{"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/21","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":21,"pages_in_order":177,"rows_per_page":100,"rows":[2001,2100],"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/20","next":"/task/language-modelling/papers/22","papers":[{"url":"/paper/topology-aware-preemptive-scheduling-for-co","slug":"topology-aware-preemptive-scheduling-for-co","title":"Topology-aware Preemptive Scheduling for Co-located LLM Workloads","date":"2024-11-18","arxiv_id":"2411.11560","repositories_listed":1,"syntology":null},{"url":"/paper/vl-uncertainty-detecting-hallucination-in","slug":"vl-uncertainty-detecting-hallucination-in","title":"VL-Uncertainty: Detecting Hallucination in Large Vision-Language Model via Uncertainty Estimation","date":"2024-11-18","arxiv_id":"2411.11919","repositories_listed":1,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":6,"n_instrument":5,"n_unverified":3,"n_honours":3,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/vl-uncertainty-detecting-hallucination-in#ran","syntology_url":"https://syntology.ai/paper/2411.11919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.11919"}},"official":null}},{"url":"/paper/biancang-a-traditional-chinese-medicine-large","slug":"biancang-a-traditional-chinese-medicine-large","title":"BianCang: A Traditional Chinese Medicine Large Language Model","date":"2024-11-17","arxiv_id":"2411.11027","repositories_listed":1,"syntology":null},{"url":"/paper/geoground-a-unified-large-vision-language","slug":"geoground-a-unified-large-vision-language","title":"GeoGround: A Unified Large Vision-Language Model for Remote Sensing Visual Grounding","date":"2024-11-16","arxiv_id":"2411.11904","repositories_listed":1,"syntology":null},{"url":"/paper/metala-unified-optimal-linear-approximation","slug":"metala-unified-optimal-linear-approximation","title":"MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map","date":"2024-11-16","arxiv_id":"2411.10741","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/metala-unified-optimal-linear-approximation#ran","syntology_url":"https://syntology.ai/paper/2411.10741","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.10741"}},"official":{"repos":["BICLab/MetaLA"],"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/mpoxvlm-a-vision-language-model-for","slug":"mpoxvlm-a-vision-language-model-for","title":"MpoxVLM: A Vision-Language Model for Diagnosing Skin Lesions from Mpox Virus Infection","date":"2024-11-16","arxiv_id":"2411.10888","repositories_listed":1,"syntology":null},{"url":"/paper/multi-stage-vision-token-dropping-towards","slug":"multi-stage-vision-token-dropping-towards","title":"Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model","date":"2024-11-16","arxiv_id":"2411.10803","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":3,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multi-stage-vision-token-dropping-towards#ran","syntology_url":"https://syntology.ai/paper/2411.10803","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.10803"}},"official":{"repos":["liuting20/mustdrop"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/structured-dialogue-system-for-mental-health","slug":"structured-dialogue-system-for-mental-health","title":"Structured Dialogue System for Mental Health: An LLM Chatbot Leveraging the PM+ Guidelines","date":"2024-11-16","arxiv_id":"2411.10681","repositories_listed":1,"syntology":null},{"url":"/paper/seagull-no-reference-image-quality-assessment","slug":"seagull-no-reference-image-quality-assessment","title":"SEAGULL: No-reference Image Quality Assessment for Regions of Interest via Vision-Language Instruction Tuning","date":"2024-11-15","arxiv_id":"2411.10161","repositories_listed":1,"syntology":null},{"url":"/paper/xmodel-1-5-an-1b-scale-multilingual-llm","slug":"xmodel-1-5-an-1b-scale-multilingual-llm","title":"Xmodel-1.5: An 1B-scale Multilingual LLM","date":"2024-11-15","arxiv_id":"2411.10083","repositories_listed":1,"syntology":null},{"url":"/paper/lhrs-bot-nova-improved-multimodal-large","slug":"lhrs-bot-nova-improved-multimodal-large","title":"LHRS-Bot-Nova: Improved Multimodal Large Language Model for Remote Sensing Vision-Language Interpretation","date":"2024-11-14","arxiv_id":"2411.09301","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lhrs-bot-nova-improved-multimodal-large#ran","syntology_url":"https://syntology.ai/paper/2411.09301","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.09301"}},"official":{"repos":["NJU-LHRS/LHRS-Bot"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/magicquill-an-intelligent-interactive-image","slug":"magicquill-an-intelligent-interactive-image","title":"MagicQuill: