{"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/language-modelling/papers/20","list_of":"/task/language-modelling","task":"Language Modelling","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":20,"pages_in_order":177,"rows_per_page":100,"rows":[1901,2000],"of":17610,"counts":{"archive_papers_tagged":17610,"with_a_code_link":7012,"where_syntology_ran_a_sample":2428,"not_listed_spam_title":0,"listed":17610,"listed_where_code_ran":2428,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2027,"every_run_a_failure_of_syntologys_instrument":401,"listed_with_a_run_with_no_instrument_failure":2027,"listed_every_run_a_failure_of_syntologys_instrument":401,"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/language-modelling","prev":"/task/language-modelling/papers/19","next":"/task/language-modelling/papers/21","papers":[{"url":"/paper/large-language-models-as-realistic","slug":"large-language-models-as-realistic","title":"Large Language Models as Realistic Microservice Trace Generators","date":"2024-12-16","arxiv_id":"2502.17439","repositories_listed":1,"syntology":null},{"url":"/paper/llms-can-simulate-standardized-patients-via","slug":"llms-can-simulate-standardized-patients-via","title":"LLMs Can Simulate Standardized Patients via Agent Coevolution","date":"2024-12-16","arxiv_id":"2412.11716","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":14,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/llms-can-simulate-standardized-patients-via#ran","syntology_url":"https://syntology.ai/paper/2412.11716","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.11716"}},"official":{"repos":["zjumai/evopatient"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/next-token-prediction-towards-multimodal","slug":"next-token-prediction-towards-multimodal","title":"Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey","date":"2024-12-16","arxiv_id":"2412.18619","repositories_listed":1,"syntology":null},{"url":"/paper/personalized-llm-for-generating-customized","slug":"personalized-llm-for-generating-customized","title":"Personalized LLM for Generating Customized Responses to the Same Query from Different Users","date":"2024-12-16","arxiv_id":"2412.11736","repositories_listed":1,"syntology":null},{"url":"/paper/sepllm-accelerate-large-language-models-by","slug":"sepllm-accelerate-large-language-models-by","title":"SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator","date":"2024-12-16","arxiv_id":"2412.12094","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/sepllm-accelerate-large-language-models-by#ran","syntology_url":"https://syntology.ai/paper/2412.12094","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.12094"}},"official":{"repos":["HKUDS/SepLLM"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/learning-to-verify-summary-facts-with-fine","slug":"learning-to-verify-summary-facts-with-fine","title":"Learning to Verify Summary Facts with Fine-Grained LLM Feedback","date":"2024-12-14","arxiv_id":"2412.10689","repositories_listed":1,"syntology":null},{"url":"/paper/b-vllm-a-vision-large-language-model-with","slug":"b-vllm-a-vision-large-language-model-with","title":"B-VLLM: A Vision Large Language Model with Balanced Spatio-Temporal Tokens","date":"2024-12-13","arxiv_id":"2412.09919","repositories_listed":1,"syntology":null},{"url":"/paper/from-allies-to-adversaries-manipulating-llm","slug":"from-allies-to-adversaries-manipulating-llm","title":"From Allies to Adversaries: Manipulating LLM Tool-Calling through Adversarial Injection","date":"2024-12-13","arxiv_id":"2412.10198","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"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) · 2 unverified","sample_list":"/paper/from-allies-to-adversaries-manipulating-llm#ran","syntology_url":"https://syntology.ai/paper/2412.10198","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.10198"}},"official":{"repos":["anonymous-lgtm/toolcommander"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/wisead-knowledge-augmented-end-to-end","slug":"wisead-knowledge-augmented-end-to-end","title":"WiseAD: Knowledge Augmented End-to-End Autonomous Driving with Vision-Language Model","date":"2024-12-13","arxiv_id":"2412.09951","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":5,"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/wisead-knowledge-augmented-end-to-end#ran","syntology_url":"https://syntology.ai/paper/2412.09951","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.09951"}},"official":{"repos":["wyddmw/WiseAD"],"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/phi-4-technical-report","slug":"phi-4-technical-report","title":"Phi-4 