Learn to Mislead Humans via RLHF","date":"2024-09-19","arxiv_id":"2409.12822","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/language-models-learn-to-mislead-humans-via#ran","syntology_url":"https://syntology.ai/paper/2409.12822","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.12822"}},"official":{"repos":["jiaxin-wen/misleadlm"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/less-is-more-a-simple-yet-effective-token","slug":"less-is-more-a-simple-yet-effective-token","title":"Less is More: A Simple yet Effective Token Reduction Method for Efficient Multi-modal LLMs","date":"2024-09-17","arxiv_id":"2409.10994","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/less-is-more-a-simple-yet-effective-token#ran","syntology_url":"https://syntology.ai/paper/2409.10994","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.10994"}},"official":{"repos":["freedomintelligence/trim"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-llm-reasoning-with-multi-agent-tree","slug":"improving-llm-reasoning-with-multi-agent-tree","title":"Improving LLM Reasoning with Multi-Agent Tree-of-Thought Validator Agent","date":"2024-09-17","arxiv_id":"2409.11527","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/improving-llm-reasoning-with-multi-agent-tree#ran","syntology_url":"https://syntology.ai/paper/2409.11527","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.11527"}},"official":{"repos":["secureaiautonomylab/ma-tot"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/adacad-adaptively-decoding-to-balance","slug":"adacad-adaptively-decoding-to-balance","title":"AdaCAD: Adaptively Decoding to Balance Conflicts between Contextual and Parametric Knowledge","date":"2024-09-11","arxiv_id":"2409.07394","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adacad-adaptively-decoding-to-balance#ran","syntology_url":"https://syntology.ai/paper/2409.07394","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.07394"}},"official":{"repos":["hannight/adacad"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/lime-m-less-is-more-for-evaluation-of-mllms","slug":"lime-m-less-is-more-for-evaluation-of-mllms","title":"LIME: Less Is More for MLLM Evaluation","date":"2024-09-10","arxiv_id":"2409.06851","repositories_listed":2,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":7,"n_instrument":6,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":14,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/lime-m-less-is-more-for-evaluation-of-mllms#ran","syntology_url":"https://syntology.ai/paper/2409.06851","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.06851"}},"official":{"repos":["kangreen0210/lime","kangreen0210/lime-m"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/2409-13731","slug":"2409-13731","title":"KAG: Boosting LLMs in Professional Domains via Knowledge Augmented Generation","date":"2024-09-10","arxiv_id":"2409.13731","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/2409-13731#ran","syntology_url":"https://syntology.ai/paper/2409.13731","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.13731"}},"official":{"repos":["openspg/kag"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/shaking-up-vlms-comparing-transformers-and","slug":"shaking-up-vlms-comparing-transformers-and","title":"Shaking Up VLMs: Comparing Transformers and Structured State Space Models for Vision & Language Modeling","date":"2024-09-09","arxiv_id":"2409.05395","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/shaking-up-vlms-comparing-transformers-and#ran","syntology_url":"https://syntology.ai/paper/2409.05395","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.05395"}},"official":{"repos":["gpantaz/vl_mamba"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/memorag-moving-towards-next-gen-rag-via","slug":"memorag-moving-towards-next-gen-rag-via","title":"MemoRAG: Moving towards Next-Gen RAG Via Memory-Inspired Knowledge Discovery","date":"2024-09-09","arxiv_id":"2409.05591","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":6,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/memorag-moving-towards-next-gen-rag-via#ran","syntology_url":"https://syntology.ai/paper/2409.05591","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.05591"}},"official":{"repos":["qhjqhj00/memorag"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/alt-moe-multimodal-alignment-via-alternating","slug":"alt-moe-multimodal-alignment-via-alternating","title":"M3-Jepa: Multimodal Alignment via Multi-directional MoE based on the JEPA framework","date":"2024-09-09","arxiv_id":"2409.05929","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/alt-moe-multimodal-alignment-via-alternating#ran","syntology_url":"https://syntology.ai/paper/2409.05929","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.05929"}},"official":{"repos":["HongyangLL/M3-JEPA"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/columbus-evaluating-cognitive-lateral","slug":"columbus-evaluating-cognitive-lateral","title":"COLUMBUS: Evaluating COgnitive Lateral Understanding through Multiple-choice