An Intelligent Interactive Image Editing System","date":"2024-11-14","arxiv_id":"2411.09703","repositories_listed":1,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":12,"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) · 0 unverified","sample_list":"/paper/magicquill-an-intelligent-interactive-image#ran","syntology_url":"https://syntology.ai/paper/2411.09703","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.09703"}},"official":{"repos":["ant-research/MagicQuill"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/reducing-reasoning-costs-the-path-of","slug":"reducing-reasoning-costs-the-path-of","title":"Reducing Reasoning Costs: The Path of Optimization for Chain of Thought via Sparse Attention Mechanism","date":"2024-11-14","arxiv_id":"2411.09111","repositories_listed":1,"syntology":null},{"url":"/paper/language-model-prior-overcomes-cold-start","slug":"language-model-prior-overcomes-cold-start","title":"Language-Model Prior Overcomes Cold-Start Items","date":"2024-11-13","arxiv_id":"2411.09065","repositories_listed":1,"syntology":null},{"url":"/paper/separating-tongue-from-thought-activation","slug":"separating-tongue-from-thought-activation","title":"Separating Tongue from Thought: Activation Patching Reveals Language-Agnostic Concept Representations in Transformers","date":"2024-11-13","arxiv_id":"2411.08745","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":10,"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/separating-tongue-from-thought-activation#ran","syntology_url":"https://syntology.ai/paper/2411.08745","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.08745"}},"official":{"repos":["butanium/llm-lang-agnostic"],"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/contrastive-language-prompting-to-ease-false","slug":"contrastive-language-prompting-to-ease-false","title":"Contrastive Language Prompting to Ease False Positives in Medical Anomaly Detection","date":"2024-11-12","arxiv_id":"2411.07546","repositories_listed":1,"syntology":null},{"url":"/paper/janusflow-harmonizing-autoregression-and","slug":"janusflow-harmonizing-autoregression-and","title":"JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation","date":"2024-11-12","arxiv_id":"2411.07975","repositories_listed":1,"syntology":null},{"url":"/paper/language-models-as-causal-effect-generators","slug":"language-models-as-causal-effect-generators","title":"Language Models as Causal Effect Generators","date":"2024-11-12","arxiv_id":"2411.08019","repositories_listed":1,"syntology":null},{"url":"/paper/likelihood-as-a-performance-gauge-for","slug":"likelihood-as-a-performance-gauge-for","title":"Likelihood as a Performance Gauge for Retrieval-Augmented Generation","date":"2024-11-12","arxiv_id":"2411.07773","repositories_listed":1,"syntology":null},{"url":"/paper/prompt-enhanced-network-for-hateful-meme","slug":"prompt-enhanced-network-for-hateful-meme","title":"Prompt-enhanced Network for Hateful Meme Classification","date":"2024-11-12","arxiv_id":"2411.07527","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":3,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"5 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/prompt-enhanced-network-for-hateful-meme#ran","syntology_url":"https://syntology.ai/paper/2411.07527","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.07527"}},"official":{"repos":["juszzi/pen"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tipo-text-to-image-with-text-presampling-for","slug":"tipo-text-to-image-with-text-presampling-for","title":"TIPO: Text to Image with Text Presampling for Prompt Optimization","date":"2024-11-12","arxiv_id":"2411.08127","repositories_listed":1,"syntology":null},{"url":"/paper/tucano-advancing-neural-text-generation-for","slug":"tucano-advancing-neural-text-generation-for","title":"Tucano: Advancing Neural Text Generation for Portuguese","date":"2024-11-12","arxiv_id":"2411.07854","repositories_listed":1,"syntology":null},{"url":"/paper/building-a-taiwanese-mandarin-spoken-language","slug":"building-a-taiwanese-mandarin-spoken-language","title":"Building a Taiwanese Mandarin Spoken Language Model: A First Attempt","date":"2024-11-11","arxiv_id":"2411.07111","repositories_listed":1,"syntology":null},{"url":"/paper/iter-iterative-transformer-based-entity","slug":"iter-iterative-transformer-based-entity","title":"ITER: Iterative Transformer-based Entity Recognition