Technical Report","date":"2024-12-12","arxiv_id":"2412.08905","repositories_listed":1,"syntology":null},{"url":"/paper/regulation-of-language-models-with","slug":"regulation-of-language-models-with","title":"Regulation of Language Models With Interpretability Will Likely Result In A Performance Trade-Off","date":"2024-12-12","arxiv_id":"2412.12169","repositories_listed":1,"syntology":null},{"url":"/paper/sprec-leveraging-self-play-to-debias","slug":"sprec-leveraging-self-play-to-debias","title":"SPRec: Leveraging Self-Play to Debias Preference Alignment for Large Language Model-based Recommendations","date":"2024-12-12","arxiv_id":"2412.09243","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":9,"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) · 2 unverified","sample_list":"/paper/sprec-leveraging-self-play-to-debias#ran","syntology_url":"https://syntology.ai/paper/2412.09243","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.09243"}},"official":{"repos":["regionch/sprec"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"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/concept-bottleneck-large-language-models","slug":"concept-bottleneck-large-language-models","title":"Concept Bottleneck Large Language Models","date":"2024-12-11","arxiv_id":"2412.07992","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/concept-bottleneck-large-language-models#ran","syntology_url":"https://syntology.ai/paper/2412.07992","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.07992"}},"official":{"repos":["trustworthy-ml-lab/cb-llms"],"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/large-concept-models-language-modeling-in-a","slug":"large-concept-models-language-modeling-in-a","title":"Large Concept Models: Language Modeling in a Sentence Representation Space","date":"2024-12-11","arxiv_id":"2412.08821","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/large-concept-models-language-modeling-in-a#ran","syntology_url":"https://syntology.ai/paper/2412.08821","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.08821"}},"official":{"repos":["facebookresearch/large_concept_model"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/multimodal-latent-language-modeling-with-next","slug":"multimodal-latent-language-modeling-with-next","title":"Multimodal Latent Language Modeling with Next-Token Diffusion","date":"2024-12-11","arxiv_id":"2412.08635","repositories_listed":1,"syntology":null},{"url":"/paper/nyayaanumana-inlegalllama-the-largest-indian","slug":"nyayaanumana-inlegalllama-the-largest-indian","title":"NyayaAnumana & INLegalLlama: The Largest Indian Legal Judgment Prediction Dataset and Specialized Language Model for Enhanced Decision Analysis","date":"2024-12-11","arxiv_id":"2412.08385","repositories_listed":1,"syntology":null},{"url":"/paper/predicting-human-brain-states-with","slug":"predicting-human-brain-states-with","title":"Predicting Human Brain States with Transformer","date":"2024-12-11","arxiv_id":"2412.19814","repositories_listed":1,"syntology":null},{"url":"/paper/template-matters-understanding-the-role-of","slug":"template-matters-understanding-the-role-of","title":"Template Matters: Understanding the Role of Instruction Templates in Multimodal Language Model Evaluation and Training","date":"2024-12-11","arxiv_id":"2412.08307","repositories_listed":1,"syntology":null},{"url":"/paper/active-inference-for-self-organizing-multi","slug":"active-inference-for-self-organizing-multi","title":"Active Inference for Self-Organizing Multi-LLM Systems: A Bayesian Thermodynamic Approach to Adaptation","date":"2024-12-10","arxiv_id":"2412.10425","repositories_listed":1,"syntology":null},{"url":"/paper/bayesian-optimization-of-antibodies-informed","slug":"bayesian-optimization-of-antibodies-informed","title":"Bayesian Optimization of Antibodies Informed by a Generative Model of Evolving Sequences","date":"2024-12-10","arxiv_id":"2412.07763","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"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) · 3 unverified","sample_list":"/paper/bayesian-optimization-of-antibodies-informed#ran","syntology_url":"https://syntology.ai/paper/2412.07763","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.07763"}},"official":{"repos":["alannawzadamin/clonebo"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/coprus-consistency-preserving-utterance","slug":"coprus-consistency-preserving-utterance","title":"CoPrUS: Consistency Preserving Utterance Synthesis towards more realistic benchmark dialogues","date":"2024-12-10","arxiv_id":"2412.07515","repositories_listed":1,"syntology":null},{"url":"/paper/granite-guardian","slug":"granite-guardian","title":"Granite