{"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/12","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":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":12,"pages_in_order":109,"rows_per_page":100,"rows":[1101,1200],"of":10817,"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","prev":"/task/question-answering/papers/11","next":"/task/question-answering/papers/13","papers":[{"url":"/paper/online-video-understanding-a-comprehensive","slug":"online-video-understanding-a-comprehensive","title":"Online Video Understanding: OVBench and VideoChat-Online","date":"2024-12-31","arxiv_id":"2501.00584","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-table-recognition-with-vision-llms","slug":"enhancing-table-recognition-with-vision-llms","title":"Enhancing Table Recognition with Vision LLMs: A Benchmark and Neighbor-Guided Toolchain Reasoner","date":"2024-12-30","arxiv_id":"2412.20662","repositories_listed":1,"syntology":null},{"url":"/paper/framefusion-combining-similarity-and","slug":"framefusion-combining-similarity-and","title":"FrameFusion: Combining Similarity and Importance for Video Token Reduction on Large Visual Language Models","date":"2024-12-30","arxiv_id":"2501.01986","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":1,"phrase":"10 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; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/framefusion-combining-similarity-and#ran","syntology_url":"https://syntology.ai/paper/2501.01986","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.01986"}},"official":{"repos":["thu-nics/framefusion"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/hierarchical-banzhaf-interaction-for-general","slug":"hierarchical-banzhaf-interaction-for-general","title":"Hierarchical Banzhaf Interaction for General Video-Language Representation Learning","date":"2024-12-30","arxiv_id":"2412.20964","repositories_listed":1,"syntology":null},{"url":"/paper/mapqator-a-system-for-efficient-annotation-of","slug":"mapqator-a-system-for-efficient-annotation-of","title":"MapQaTor: An Extensible Framework for Efficient Annotation of Map-Based QA Datasets","date":"2024-12-30","arxiv_id":"2412.21015","repositories_listed":1,"syntology":null},{"url":"/paper/unirs-unifying-multi-temporal-remote-sensing","slug":"unirs-unifying-multi-temporal-remote-sensing","title":"UniRS: Unifying Multi-temporal Remote Sensing Tasks through Vision Language Models","date":"2024-12-30","arxiv_id":"2412.20742","repositories_listed":1,"syntology":null},{"url":"/paper/audiopedia-audio-qa-with-knowledge","slug":"audiopedia-audio-qa-with-knowledge","title":"Audiopedia: Audio QA with Knowledge","date":"2024-12-29","arxiv_id":"2412.20619","repositories_listed":1,"syntology":null},{"url":"/paper/hallucinogen-a-benchmark-for-evaluating","slug":"hallucinogen-a-benchmark-for-evaluating","title":"HALLUCINOGEN: A Benchmark for Evaluating Object Hallucination in Large Visual-Language Models","date":"2024-12-29","arxiv_id":"2412.20622","repositories_listed":1,"syntology":null},{"url":"/paper/interacted-object-grounding-in-spatio","slug":"interacted-object-grounding-in-spatio","title":"Interacted Object Grounding in Spatio-Temporal Human-Object Interactions","date":"2024-12-27","arxiv_id":"2412.19542","repositories_listed":1,"syntology":null},{"url":"/paper/long-context-vs-rag-for-llms-an-evaluation","slug":"long-context-vs-rag-for-llms-an-evaluation","title":"Long Context vs. RAG for LLMs: An Evaluation and Revisits","date":"2024-12-27","arxiv_id":"2501.01880","repositories_listed":1,"syntology":null},{"url":"/paper/cypherbench-towards-precise-retrieval-over","slug":"cypherbench-towards-precise-retrieval-over","title":"CypherBench: Towards Precise Retrieval over Full-scale Modern Knowledge Graphs in the LLM