and Relation Extraction","date":"2024-11-11","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/model-fusion-through-bayesian-optimization-in","slug":"model-fusion-through-bayesian-optimization-in","title":"Model Fusion through Bayesian Optimization in Language Model Fine-Tuning","date":"2024-11-11","arxiv_id":"2411.06710","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/model-fusion-through-bayesian-optimization-in#ran","syntology_url":"https://syntology.ai/paper/2411.06710","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.06710"}},"official":{"repos":["chaeyoon-jang/bomf"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/more-expressive-attention-with-negative","slug":"more-expressive-attention-with-negative","title":"More Expressive Attention with Negative Weights","date":"2024-11-11","arxiv_id":"2411.07176","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/more-expressive-attention-with-negative#ran","syntology_url":"https://syntology.ai/paper/2411.07176","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.07176"}},"official":{"repos":["trestad/cogattn"],"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","unlocated"]}}},{"url":"/paper/music-discovery-dialogue-generation-using","slug":"music-discovery-dialogue-generation-using","title":"Music Discovery Dialogue Generation Using Human Intent Analysis and Large Language Models","date":"2024-11-11","arxiv_id":"2411.07439","repositories_listed":1,"syntology":null},{"url":"/paper/the-super-weight-in-large-language-models","slug":"the-super-weight-in-large-language-models","title":"The Super Weight in Large Language Models","date":"2024-11-11","arxiv_id":"2411.07191","repositories_listed":1,"syntology":{"n":8,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":8,"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) · 4 unverified","sample_list":"/paper/the-super-weight-in-large-language-models#ran","syntology_url":"https://syntology.ai/paper/2411.07191","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.07191"}},"official":{"repos":["mengxiayu/llmsuperweight"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/the-surprising-effectiveness-of-test-time","slug":"the-surprising-effectiveness-of-test-time","title":"The Surprising Effectiveness of Test-Time Training for Few-Shot Learning","date":"2024-11-11","arxiv_id":"2411.07279","repositories_listed":1,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/the-surprising-effectiveness-of-test-time#ran","syntology_url":"https://syntology.ai/paper/2411.07279","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.07279"}},"official":{"repos":["ekinakyurek/marc"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/zeroth-order-adaptive-neuron-alignment-based","slug":"zeroth-order-adaptive-neuron-alignment-based","title":"Zeroth-Order Adaptive Neuron Alignment Based Pruning without Re-Training","date":"2024-11-11","arxiv_id":"2411.07066","repositories_listed":1,"syntology":null},{"url":"/paper/ctc-assisted-llm-based-contextual-asr","slug":"ctc-assisted-llm-based-contextual-asr","title":"CTC-Assisted LLM-Based Contextual ASR","date":"2024-11-10","arxiv_id":"2411.06437","repositories_listed":1,"syntology":null},{"url":"/paper/concept-bottleneck-language-models-for","slug":"concept-bottleneck-language-models-for","title":"Concept Bottleneck Language Models For protein design","date":"2024-11-09","arxiv_id":"2411.06090","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/concept-bottleneck-language-models-for#ran","syntology_url":"https://syntology.ai/paper/2411.06090","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.06090"}},"official":{"repos":["prescient-design/lobster"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-taxonomy-of-agentops-for-enabling","slug":"a-taxonomy-of-agentops-for-enabling","title":"AgentOps: Enabling Observability of LLM Agents","date":"2024-11-08","arxiv_id":"2411.05285","repositories_listed":1,"syntology":null},{"url":"/paper/a-two-step-concept-based-approach-for","slug":"a-two-step-concept-based-approach-for","title":"A Two-Step Concept-Based Approach for Enhanced Interpretability and Trust in Skin Lesion Diagnosis","date":"2024-11-08","arxiv_id":"2411.05609","repositories_listed":1,"syntology":null},{"url":"/paper/aioli-a-unified-optimization-framework-for","slug":"aioli-a-unified-optimization-framework-for","title":"Aioli: A Unified Optimization Framework for Language Model Data