Guardian","date":"2024-12-10","arxiv_id":"2412.07724","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/granite-guardian#ran","syntology_url":"https://syntology.ai/paper/2412.07724","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.07724"}},"official":{"repos":["ibm-granite/granite-guardian"],"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/intellectseeker-a-personalized-literature","slug":"intellectseeker-a-personalized-literature","title":"IntellectSeeker: A Personalized Literature Management System with the Probabilistic Model and Large Language Model","date":"2024-12-10","arxiv_id":"2412.07213","repositories_listed":1,"syntology":null},{"url":"/paper/neural-scaling-laws-rooted-in-the-data","slug":"neural-scaling-laws-rooted-in-the-data","title":"Neural Scaling Laws Rooted in the Data Distribution","date":"2024-12-10","arxiv_id":"2412.07942","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/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/c-2-leva-toward-comprehensive-and","slug":"c-2-leva-toward-comprehensive-and","title":"C$^2$LEVA: Toward Comprehensive and Contamination-Free Language Model Evaluation","date":"2024-12-06","arxiv_id":"2412.04947","repositories_listed":1,"syntology":null},{"url":"/paper/dart-eval-a-comprehensive-dna-language-model","slug":"dart-eval-a-comprehensive-dna-language-model","title":"DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA","date":"2024-12-06","arxiv_id":"2412.05430","repositories_listed":1,"syntology":{"n":16,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":16,"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) · 5 unverified","sample_list":"/paper/dart-eval-a-comprehensive-dna-language-model#ran","syntology_url":"https://syntology.ai/paper/2412.05430","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.05430"}},"official":{"repos":["kundajelab/dart-eval"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/expanding-performance-boundaries-of-open","slug":"expanding-performance-boundaries-of-open","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","date":"2024-12-06","arxiv_id":"2412.05271","repositories_listed":1,"syntology":{"n":9,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":8,"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) · 8 unverified","sample_list":"/paper/expanding-performance-boundaries-of-open#ran","syntology_url":"https://syntology.ai/paper/2412.05271","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.05271"}},"official":{"repos":["opengvlab/internvl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/gla-ai4biomed-at-rrg24-visual-instruction","slug":"gla-ai4biomed-at-rrg24-visual-instruction","title":"Gla-AI4BioMed at RRG24: Visual Instruction-tuned Adaptation for Radiology Report Generation","date":"2024-12-06","arxiv_id":"2412.04954","repositories_listed":1,"syntology":null},{"url":"/paper/linvt-empower-your-image-level-large-language","slug":"linvt-empower-your-image-level-large-language","title":"LinVT: Empower Your Image-level Large Language Model to Understand Videos","date":"2024-12-06","arxiv_id":"2412.05185","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":2,"n_honours":2,"n_violates":1,"n_no_contract":6,"n_pointer_only":12,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 1 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/linvt-empower-your-image-level-large-language#ran","syntology_url":"https://syntology.ai/paper/2412.05185","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.05185"}},"official":{"repos":["gls0425/linvt"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/smoothie-label-free-language-model-routing","slug":"smoothie-label-free-language-model-routing","title":"Smoothie: Label Free Language Model Routing","date":"2024-12-06","arxiv_id":"2412.04692","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":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) · 0 unverified","sample_list":"/paper/smoothie-label-free-language-model-routing#ran","syntology_url":"https://syntology.ai/paper/2412.04692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.04692"}},"official":{"repos":["hazyresearch/smoothie"],"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/transformers-can-navigate-mazes-with-multi","slug":"transformers-can-navigate-mazes-with-multi","title":"Transformers Can Navigate Mazes With Multi-Step Prediction","date":"2024-12-06","arxiv_id":"2412.05117","repositories_listed":1,"syntology":null},{"url":"/paper/aligned-music-notation-and-lyrics","slug":"aligned-music-notation-and-lyrics","title":"Aligned Music Notation and Lyrics