Era","date":"2024-12-24","arxiv_id":"2412.18702","repositories_listed":1,"syntology":null},{"url":"/paper/harnessing-large-language-models-for-1","slug":"harnessing-large-language-models-for-1","title":"Harnessing Large Language Models for Knowledge Graph Question Answering via Adaptive Multi-Aspect Retrieval-Augmentation","date":"2024-12-24","arxiv_id":"2412.18537","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":3,"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/harnessing-large-language-models-for-1#ran","syntology_url":"https://syntology.ai/paper/2412.18537","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.18537"}},"official":{"repos":["Applied-Machine-Learning-Lab/AMAR"],"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/linin-logic-integrated-neural-inference","slug":"linin-logic-integrated-neural-inference","title":"LININ: Logic Integrated Neural Inference Network for Explanatory Visual Question Answering","date":"2024-12-24","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/longdocurl-a-comprehensive-multimodal-long","slug":"longdocurl-a-comprehensive-multimodal-long","title":"LongDocURL: a Comprehensive Multimodal Long Document Benchmark Integrating Understanding, Reasoning, and Locating","date":"2024-12-24","arxiv_id":"2412.18424","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/longdocurl-a-comprehensive-multimodal-long#ran","syntology_url":"https://syntology.ai/paper/2412.18424","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.18424"}},"official":{"repos":["dengc2023/longdocurl"],"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/property-enhanced-instruction-tuning-for","slug":"property-enhanced-instruction-tuning-for","title":"Property Enhanced Instruction Tuning for Multi-task Molecule Generation with Large Language Models","date":"2024-12-24","arxiv_id":"2412.18084","repositories_listed":1,"syntology":null},{"url":"/paper/video-panda-parameter-efficient-alignment-for","slug":"video-panda-parameter-efficient-alignment-for","title":"Video-Panda: Parameter-efficient Alignment for Encoder-free Video-Language Models","date":"2024-12-24","arxiv_id":"2412.18609","repositories_listed":1,"syntology":null},{"url":"/paper/from-models-to-microtheories-distilling-a","slug":"from-models-to-microtheories-distilling-a","title":"From Models to Microtheories: Distilling a Model's Topical Knowledge for Grounded Question Answering","date":"2024-12-23","arxiv_id":"2412.17701","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-preference-data-synthetic","slug":"multimodal-preference-data-synthetic","title":"Multimodal Preference Data Synthetic Alignment with Reward Model","date":"2024-12-23","arxiv_id":"2412.17417","repositories_listed":1,"syntology":null},{"url":"/paper/resource-aware-arabic-llm-creation-model","slug":"resource-aware-arabic-llm-creation-model","title":"Resource-Aware Arabic LLM Creation: Model Adaptation, Integration, and Multi-Domain Testing","date":"2024-12-23","arxiv_id":"2412.17548","repositories_listed":1,"syntology":null},{"url":"/paper/vidctx-context-aware-video-question-answering","slug":"vidctx-context-aware-video-question-answering","title":"VidCtx: Context-aware Video Question Answering with Image Models","date":"2024-12-23","arxiv_id":"2412.17415","repositories_listed":1,"syntology":null},{"url":"/paper/friendsqa-a-new-large-scale-deep-video","slug":"friendsqa-a-new-large-scale-deep-video","title":"FriendsQA: A New Large-Scale Deep Video Understanding Dataset with Fine-grained Topic Categorization for Story Videos","date":"2024-12-22","arxiv_id":"2412.17022","repositories_listed":1,"syntology":null},{"url":"/paper/mintqa-a-multi-hop-question-answering","slug":"mintqa-a-multi-hop-question-answering","title":"MINTQA: A Multi-Hop Question Answering Benchmark for Evaluating LLMs on New and