Mixing","date":"2024-11-08","arxiv_id":"2411.05735","repositories_listed":1,"syntology":{"n":31,"n_ran":23,"n_constructed":3,"n_ran_checked":19,"n_instrument":4,"n_unverified":8,"n_honours":1,"n_violates":0,"n_no_contract":18,"n_pointer_only":0,"phrase":"23 ran (of which 3 constructed an object rather than computing a result; 19 with no instrument failure: 1 honoured, 0 violated, 18 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/aioli-a-unified-optimization-framework-for#ran","syntology_url":"https://syntology.ai/paper/2411.05735","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.05735"}},"official":{"repos":["hazyresearch/aioli"],"state":"official (archive's flag): 23 ran","n_ran":23,"n_constructed":3,"n_ran_no_instrument_failure":19,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/end-to-end-navigation-with-vision-language","slug":"end-to-end-navigation-with-vision-language","title":"End-to-End Navigation with Vision Language Models: Transforming Spatial Reasoning into Question-Answering","date":"2024-11-08","arxiv_id":"2411.05755","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/end-to-end-navigation-with-vision-language#ran","syntology_url":"https://syntology.ai/paper/2411.05755","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.05755"}},"official":{"repos":["Jirl-upenn/VLMnav"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/llm-pysc2-starcraft-ii-learning-environment","slug":"llm-pysc2-starcraft-ii-learning-environment","title":"LLM-PySC2: Starcraft II learning environment for Large Language Models","date":"2024-11-08","arxiv_id":"2411.05348","repositories_listed":1,"syntology":null},{"url":"/paper/recycled-attention-efficient-inference-for","slug":"recycled-attention-efficient-inference-for","title":"Recycled Attention: Efficient inference for long-context language models","date":"2024-11-08","arxiv_id":"2411.05787","repositories_listed":1,"syntology":null},{"url":"/paper/autoproteinengine-a-large-language-model","slug":"autoproteinengine-a-large-language-model","title":"AutoProteinEngine: A Large Language Model Driven Agent Framework for Multimodal AutoML in Protein Engineering","date":"2024-11-07","arxiv_id":"2411.04440","repositories_listed":1,"syntology":null},{"url":"/paper/bendvlm-test-time-debiasing-of-vision","slug":"bendvlm-test-time-debiasing-of-vision","title":"BendVLM: Test-Time Debiasing of Vision-Language Embeddings","date":"2024-11-07","arxiv_id":"2411.04420","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":5,"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/bendvlm-test-time-debiasing-of-vision#ran","syntology_url":"https://syntology.ai/paper/2411.04420","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.04420"}},"official":{"repos":["waltergerych/bend_vlm"],"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/delift-data-efficient-language-model","slug":"delift-data-efficient-language-model","title":"DELIFT: Data Efficient Language model Instruction Fine Tuning","date":"2024-11-07","arxiv_id":"2411.04425","repositories_listed":1,"syntology":{"n":7,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/delift-data-efficient-language-model#ran","syntology_url":"https://syntology.ai/paper/2411.04425","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.04425"}},"official":{"repos":["agarwalishika/delift"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/llm2clip-powerful-language-model-unlock","slug":"llm2clip-powerful-language-model-unlock","title":"LLM2CLIP: Powerful Language Model Unlocks Richer Visual Representation","date":"2024-11-07","arxiv_id":"2411.04997","repositories_listed":1,"syntology":null},{"url":"/paper/phonelm-an-efficient-and-capable-small","slug":"phonelm-an-efficient-and-capable-small","title":"PhoneLM:an Efficient and Capable Small Language Model Family through Principled Pre-training","date":"2024-11-07","arxiv_id":"2411.05046","repositories_listed":1,"syntology":null},{"url":"/paper/suffixdecoding-a-model-free-approach-to","slug":"suffixdecoding-a-model-free-approach-to","title":"SuffixDecoding: Extreme Speculative Decoding for Emerging AI Applications","date":"2024-11-07","arxiv_id":"2411.04975","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/suffixdecoding-a-model-free-approach-to#ran","syntology_url":"https://syntology.ai/paper/2411.04975","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.04975"}},"official":{"repos":["snowflakedb/arcticinference"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/thanos-enhancing-conversational-agents-with","slug":"thanos-enhancing-conversational-agents-with","title":"Thanos: Enhancing Conversational Agents with Skill-of-Mind-Infused Large Language