Transcription","date":"2024-12-05","arxiv_id":"2412.04217","repositories_listed":1,"syntology":null},{"url":"/paper/liquid-language-models-are-scalable-multi","slug":"liquid-language-models-are-scalable-multi","title":"Liquid: Language Models are Scalable Multi-modal Generators","date":"2024-12-05","arxiv_id":"2412.04332","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/liquid-language-models-are-scalable-multi#ran","syntology_url":"https://syntology.ai/paper/2412.04332","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.04332"}},"official":{"repos":["foundationvision/liquid"],"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","unlocated"]}}},{"url":"/paper/mind-effective-incorrect-assignment-detection","slug":"mind-effective-incorrect-assignment-detection","title":"MIND: Effective Incorrect Assignment Detection through a Multi-Modal Structure-Enhanced Language Model","date":"2024-12-05","arxiv_id":"2412.03930","repositories_listed":1,"syntology":null},{"url":"/paper/misr-measuring-instrumental-self-reasoning-in","slug":"misr-measuring-instrumental-self-reasoning-in","title":"MISR: Measuring Instrumental Self-Reasoning in Frontier Models","date":"2024-12-05","arxiv_id":"2412.03904","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-hidden-computations-in-chain-of","slug":"understanding-hidden-computations-in-chain-of","title":"Understanding Hidden Computations in Chain-of-Thought Reasoning","date":"2024-12-05","arxiv_id":"2412.04537","repositories_listed":1,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":14,"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) · 1 unverified","sample_list":"/paper/understanding-hidden-computations-in-chain-of#ran","syntology_url":"https://syntology.ai/paper/2412.04537","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.04537"}},"official":{"repos":["rokosbasilisk/filler_tokens"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/a-surprisal-oracle-for-when-every-layer","slug":"a-surprisal-oracle-for-when-every-layer","title":"A surprisal oracle for when every layer counts","date":"2024-12-04","arxiv_id":"2412.03098","repositories_listed":1,"syntology":null},{"url":"/paper/composed-image-retrieval-for-training-free","slug":"composed-image-retrieval-for-training-free","title":"Composed Image Retrieval for Training-Free Domain Conversion","date":"2024-12-04","arxiv_id":"2412.03297","repositories_listed":1,"syntology":null},{"url":"/paper/fine-grained-behavior-simulation-with-role","slug":"fine-grained-behavior-simulation-with-role","title":"Fine-Grained Behavior Simulation with Role-Playing Large Language Model on Social Media","date":"2024-12-04","arxiv_id":"2412.03148","repositories_listed":1,"syntology":null},{"url":"/paper/from-individual-to-society-a-survey-on-social","slug":"from-individual-to-society-a-survey-on-social","title":"From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents","date":"2024-12-04","arxiv_id":"2412.03563","repositories_listed":1,"syntology":null},{"url":"/paper/paligemma-2-a-family-of-versatile-vlms-for","slug":"paligemma-2-a-family-of-versatile-vlms-for","title":"PaliGemma 2: A Family of Versatile VLMs for Transfer","date":"2024-12-04","arxiv_id":"2412.03555","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/paligemma-2-a-family-of-versatile-vlms-for#ran","syntology_url":"https://syntology.ai/paper/2412.03555","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.03555"}},"official":null}},{"url":"/paper/scaling-inference-time-search-with-vision","slug":"scaling-inference-time-search-with-vision","title":"Scaling Inference-Time Search with Vision Value Model for Improved Visual Comprehension","date":"2024-12-04","arxiv_id":"2412.03704","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/multi-granularity-tibetan-textual-adversarial","slug":"multi-granularity-tibetan-textual-adversarial","title":"Multi-Granularity Tibetan Textual Adversarial Attack Method Based on Masked Language Model","date":"2024-12-03","arxiv_id":"2412.02343","repositories_listed":1,"syntology":null},{"url":"/paper/advancing-speech-language-models-by-scaling","slug":"advancing-speech-language-models-by-scaling","title":"Advancing Speech Language Models by Scaling Supervised Fine-Tuning with Over 60,000 Hours of Synthetic Speech Dialogue