Tail Knowledge","date":"2024-12-22","arxiv_id":"2412.17032","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-end-to-end-vlms-leveraging","slug":"beyond-end-to-end-vlms-leveraging","title":"Beyond End-to-End VLMs: Leveraging Intermediate Text Representations for Superior Flowchart Understanding","date":"2024-12-21","arxiv_id":"2412.16420","repositories_listed":1,"syntology":null},{"url":"/paper/dragonverseqa-open-domain-long-form-context","slug":"dragonverseqa-open-domain-long-form-context","title":"DragonVerseQA: Open-Domain Long-Form Context-Aware Question-Answering","date":"2024-12-21","arxiv_id":"2412.16694","repositories_listed":1,"syntology":null},{"url":"/paper/silvar-speech-driven-multimodal-model-for","slug":"silvar-speech-driven-multimodal-model-for","title":"SilVar: Speech Driven Multimodal Model for Reasoning Visual Question Answering and Object Localization","date":"2024-12-21","arxiv_id":"2412.16771","repositories_listed":1,"syntology":null},{"url":"/paper/contrastive-learning-for-task-independent","slug":"contrastive-learning-for-task-independent","title":"Contrastive Learning for Task-Independent SpeechLLM-Pretraining","date":"2024-12-20","arxiv_id":"2412.15712","repositories_listed":1,"syntology":null},{"url":"/paper/autotrust-benchmarking-trustworthiness-in","slug":"autotrust-benchmarking-trustworthiness-in","title":"AutoTrust: Benchmarking Trustworthiness in Large Vision Language Models for Autonomous Driving","date":"2024-12-19","arxiv_id":"2412.15206","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"6 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; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/autotrust-benchmarking-trustworthiness-in#ran","syntology_url":"https://syntology.ai/paper/2412.15206","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.15206"}},"official":{"repos":["taco-group/autotrust"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/defeasible-visual-entailment-benchmark","slug":"defeasible-visual-entailment-benchmark","title":"Defeasible Visual Entailment: Benchmark, Evaluator, and Reward-Driven Optimization","date":"2024-12-19","arxiv_id":"2412.16232","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-hypothetical-summary-for-retrieval","slug":"multimodal-hypothetical-summary-for-retrieval","title":"Multimodal Hypothetical Summary for Retrieval-based Multi-image Question Answering","date":"2024-12-19","arxiv_id":"2412.14880","repositories_listed":1,"syntology":null},{"url":"/paper/unveiling-uncertainty-a-deep-dive-into","slug":"unveiling-uncertainty-a-deep-dive-into","title":"Unveiling Uncertainty: A Deep Dive into Calibration and Performance of Multimodal Large Language Models","date":"2024-12-19","arxiv_id":"2412.14660","repositories_listed":1,"syntology":null},{"url":"/paper/cad-recode-reverse-engineering-cad-code-from","slug":"cad-recode-reverse-engineering-cad-code-from","title":"CAD-Recode: Reverse Engineering CAD Code from Point Clouds","date":"2024-12-18","arxiv_id":"2412.14042","repositories_listed":1,"syntology":null},{"url":"/paper/consistency-of-compositional-generalization","slug":"consistency-of-compositional-generalization","title":"Consistency of Compositional Generalization across Multiple Levels","date":"2024-12-18","arxiv_id":"2412.13636","repositories_listed":1,"syntology":null},{"url":"/paper/knowledge-editing-with-dynamic-knowledge","slug":"knowledge-editing-with-dynamic-knowledge","title":"Knowledge Editing with Dynamic Knowledge Graphs for Multi-Hop Question Answering","date":"2024-12-18","arxiv_id":"2412.13782","repositories_listed":1,"syntology":null},{"url":"/paper/medcot-medical-chain-of-thought-via","slug":"medcot-medical-chain-of-thought-via","title":"MedCoT: Medical Chain of Thought via Hierarchical