Model","date":"2024-11-07","arxiv_id":"2411.04496","repositories_listed":1,"syntology":null},{"url":"/paper/when-does-classical-chinese-help-quantifying","slug":"when-does-classical-chinese-help-quantifying","title":"When Does Classical Chinese Help? Quantifying Cross-Lingual Transfer in Hanja and Kanbun","date":"2024-11-07","arxiv_id":"2411.04822","repositories_listed":1,"syntology":null},{"url":"/paper/reducing-hyperparameter-tuning-costs-in-ml","slug":"reducing-hyperparameter-tuning-costs-in-ml","title":"Reducing Hyperparameter Tuning Costs in ML, Vision and Language Model Training Pipelines via Memoization-Awareness","date":"2024-11-06","arxiv_id":"2411.03731","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-vision-language-model-unlearning","slug":"benchmarking-vision-language-model-unlearning","title":"Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset","date":"2024-11-05","arxiv_id":"2411.03554","repositories_listed":1,"syntology":{"n":18,"n_ran":13,"n_constructed":0,"n_ran_checked":11,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":18,"phrase":"13 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; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/benchmarking-vision-language-model-unlearning#ran","syntology_url":"https://syntology.ai/paper/2411.03554","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.03554"}},"official":{"repos":["safolab-wisc/fiubench"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/v-dpo-mitigating-hallucination-in-large","slug":"v-dpo-mitigating-hallucination-in-large","title":"V-DPO: Mitigating Hallucination in Large Vision Language Models via Vision-Guided Direct Preference Optimization","date":"2024-11-05","arxiv_id":"2411.02712","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/v-dpo-mitigating-hallucination-in-large#ran","syntology_url":"https://syntology.ai/paper/2411.02712","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.02712"}},"official":{"repos":["yuxixie/v-dpo"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/exploring-the-landscape-for-generative","slug":"exploring-the-landscape-for-generative","title":"Exploring the Landscape for Generative Sequence Models for Specialized Data Synthesis","date":"2024-11-04","arxiv_id":"2411.01929","repositories_listed":1,"syntology":null},{"url":"/paper/ragviz-diagnose-and-visualize-retrieval","slug":"ragviz-diagnose-and-visualize-retrieval","title":"RAGViz: Diagnose and Visualize Retrieval-Augmented Generation","date":"2024-11-04","arxiv_id":"2411.01751","repositories_listed":1,"syntology":null},{"url":"/paper/regress-don-t-guess-a-regression-like-loss-on","slug":"regress-don-t-guess-a-regression-like-loss-on","title":"Regress, Don't Guess -- A Regression-like Loss on Number Tokens for Language Models","date":"2024-11-04","arxiv_id":"2411.02083","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/regress-don-t-guess-a-regression-like-loss-on#ran","syntology_url":"https://syntology.ai/paper/2411.02083","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.02083"}},"official":{"repos":["tum-ai/number-token-loss"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/teleoracle-fine-tuned-retrieval-augmented","slug":"teleoracle-fine-tuned-retrieval-augmented","title":"TeleOracle: Fine-Tuned Retrieval-Augmented Generation with Long-Context Support for Network","date":"2024-11-04","arxiv_id":"2411.02617","repositories_listed":1,"syntology":null},{"url":"/paper/training-compute-optimal-protein-language","slug":"training-compute-optimal-protein-language","title":"Training Compute-Optimal Protein Language Models","date":"2024-11-04","arxiv_id":"2411.02142","repositories_listed":1,"syntology":null},{"url":"/paper/zebra-llama-a-context-aware-large-language","slug":"zebra-llama-a-context-aware-large-language","title":"Zebra-Llama: A Context-Aware Large Language Model for Democratizing Rare Disease Knowledge","date":"2024-11-04","arxiv_id":"2411.02657","repositories_listed":1,"syntology":null},{"url":"/paper/graphxform-graph-transformer-for-computer","slug":"graphxform-graph-transformer-for-computer","title":"GraphXForm: Graph transformer for computer-aided molecular design","date":"2024-11-03","arxiv_id":"2411.01667","repositories_listed":1,"syntology":null},{"url":"/paper/rule-based-rewards-for-language-model-safety","slug":"rule-based-rewards-for-language-model-safety","title":"Rule Based Rewards for Language Model