Data","date":"2024-12-02","arxiv_id":"2412.01078","repositories_listed":1,"syntology":null},{"url":"/paper/align-kd-distilling-cross-modal-alignment","slug":"align-kd-distilling-cross-modal-alignment","title":"Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Model","date":"2024-12-02","arxiv_id":"2412.01282","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":4,"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/align-kd-distilling-cross-modal-alignment#ran","syntology_url":"https://syntology.ai/paper/2412.01282","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.01282"}},"official":{"repos":["fqhank/align-kd"],"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/data-centric-and-heterogeneity-adaptive","slug":"data-centric-and-heterogeneity-adaptive","title":"FlexSP: Accelerating Large Language Model Training via Flexible Sequence Parallelism","date":"2024-12-02","arxiv_id":"2412.01523","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/data-centric-and-heterogeneity-adaptive#ran","syntology_url":"https://syntology.ai/paper/2412.01523","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.01523"}},"official":null}},{"url":"/paper/hacksynth-llm-agent-and-evaluation-framework","slug":"hacksynth-llm-agent-and-evaluation-framework","title":"HackSynth: LLM Agent and Evaluation Framework for Autonomous Penetration Testing","date":"2024-12-02","arxiv_id":"2412.01778","repositories_listed":1,"syntology":null},{"url":"/paper/mba-rag-a-bandit-approach-for-adaptive","slug":"mba-rag-a-bandit-approach-for-adaptive","title":"MBA-RAG: a Bandit Approach for Adaptive Retrieval-Augmented Generation through Question Complexity","date":"2024-12-02","arxiv_id":"2412.01572","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":0,"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/mba-rag-a-bandit-approach-for-adaptive#ran","syntology_url":"https://syntology.ai/paper/2412.01572","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.01572"}},"official":{"repos":["futureeeeee/mba"],"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/rilq-rank-insensitive-lora-based-quantization","slug":"rilq-rank-insensitive-lora-based-quantization","title":"RILQ: Rank-Insensitive LoRA-based Quantization Error Compensation for Boosting 2-bit Large Language Model Accuracy","date":"2024-12-02","arxiv_id":"2412.01129","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"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) · 3 unverified","sample_list":"/paper/rilq-rank-insensitive-lora-based-quantization#ran","syntology_url":"https://syntology.ai/paper/2412.01129","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.01129"}},"official":{"repos":["aiha-lab/rilq"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/x-prompt-towards-universal-in-context-image","slug":"x-prompt-towards-universal-in-context-image","title":"X-Prompt: Towards Universal In-Context Image Generation in Auto-Regressive Vision Language Foundation Models","date":"2024-12-02","arxiv_id":"2412.01824","repositories_listed":1,"syntology":null},{"url":"/paper/free-and-customizable-code-documentation-with","slug":"free-and-customizable-code-documentation-with","title":"Free and Customizable Code Documentation with LLMs: A Fine-Tuning Approach","date":"2024-12-01","arxiv_id":"2412.00726","repositories_listed":1,"syntology":null},{"url":"/paper/kv-shifting-attention-enhances-language","slug":"kv-shifting-attention-enhances-language","title":"KV Shifting Attention Enhances Language Modeling","date":"2024-11-29","arxiv_id":"2411.19574","repositories_listed":1,"syntology":null},{"url":"/paper/covidllm-a-robust-large-language-model-with","slug":"covidllm-a-robust-large-language-model-with","title":"CovidLLM: A Robust Large Language Model with Missing Value Adaptation and Multi-Objective Learning Strategy for Predicting Disease Severity and Clinical Outcomes in COVID-19 Patients","date":"2024-11-28","arxiv_id":"2412.03593","repositories_listed":1,"syntology":null},{"url":"/paper/aligning-knowledge-concepts-to-whole-slide","slug":"aligning-knowledge-concepts-to-whole-slide","title":"Aligning Knowledge Concepts to Whole Slide Images for Precise Histopathology Image Analysis","date":"2024-11-27","arxiv_id":"2411.18101","repositories_listed":1,"syntology":null},{"url":"/paper/fastswitch-optimizing-context-switching","slug":"fastswitch-optimizing-context-switching","title":"FastSwitch: Optimizing Context Switching Efficiency in Fairness-aware Large Language Model Serving","date":"2024-11-27","arxiv_id":"2411.18424","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-model-brained-gui-agents-a","slug":"large-language-model-brained-gui-agents-a","title":"Large Language Model-Brained GUI Agents: A Survey","date":"2024-11-27","arxiv_id":"2411.18279","repositories_listed":1,"syntology":null},{"url":"/paper/verbalized-representation-learning-for","slug":"verbalized-representation-learning-for","title":"Verbalized Representation Learning for Interpretable Few-Shot