Expert","date":"2024-12-18","arxiv_id":"2412.13736","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/medcot-medical-chain-of-thought-via#ran","syntology_url":"https://syntology.ai/paper/2412.13736","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.13736"}},"official":{"repos":["jxliu-ai/medcot"],"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/racquet-unveiling-the-dangers-of-overlooked","slug":"racquet-unveiling-the-dangers-of-overlooked","title":"RACQUET: Unveiling the Dangers of Overlooked Referential Ambiguity in Visual LLMs","date":"2024-12-18","arxiv_id":"2412.13835","repositories_listed":1,"syntology":null},{"url":"/paper/thinking-in-space-how-multimodal-large","slug":"thinking-in-space-how-multimodal-large","title":"Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces","date":"2024-12-18","arxiv_id":"2412.14171","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/thinking-in-space-how-multimodal-large#ran","syntology_url":"https://syntology.ai/paper/2412.14171","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.14171"}},"official":{"repos":["vision-x-nyu/thinking-in-space"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/exit-context-aware-extractive-compression-for","slug":"exit-context-aware-extractive-compression-for","title":"EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generation","date":"2024-12-17","arxiv_id":"2412.12559","repositories_listed":1,"syntology":null},{"url":"/paper/medmax-mixed-modal-instruction-tuning-for","slug":"medmax-mixed-modal-instruction-tuning-for","title":"MedMax: Mixed-Modal Instruction Tuning for Training Biomedical Assistants","date":"2024-12-17","arxiv_id":"2412.12661","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-structural-memory-of-llm-agents","slug":"on-the-structural-memory-of-llm-agents","title":"On the Structural Memory of LLM Agents","date":"2024-12-17","arxiv_id":"2412.15266","repositories_listed":1,"syntology":null},{"url":"/paper/simgrag-leveraging-similar-subgraphs-for","slug":"simgrag-leveraging-similar-subgraphs-for","title":"SimGRAG: Leveraging Similar Subgraphs for Knowledge Graphs Driven Retrieval-Augmented Generation","date":"2024-12-17","arxiv_id":"2412.15272","repositories_listed":1,"syntology":null},{"url":"/paper/track-the-answer-extending-textvqa-from-image","slug":"track-the-answer-extending-textvqa-from-image","title":"Track the Answer: Extending TextVQA from Image to Video with Spatio-Temporal Clues","date":"2024-12-17","arxiv_id":"2412.12502","repositories_listed":1,"syntology":null},{"url":"/paper/bioragent-a-retrieval-augmented-generation","slug":"bioragent-a-retrieval-augmented-generation","title":"BioRAGent: A Retrieval-Augmented Generation System for Showcasing Generative Query Expansion and Domain-Specific Search for Scientific Q&A","date":"2024-12-16","arxiv_id":"2412.12358","repositories_listed":1,"syntology":null},{"url":"/paper/darwin-1-5-large-language-models-as-materials","slug":"darwin-1-5-large-language-models-as-materials","title":"DARWIN 1.5: Large Language Models as Materials Science Adapted Learners","date":"2024-12-16","arxiv_id":"2412.11970","repositories_listed":1,"syntology":null},{"url":"/paper/scitat-a-question-answering-benchmark-for","slug":"scitat-a-question-answering-benchmark-for","title":"SCITAT: A Question Answering Benchmark for Scientific Tables and Text Covering Diverse Reasoning Types","date":"2024-12-16","arxiv_id":"2412.11757","repositories_listed":1,"syntology":null},{"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/medg-krp-medical-graph-knowledge","slug":"medg-krp-medical-graph-knowledge","title":"MedG-KRP: Medical Graph Knowledge Representation Probing","date":"2024-12-14","arxiv_id":"2412.10982","repositories_listed":1,"syntology":null},{"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/lost-in-the-middle-and-in-between-enhancing","slug":"lost-in-the-middle-and-in-between-enhancing","title":"Lost