Safety","date":"2024-11-02","arxiv_id":"2411.01111","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/rule-based-rewards-for-language-model-safety#ran","syntology_url":"https://syntology.ai/paper/2411.01111","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.01111"}},"official":{"repos":["openai/safety-rbr-code-and-data"],"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/leveraging-large-language-models-for-code-1","slug":"leveraging-large-language-models-for-code-1","title":"Leveraging Large Language Models for Code-Mixed Data Augmentation in Sentiment Analysis","date":"2024-11-01","arxiv_id":"2411.00691","repositories_listed":1,"syntology":null},{"url":"/paper/lingma-swe-gpt-an-open-development-process","slug":"lingma-swe-gpt-an-open-development-process","title":"Lingma SWE-GPT: An Open Development-Process-Centric Language Model for Automated Software Improvement","date":"2024-11-01","arxiv_id":"2411.00622","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":12,"phrase":"10 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; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/lingma-swe-gpt-an-open-development-process#ran","syntology_url":"https://syntology.ai/paper/2411.00622","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00622"}},"official":{"repos":["LingmaTongyi/Lingma-SWE-GPT"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-expert-prompting-improves-reliability","slug":"multi-expert-prompting-improves-reliability","title":"Multi-expert Prompting Improves Reliability, Safety, and Usefulness of Large Language Models","date":"2024-11-01","arxiv_id":"2411.00492","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"5 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; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/multi-expert-prompting-improves-reliability#ran","syntology_url":"https://syntology.ai/paper/2411.00492","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00492"}},"official":{"repos":["dxlong2000/multi-expert-prompting"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/normalization-layer-per-example-gradients-are","slug":"normalization-layer-per-example-gradients-are","title":"Normalization Layer Per-Example Gradients are Sufficient to Predict Gradient Noise Scale in Transformers","date":"2024-11-01","arxiv_id":"2411.00999","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":2,"n_no_contract":11,"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, 2 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/normalization-layer-per-example-gradients-are#ran","syntology_url":"https://syntology.ai/paper/2411.00999","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00999"}},"official":{"repos":["cerebrasresearch/nanogns"],"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/randomized-autoregressive-visual-generation","slug":"randomized-autoregressive-visual-generation","title":"Randomized Autoregressive Visual Generation","date":"2024-11-01","arxiv_id":"2411.00776","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/randomized-autoregressive-visual-generation#ran","syntology_url":"https://syntology.ai/paper/2411.00776","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00776"}},"official":{"repos":["bytedance/1d-tokenizer"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/echonarrator-generating-natural-text","slug":"echonarrator-generating-natural-text","title":"EchoNarrator: Generating natural text explanations for ejection fraction predictions","date":"2024-10-31","arxiv_id":"2410.23744","repositories_listed":1,"syntology":null},{"url":"/paper/gpt-or-bert-why-not-both","slug":"gpt-or-bert-why-not-both","title":"GPT or BERT: why not both?","date":"2024-10-31","arxiv_id":"2410.24159","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/gpt-or-bert-why-not-both#ran","syntology_url":"https://syntology.ai/paper/2410.24159","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.24159"}},"official":{"repos":["ltgoslo/gpt-bert"],"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/instruction-tuning-llama-3-8b-excels-in-city","slug":"instruction-tuning-llama-3-8b-excels-in-city","title":"Instruction-Tuning Llama-3-8B Excels in City-Scale Mobility Prediction","date":"2024-10-31","arxiv_id":"2410.23692","repositories_listed":1,"syntology":null},{"url":"/paper/interpretable-language-modeling-via-induction","slug":"interpretable-language-modeling-via-induction","title":"Interpretable Language Modeling via Induction-head Ngram