Generalization","date":"2024-11-27","arxiv_id":"2411.18651","repositories_listed":1,"syntology":null},{"url":"/paper/longkey-keyphrase-extraction-for-long","slug":"longkey-keyphrase-extraction-for-long","title":"LongKey: Keyphrase Extraction for Long Documents","date":"2024-11-26","arxiv_id":"2411.17863","repositories_listed":1,"syntology":null},{"url":"/paper/motionllama-a-unified-framework-for-motion","slug":"motionllama-a-unified-framework-for-motion","title":"MotionLLaMA: A Unified Framework for Motion Synthesis and Comprehension","date":"2024-11-26","arxiv_id":"2411.17335","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-efficiency-of-nlp-inspired-methods-for","slug":"on-the-efficiency-of-nlp-inspired-methods-for","title":"On the Efficiency of NLP-Inspired Methods for Tabular Deep Learning","date":"2024-11-26","arxiv_id":"2411.17207","repositories_listed":1,"syntology":null},{"url":"/paper/openad-open-world-autonomous-driving","slug":"openad-open-world-autonomous-driving","title":"OpenAD: Open-World Autonomous Driving Benchmark for 3D Object Detection","date":"2024-11-26","arxiv_id":"2411.17761","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/bayling-2-a-multilingual-large-language-model","slug":"bayling-2-a-multilingual-large-language-model","title":"BayLing 2: A Multilingual Large Language Model with Efficient Language Alignment","date":"2024-11-25","arxiv_id":"2411.16300","repositories_listed":1,"syntology":null},{"url":"/paper/when-babies-teach-babies-can-student","slug":"when-babies-teach-babies-can-student","title":"When Babies Teach Babies: Can student knowledge sharing outperform Teacher-Guided Distillation on small datasets?","date":"2024-11-25","arxiv_id":"2411.16487","repositories_listed":1,"syntology":null},{"url":"/paper/can-a-large-language-model-learn-matrix","slug":"can-a-large-language-model-learn-matrix","title":"Can a Large Language Model Learn Matrix Functions In Context?","date":"2024-11-24","arxiv_id":"2411.15675","repositories_listed":1,"syntology":null},{"url":"/paper/generative-context-distillation","slug":"generative-context-distillation","title":"Generative Prompt Internalization","date":"2024-11-24","arxiv_id":"2411.15927","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/generative-context-distillation#ran","syntology_url":"https://syntology.ai/paper/2411.15927","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.15927"}},"official":{"repos":["kaistai/generative-context-distillation"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/is-training-data-quality-or-quantity-more","slug":"is-training-data-quality-or-quantity-more","title":"Is Training Data Quality or Quantity More Impactful to Small Language Model Performance?","date":"2024-11-24","arxiv_id":"2411.15821","repositories_listed":1,"syntology":null},{"url":"/paper/prompthsi-universal-hyperspectral-image","slug":"prompthsi-universal-hyperspectral-image","title":"PromptHSI: Universal Hyperspectral Image Restoration with Vision-Language Modulated Frequency Adaptation","date":"2024-11-24","arxiv_id":"2411.15922","repositories_listed":1,"syntology":{"n":17,"n_ran":17,"n_constructed":0,"n_ran_checked":12,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":11,"n_pointer_only":2,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 1 violated, 11 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/prompthsi-universal-hyperspectral-image#ran","syntology_url":"https://syntology.ai/paper/2411.15922","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.15922"}},"official":{"repos":["chingheng0808/PromptHSI"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/valid-mitigating-the-hallucination-of-large","slug":"valid-mitigating-the-hallucination-of-large","title":"VaLiD: Mitigating the Hallucination of Large Vision Language Models by Visual Layer Fusion Contrastive Decoding","date":"2024-11-24","arxiv_id":"2411.15839","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-model-with-region-guided","slug":"large-language-model-with-region-guided","title":"Large Language Model with Region-guided Referring and Grounding for CT Report Generation","date":"2024-11-23","arxiv_id":"2411.15539","repositories_listed":1,"syntology":null},{"url":"/paper/molmetalm-a-physicochemical-knowledge-guided","slug":"molmetalm-a-physicochemical-knowledge-guided","title":"MolMetaLM: a Physicochemical Knowledge-Guided Molecular Meta Language Model","date":"2024-11-23","arxiv_id":"2411.15500","repositories_listed":1,"syntology":null},{"url":"/paper/multi-label-sequential-sentence","slug":"multi-label-sequential-sentence","title":"Multi-label Sequential Sentence Classification via Large Language