in the Middle, and In-Between: Enhancing Language Models' Ability to Reason Over Long Contexts in Multi-Hop QA","date":"2024-12-13","arxiv_id":"2412.10079","repositories_listed":1,"syntology":null},{"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/multi-scale-heterogeneous-text-attributed","slug":"multi-scale-heterogeneous-text-attributed","title":"Multi-Scale Heterogeneous Text-Attributed Graph Datasets From Diverse Domains","date":"2024-12-12","arxiv_id":"2412.08937","repositories_listed":1,"syntology":null},{"url":"/paper/neptune-the-long-orbit-to-benchmarking-long","slug":"neptune-the-long-orbit-to-benchmarking-long","title":"Neptune: The Long Orbit to Benchmarking Long Video Understanding","date":"2024-12-12","arxiv_id":"2412.09582","repositories_listed":1,"syntology":null},{"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/unifying-ai-tutor-evaluation-an-evaluation","slug":"unifying-ai-tutor-evaluation-an-evaluation","title":"Unifying AI Tutor Evaluation: An Evaluation Taxonomy for Pedagogical Ability Assessment of LLM-Powered AI Tutors","date":"2024-12-12","arxiv_id":"2412.09416","repositories_listed":1,"syntology":null},{"url":"/paper/discrete-subgraph-sampling-for-interpretable","slug":"discrete-subgraph-sampling-for-interpretable","title":"Discrete Subgraph Sampling for Interpretable Graph based Visual Question Answering","date":"2024-12-11","arxiv_id":"2412.08263","repositories_listed":1,"syntology":null},{"url":"/paper/illusory-vqa-benchmarking-and-enhancing","slug":"illusory-vqa-benchmarking-and-enhancing","title":"Illusory VQA: Benchmarking and Enhancing Multimodal Models on Visual Illusions","date":"2024-12-11","arxiv_id":"2412.08169","repositories_listed":1,"syntology":null},{"url":"/paper/progressive-multi-granular-alignments-for","slug":"progressive-multi-granular-alignments-for","title":"Progressive Multi-granular Alignments for Grounded Reasoning in Large Vision-Language Models","date":"2024-12-11","arxiv_id":"2412.08125","repositories_listed":1,"syntology":null},{"url":"/paper/bimedix2-bio-medical-expert-lmm-for-diverse","slug":"bimedix2-bio-medical-expert-lmm-for-diverse","title":"BiMediX2: Bio-Medical EXpert LMM for Diverse Medical Modalities","date":"2024-12-10","arxiv_id":"2412.07769","repositories_listed":1,"syntology":null},{"url":"/paper/impact-a-large-scale-integrated-multimodal","slug":"impact-a-large-scale-integrated-multimodal","title":"IMPACT: A Large-scale Integrated Multimodal Patent Analysis and Creation Dataset for Design Patents","date":"2024-12-10","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/mm-poe-multiple-choice-reasoning-via-process","slug":"mm-poe-multiple-choice-reasoning-via-process","title":"MM-PoE: Multiple Choice Reasoning via. Process of Elimination using Multi-Modal Models","date":"2024-12-10","arxiv_id":"2412.07148","repositories_listed":1,"syntology":null},{"url":"/paper/fm2ds-few-shot-multimodal-multihop-data","slug":"fm2ds-few-shot-multimodal-multihop-data","title":"FM2DS: Few-Shot Multimodal Multihop Data Synthesis with Knowledge Distillation for Question Answering","date":"2024-12-09","arxiv_id":"2412.07030","repositories_listed":1,"syntology":null},{"url":"/paper/llava-spacesgg-visual-instruct-tuning-for","slug":"llava-spacesgg-visual-instruct-tuning-for","title":"LLaVA-SpaceSGG: Visual Instruct Tuning for Open-vocabulary Scene Graph Generation with Enhanced Spatial Relations","date":"2024-12-09","arxiv_id":"2412.06322","repositories_listed":1,"syntology":null},{"url":"/paper/pediabench-a-comprehensive-chinese-pediatric","slug":"pediabench-a-comprehensive-chinese-pediatric","title":"PediaBench: A Comprehensive Chinese Pediatric Dataset for Benchmarking Large Language