reBUSes","date":"2024-09-06","arxiv_id":"2409.04053","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/columbus-evaluating-cognitive-lateral#ran","syntology_url":"https://syntology.ai/paper/2409.04053","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.04053"}},"official":{"repos":["koen-47/columbus"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/debate-on-graph-a-flexible-and-reliable","slug":"debate-on-graph-a-flexible-and-reliable","title":"Debate on Graph: a Flexible and Reliable Reasoning Framework for Large Language Models","date":"2024-09-05","arxiv_id":"2409.03155","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/debate-on-graph-a-flexible-and-reliable#ran","syntology_url":"https://syntology.ai/paper/2409.03155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.03155"}},"official":{"repos":["reml-group/dog"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/the-representation-landscape-of-few-shot","slug":"the-representation-landscape-of-few-shot","title":"The representation landscape of few-shot learning and fine-tuning in large language models","date":"2024-09-05","arxiv_id":"2409.03662","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":13,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/the-representation-landscape-of-few-shot#ran","syntology_url":"https://syntology.ai/paper/2409.03662","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.03662"}},"official":{"repos":["diegodoimo/geometry_icl_finetuning"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/lexicon3d-probing-visual-foundation-models","slug":"lexicon3d-probing-visual-foundation-models","title":"Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene Understanding","date":"2024-09-05","arxiv_id":"2409.03757","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/lexicon3d-probing-visual-foundation-models#ran","syntology_url":"https://syntology.ai/paper/2409.03757","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.03757"}},"official":null}},{"url":"/paper/longcite-enabling-llms-to-generate-fine","slug":"longcite-enabling-llms-to-generate-fine","title":"LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA","date":"2024-09-04","arxiv_id":"2409.02897","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/longcite-enabling-llms-to-generate-fine#ran","syntology_url":"https://syntology.ai/paper/2409.02897","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.02897"}},"official":{"repos":["THUDM/LongCite"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/how-to-determine-the-preferred-image","slug":"how-to-determine-the-preferred-image","title":"How to Determine the Preferred Image Distribution of a Black-Box Vision-Language Model?","date":"2024-09-03","arxiv_id":"2409.02253","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/how-to-determine-the-preferred-image#ran","syntology_url":"https://syntology.ai/paper/2409.02253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.02253"}},"official":{"repos":["asgsaeid/cad_vqa"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/grounded-multi-hop-videoqa-in-long-form","slug":"grounded-multi-hop-videoqa-in-long-form","title":"Grounded Multi-Hop VideoQA in Long-Form Egocentric Videos","date":"2024-08-26","arxiv_id":"2408.14469","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/grounded-multi-hop-videoqa-in-long-form#ran","syntology_url":"https://syntology.ai/paper/2408.14469","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.14469"}},"official":null}},{"url":"/paper/towards-evaluating-and-building-versatile","slug":"towards-evaluating-and-building-versatile","title":"Towards Evaluating and Building Versatile Large Language Models for Medicine","date":"2024-08-22","arxiv_id":"2408.12547","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-evaluating-and-building-versatile#ran","syntology_url":"https://syntology.ai/paper/2408.12547","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.12547"}},"official":{"repos":["magic-ai4med/meds-ins"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/hierarchical-retrieval-augmented-generation","slug":"hierarchical-retrieval-augmented-generation","title":"Hierarchical Retrieval-Augmented Generation Model with Rethink for Multi-hop Question Answering","date":"2024-08-20","arxiv_id":"2408.11875","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/hierarchical-retrieval-augmented-generation#ran","syntology_url":"https://syntology.ai/paper/2408.11875","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.11875"}},"official":{"repos":["2282588541a/hirag"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/multilingual-needle-in-a-haystack","slug":"multilingual-needle-in-a-haystack","title":"Multilingual Needle in a Haystack: Investigating Long-Context Behavior of Multilingual Large Language Models","date":"2024-08-19","arxiv_id":"2408.10151","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multilingual-needle-in-a-haystack#ran","syntology_url":"https://syntology.ai/paper/2408.10151","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.10151"}},"official":{"repos":["AmeyHengle/multilingual-needle-in-a-haystack"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/fedmeki-a-benchmark-for-scaling-medical","slug":"fedmeki-a-benchmark-for-scaling-medical","title":"FEDMEKI: A Benchmark for Scaling Medical Foundation Models via Federated Knowledge Injection","date":"2024-08-17","arxiv_id":"2408.09227","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fedmeki-a-benchmark-for-scaling-medical#ran","syntology_url":"https://syntology.ai/paper/2408.09227","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.09227"}},"official":{"repos":["psudslab/FEDMEKI"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/med-pmc-medical-personalized-multi-modal","slug":"med-pmc-medical-personalized-multi-modal","title":"Med-PMC: Medical Personalized Multi-modal Consultation with a Proactive Ask-First-Observe-Next Paradigm","date":"2024-08-16","arxiv_id":"2408.08693","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/med-pmc-medical-personalized-multi-modal#ran","syntology_url":"https://syntology.ai/paper/2408.08693","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.08693"}},"official":{"repos":["liuhc0428/med-pmc"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/visual-agents-as-fast-and-slow-thinkers","slug":"visual-agents-as-fast-and-slow-thinkers","title":"Visual Agents as Fast and Slow Thinkers","date":"2024-08-16","arxiv_id":"2408.08862","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/visual-agents-as-fast-and-slow-thinkers#ran","syntology_url":"https://syntology.ai/paper/2408.08862","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.08862"}},"official":{"repos":["guangyans/sys2-llava"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/fine-tuning-large-language-models-with-human","slug":"fine-tuning-large-language-models-with-human","title":"Evaluating Fine-Tuning Efficiency of Human-Inspired Learning Strategies in Medical Question Answering","date":"2024-08-15","arxiv_id":"2408.07888","repositories_listed":2,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":10,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/fine-tuning-large-language-models-with-human#ran","syntology_url":"https://syntology.ai/paper/2408.07888","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.07888"}},"official":{"repos":["Oxford-AI-for-Society/human-learning-strategies"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/seeing-and-understanding-bridging-vision-with","slug":"seeing-and-understanding-bridging-vision-with","title":"ChemVLM: Exploring the Power of Multimodal Large Language Models in Chemistry Area","date":"2024-08-14","arxiv_id":"2408.07246","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/seeing-and-understanding-bridging-vision-with#ran","syntology_url":"https://syntology.ai/paper/2408.07246","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.07246"}},"official":{"repos":["AI4Chem/ChemVlm"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/surgical-vqla-adversarial-contrastive","slug":"surgical-vqla-adversarial-contrastive","title":"Surgical-VQLA++: Adversarial Contrastive Learning for Calibrated Robust Visual Question-Localized Answering in Robotic Surgery","date":"2024-08-09","arxiv_id":"2408.04958","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/surgical-vqla-adversarial-contrastive#ran","syntology_url":"https://syntology.ai/paper/2408.04958","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.04958"}},"official":{"repos":["longbai1006/surgical-vqlaplus"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/efficientrag-efficient-retriever-for-multi","slug":"efficientrag-efficient-retriever-for-multi","title":"EfficientRAG: Efficient Retriever for Multi-Hop Question Answering","date":"2024-08-08","arxiv_id":"2408.04259","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/efficientrag-efficient-retriever-for-multi#ran","syntology_url":"https://syntology.ai/paper/2408.04259","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.04259"}},"official":{"repos":["nil-zhuang/efficientrag-official"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/2408-03094","slug":"2408-03094","title":"500xCompressor: Generalized Prompt Compression for Large Language Models","date":"2024-08-06","arxiv_id":"2408.03094","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/2408-03094#ran","syntology_url":"https://syntology.ai/paper/2408.03094","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.03094"}},"official":{"repos":["ZongqianLi/500xCompressor"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/citekit-a-modular-toolkit-for-large-language","slug":"citekit-a-modular-toolkit-for-large-language","title":"Citekit: A Modular Toolkit for Large Language Model Citation Generation","date":"2024-08-06","arxiv_id":"2408.04662","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/citekit-a-modular-toolkit-for-large-language#ran","syntology_url":"https://syntology.ai/paper/2408.04662","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.04662"}},"official":{"repos":["sjj1017/citekit"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}}],"record_sha256":"3d2afe3e4c6de198b2d4781ada0a89abd82d7dcf99e3df6a8a0c7c3cb147b00e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}