Model","date":"2024-11-23","arxiv_id":"2411.15623","repositories_listed":1,"syntology":null},{"url":"/paper/semantic-shield-defending-vision-language-1","slug":"semantic-shield-defending-vision-language-1","title":"Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment","date":"2024-11-23","arxiv_id":"2411.15673","repositories_listed":1,"syntology":null},{"url":"/paper/steering-away-from-harm-an-adaptive-approach","slug":"steering-away-from-harm-an-adaptive-approach","title":"Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks","date":"2024-11-23","arxiv_id":"2411.16721","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/steering-away-from-harm-an-adaptive-approach#ran","syntology_url":"https://syntology.ai/paper/2411.16721","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.16721"}},"official":{"repos":["ASTRAL-Group/ASTRA"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/textit-revelio-interpreting-and-leveraging","slug":"textit-revelio-interpreting-and-leveraging","title":"$\\textit{Revelio}$: Interpreting and leveraging semantic information in diffusion models","date":"2024-11-23","arxiv_id":"2411.16725","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":1,"n_no_contract":3,"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, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/textit-revelio-interpreting-and-leveraging#ran","syntology_url":"https://syntology.ai/paper/2411.16725","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.16725"}},"official":{"repos":["revelio-diffusion/revelio"],"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","unlocated"]}}},{"url":"/paper/revisionllm-recursive-vision-language-model","slug":"revisionllm-recursive-vision-language-model","title":"ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videos","date":"2024-11-22","arxiv_id":"2411.14901","repositories_listed":1,"syntology":null},{"url":"/paper/scribeagent-towards-specialized-web-agents","slug":"scribeagent-towards-specialized-web-agents","title":"ScribeAgent: Towards Specialized Web Agents Using Production-Scale Workflow Data","date":"2024-11-22","arxiv_id":"2411.15004","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/scribeagent-towards-specialized-web-agents#ran","syntology_url":"https://syntology.ai/paper/2411.15004","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.15004"}},"official":{"repos":["colonylabs/ScribeAgent"],"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/tulu-3-pushing-frontiers-in-open-language","slug":"tulu-3-pushing-frontiers-in-open-language","title":"Tulu 3: Pushing Frontiers in Open Language Model Post-Training","date":"2024-11-22","arxiv_id":"2411.15124","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/tulu-3-pushing-frontiers-in-open-language#ran","syntology_url":"https://syntology.ai/paper/2411.15124","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.15124"}},"official":{"repos":["allenai/open-instruct"],"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/drpruning-efficient-large-language-model","slug":"drpruning-efficient-large-language-model","title":"DRPruning: Efficient Large Language Model Pruning through Distributionally Robust Optimization","date":"2024-11-21","arxiv_id":"2411.14055","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/drpruning-efficient-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2411.14055","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.14055"}},"official":{"repos":["hexuandeng/drpruning"],"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","unlocated"]}}},{"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/piors-personalized-intelligent-outpatient","slug":"piors-personalized-intelligent-outpatient","title":"PIORS: Personalized Intelligent Outpatient Reception based on Large Language Model with Multi-Agents Medical Scenario Simulation","date":"2024-11-21","arxiv_id":"2411.13902","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":4,"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) · 4 unverified","sample_list":"/paper/piors-personalized-intelligent-outpatient#ran","syntology_url":"https://syntology.ai/paper/2411.13902","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.13902"}},"official":{"repos":["fudandisc/piors"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/planning-driven-programming-a-large-language","slug":"planning-driven-programming-a-large-language","title":"Planning-Driven Programming: A Large Language Model Programming