Models","date":"2024-12-09","arxiv_id":"2412.06287","repositories_listed":1,"syntology":null},{"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/kg-retriever-efficient-knowledge-indexing-for","slug":"kg-retriever-efficient-knowledge-indexing-for","title":"KG-Retriever: Efficient Knowledge Indexing for Retrieval-Augmented Large Language Models","date":"2024-12-07","arxiv_id":"2412.05547","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"0 ran · 3 unverified","sample_list":"/paper/kg-retriever-efficient-knowledge-indexing-for#ran","syntology_url":"https://syntology.ai/paper/2412.05547","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.05547"}},"official":{"repos":["bai-lab/kg-retriever"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/rsunivlm-a-unified-vision-language-model-for","slug":"rsunivlm-a-unified-vision-language-model-for","title":"RSUniVLM: A Unified Vision Language Model for Remote Sensing via Granularity-oriented Mixture of Experts","date":"2024-12-07","arxiv_id":"2412.05679","repositories_listed":1,"syntology":null},{"url":"/paper/taco-learning-multi-modal-action-models-with","slug":"taco-learning-multi-modal-action-models-with","title":"TACO: Learning Multi-modal Action Models with Synthetic Chains-of-Thought-and-Action","date":"2024-12-07","arxiv_id":"2412.05479","repositories_listed":1,"syntology":null},{"url":"/paper/give-me-some-hard-questions-synthetic-data","slug":"give-me-some-hard-questions-synthetic-data","title":"Give me Some Hard Questions: Synthetic Data Generation for Clinical QA","date":"2024-12-05","arxiv_id":"2412.04573","repositories_listed":1,"syntology":null},{"url":"/paper/synfintabs-a-dataset-of-synthetic-financial","slug":"synfintabs-a-dataset-of-synthetic-financial","title":"SynFinTabs: A Dataset of Synthetic Financial Tables for Information and Table Extraction","date":"2024-12-05","arxiv_id":"2412.04262","repositories_listed":1,"syntology":null},{"url":"/paper/copy-move-forgery-detection-and-question","slug":"copy-move-forgery-detection-and-question","title":"Copy-Move Forgery Detection and Question Answering for Remote Sensing Image","date":"2024-12-03","arxiv_id":"2412.02575","repositories_listed":1,"syntology":null},{"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/gracefully-filtering-backdoor-samples-for","slug":"gracefully-filtering-backdoor-samples-for","title":"Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining","date":"2024-12-03","arxiv_id":"2412.02454","repositories_listed":1,"syntology":null},{"url":"/paper/eyes-on-the-road-state-of-the-art-video","slug":"eyes-on-the-road-state-of-the-art-video","title":"Eyes on the Road: State-of-the-Art Video Question Answering Models Assessment for Traffic Monitoring Tasks","date":"2024-12-02","arxiv_id":"2412.01132","repositories_listed":1,"syntology":null},{"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/physgame-uncovering-physical-commonsense-1","slug":"physgame-uncovering-physical-commonsense-1","title":"PhysGame: Uncovering Physical Commonsense Violations in Gameplay Videos","date":"2024-12-02","arxiv_id":"2412.01800","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-the-abilities-of-large-language","slug":"exploring-the-abilities-of-large-language","title":"KnowledgePrompts: Exploring the Abilities of Large Language Models to Solve Proportional Analogies via Knowledge-Enhanced Prompting","date":"2024-12-01","arxiv_id":"2412.00869","repositories_listed":1,"syntology":null},{"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/dlava-document-language-and-vision-assistant","slug":"dlava-document-language-and-vision-assistant","title":"DLaVA: Document Language and Vision Assistant for Answer Localization with Enhanced Interpretability and