Workflow","date":"2024-11-21","arxiv_id":"2411.14503","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/planning-driven-programming-a-large-language#ran","syntology_url":"https://syntology.ai/paper/2411.14503","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.14503"}},"official":{"repos":["you68681/lpw"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/semikong-curating-training-and-evaluating-a","slug":"semikong-curating-training-and-evaluating-a","title":"SemiKong: Curating, Training, and Evaluating A Semiconductor Industry-Specific Large Language Model","date":"2024-11-21","arxiv_id":"2411.13802","repositories_listed":1,"syntology":null},{"url":"/paper/unifiedcrawl-aggregated-common-crawl-for","slug":"unifiedcrawl-aggregated-common-crawl-for","title":"UnifiedCrawl: Aggregated Common Crawl for Affordable Adaptation of LLMs on Low-Resource Languages","date":"2024-11-21","arxiv_id":"2411.14343","repositories_listed":1,"syntology":null},{"url":"/paper/why-do-language-models-perform-worse-for","slug":"why-do-language-models-perform-worse-for","title":"Why do language models perform worse for morphologically complex languages?","date":"2024-11-21","arxiv_id":"2411.14198","repositories_listed":1,"syntology":null},{"url":"/paper/reflections-from-the-2024-large-language","slug":"reflections-from-the-2024-large-language","title":"Reflections from the 2024 Large Language Model (LLM) Hackathon for Applications in Materials Science and Chemistry","date":"2024-11-20","arxiv_id":"2411.15221","repositories_listed":1,"syntology":null},{"url":"/paper/robust-planning-with-compound-llm","slug":"robust-planning-with-compound-llm","title":"Robust Planning with Compound LLM Architectures: An LLM-Modulo Approach","date":"2024-11-20","arxiv_id":"2411.14484","repositories_listed":1,"syntology":null},{"url":"/paper/waterpark-a-robustness-assessment-of-language","slug":"waterpark-a-robustness-assessment-of-language","title":"Watermark under Fire: A Robustness Evaluation of LLM Watermarking","date":"2024-11-20","arxiv_id":"2411.13425","repositories_listed":1,"syntology":null},{"url":"/paper/probing-the-capacity-of-language-model-agents","slug":"probing-the-capacity-of-language-model-agents","title":"Probing the Capacity of Language Model Agents to Operationalize Disparate Experiential Context Despite Distraction","date":"2024-11-19","arxiv_id":"2411.12828","repositories_listed":1,"syntology":null},{"url":"/paper/ranking-unraveled-recipes-for-llm-rankings-in","slug":"ranking-unraveled-recipes-for-llm-rankings-in","title":"Ranking Unraveled: Recipes for LLM Rankings in Head-to-Head AI Combat","date":"2024-11-19","arxiv_id":"2411.14483","repositories_listed":1,"syntology":null},{"url":"/paper/selective-attention-enhancing-transformer","slug":"selective-attention-enhancing-transformer","title":"Selective Attention: Enhancing Transformer through Principled Context Control","date":"2024-11-19","arxiv_id":"2411.12892","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":2,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/selective-attention-enhancing-transformer#ran","syntology_url":"https://syntology.ai/paper/2411.12892","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.12892"}},"official":{"repos":["umich-sota/selective_attention"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/does-unlearning-truly-unlearn-a-black-box","slug":"does-unlearning-truly-unlearn-a-black-box","title":"Does Unlearning Truly Unlearn? A Black Box Evaluation of LLM Unlearning Methods","date":"2024-11-18","arxiv_id":"2411.12103","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/does-unlearning-truly-unlearn-a-black-box#ran","syntology_url":"https://syntology.ai/paper/2411.12103","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.12103"}},"official":{"repos":["jaidoshi/knowledge-erasure"],"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/improved-gui-grounding-via-iterative","slug":"improved-gui-grounding-via-iterative","title":"Improved GUI Grounding via Iterative Narrowing","date":"2024-11-18","arxiv_id":"2411.13591","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-mllm-embeddings-and-attribute","slug":"leveraging-mllm-embeddings-and-attribute","title":"Leveraging MLLM Embeddings and Attribute Smoothing for Compositional Zero-Shot Learning","date":"2024-11-18","arxiv_id":"2411.12584","repositories_listed":1,"syntology":null},{"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/preempting-text-sanitization-utility-in","slug":"preempting-text-sanitization-utility-in","title":"Preempting Text Sanitization Utility in Resource-Constrained Privacy-Preserving LLM Interactions","date":"2024-11-18","arxiv_id":"2411.11521","repositories_listed":1,"syntology":null}],"record_sha256":"7225cab7877509726d937652be9365f128737fe7a3926f5b1c51e34db46bb4fa","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}