Trustworthiness","date":"2024-11-29","arxiv_id":"2412.00151","repositories_listed":1,"syntology":null},{"url":"/paper/perla-perceptive-3d-language-assistant","slug":"perla-perceptive-3d-language-assistant","title":"PerLA: Perceptive 3D Language Assistant","date":"2024-11-29","arxiv_id":"2411.19774","repositories_listed":1,"syntology":null},{"url":"/paper/sure-vqa-systematic-understanding-of","slug":"sure-vqa-systematic-understanding-of","title":"SURE-VQA: Systematic Understanding of Robustness Evaluation in Medical VQA Tasks","date":"2024-11-29","arxiv_id":"2411.19688","repositories_listed":1,"syntology":null},{"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/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/drs-deep-question-reformulation-with","slug":"drs-deep-question-reformulation-with","title":"DRS: Deep Question Reformulation With Structured Output","date":"2024-11-27","arxiv_id":"2411.17993","repositories_listed":1,"syntology":null},{"url":"/paper/genequery-a-general-qa-based-framework-for","slug":"genequery-a-general-qa-based-framework-for","title":"GeneQuery: A General QA-based Framework for Spatial Gene Expression Predictions from Histology Images","date":"2024-11-27","arxiv_id":"2411.18391","repositories_listed":1,"syntology":null},{"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/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/grounding-iqa-multimodal-language-grounding","slug":"grounding-iqa-multimodal-language-grounding","title":"Grounding-IQA: Multimodal Language Grounding Model for Image Quality Assessment","date":"2024-11-26","arxiv_id":"2411.17237","repositories_listed":1,"syntology":null},{"url":"/paper/path-rag-knowledge-guided-key-region","slug":"path-rag-knowledge-guided-key-region","title":"Path-RAG: Knowledge-Guided Key Region Retrieval for Open-ended Pathology Visual Question Answering","date":"2024-11-26","arxiv_id":"2411.17073","repositories_listed":1,"syntology":null},{"url":"/paper/scaling-speech-text-pre-training-with","slug":"scaling-speech-text-pre-training-with","title":"Scaling Speech-Text Pre-training with Synthetic Interleaved Data","date":"2024-11-26","arxiv_id":"2411.17607","repositories_listed":1,"syntology":null},{"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/context-awareness-gate-for-retrieval","slug":"context-awareness-gate-for-retrieval","title":"Context Awareness Gate For Retrieval Augmented Generation","date":"2024-11-25","arxiv_id":"2411.16133","repositories_listed":1,"syntology":null},{"url":"/paper/document-haystacks-vision-language-reasoning","slug":"document-haystacks-vision-language-reasoning","title":"Document Haystacks: Vision-Language Reasoning Over Piles of 1000+ Documents","date":"2024-11-23","arxiv_id":"2411.16740","repositories_listed":1,"syntology":null},{"url":"/paper/seed-free-synthetic-data-generation-framework","slug":"seed-free-synthetic-data-generation-framework","title":"Seed-Free Synthetic Data Generation Framework for Instruction-Tuning LLMs: A Case Study in Thai","date":"2024-11-23","arxiv_id":"2411.15484","repositories_listed":1,"syntology":null},{"url":"/paper/kbada-efficient-self-adaptation-on-specific","slug":"kbada-efficient-self-adaptation-on-specific","title":"KBAlign: Efficient Self Adaptation on Specific Knowledge Bases","date":"2024-11-22","arxiv_id":"2411.14790","repositories_listed":1,"syntology":null},{"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/visual-contexts-clarify-ambiguous-expressions","slug":"visual-contexts-clarify-ambiguous-expressions","title":"Visual Contexts Clarify Ambiguous Expressions: A Benchmark Dataset","date":"2024-11-21","arxiv_id":"2411.14137","repositories_listed":1,"syntology":null},{"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"]}}}],"record_sha256":"a4faa80307e6a9e1bcabdbfac1f7e4a0baae08b7d9ee6673fa4dac793c0b14f8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}