Models","date":"2024-10-31","arxiv_id":"2411.00066","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"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, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/interpretable-language-modeling-via-induction#ran","syntology_url":"https://syntology.ai/paper/2411.00066","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00066"}},"official":{"repos":["ejkim47/induction-gram"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/llamo-large-language-model-based-molecular","slug":"llamo-large-language-model-based-molecular","title":"LLaMo: Large Language Model-based Molecular Graph Assistant","date":"2024-10-31","arxiv_id":"2411.00871","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":11,"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) · 1 unverified","sample_list":"/paper/llamo-large-language-model-based-molecular#ran","syntology_url":"https://syntology.ai/paper/2411.00871","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00871"}},"official":{"repos":["mlvlab/llamo"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/what-is-wrong-with-perplexity-for-long","slug":"what-is-wrong-with-perplexity-for-long","title":"What is Wrong with Perplexity for Long-context Language Modeling?","date":"2024-10-31","arxiv_id":"2410.23771","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/what-is-wrong-with-perplexity-for-long#ran","syntology_url":"https://syntology.ai/paper/2410.23771","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.23771"}},"official":{"repos":["pku-ml/longppl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/beyond-ontology-in-dialogue-state-tracking","slug":"beyond-ontology-in-dialogue-state-tracking","title":"Beyond Ontology in Dialogue State Tracking for Goal-Oriented Chatbot","date":"2024-10-30","arxiv_id":"2410.22767","repositories_listed":1,"syntology":null},{"url":"/paper/comal-a-convergent-meta-algorithm-for","slug":"comal-a-convergent-meta-algorithm-for","title":"COMAL: A Convergent Meta-Algorithm for Aligning LLMs with General Preferences","date":"2024-10-30","arxiv_id":"2410.23223","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":10,"phrase":"10 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/comal-a-convergent-meta-algorithm-for#ran","syntology_url":"https://syntology.ai/paper/2410.23223","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.23223"}},"official":{"repos":["yale-nlp/comal"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/neural-spell-checker-beyond-words-with","slug":"neural-spell-checker-beyond-words-with","title":"Neural spell-checker: Beyond words with synthetic data generation","date":"2024-10-30","arxiv_id":"2410.23514","repositories_listed":1,"syntology":null},{"url":"/paper/online-intrinsic-rewards-for-decision-making","slug":"online-intrinsic-rewards-for-decision-making","title":"Online Intrinsic Rewards for Decision Making Agents from Large Language Model Feedback","date":"2024-10-30","arxiv_id":"2410.23022","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":12,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/online-intrinsic-rewards-for-decision-making#ran","syntology_url":"https://syntology.ai/paper/2410.23022","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.23022"}},"official":{"repos":["facebookresearch/oni"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/real-time-personalization-for-llm-based","slug":"real-time-personalization-for-llm-based","title":"Real-Time Personalization for LLM-based Recommendation with Customized In-Context Learning","date":"2024-10-30","arxiv_id":"2410.23136","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/real-time-personalization-for-llm-based#ran","syntology_url":"https://syntology.ai/paper/2410.23136","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.23136"}},"official":{"repos":["ym689/rec_icl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/are-vlms-really-blind","slug":"are-vlms-really-blind","title":"Are VLMs Really Blind","date":"2024-10-29","arxiv_id":"2410.22029","repositories_listed":1,"syntology":null},{"url":"/paper/f-po-generalizing-preference-optimization","slug":"f-po-generalizing-preference-optimization","title":"$f$-PO: Generalizing Preference Optimization with $f$-divergence Minimization","date":"2024-10-29","arxiv_id":"2410.21662","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":0,"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/f-po-generalizing-preference-optimization#ran","syntology_url":"https://syntology.ai/paper/2410.21662","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.21662"}},"official":{"repos":["minkaixu/fpo"],"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/improving-in-context-learning-with-small","slug":"improving-in-context-learning-with-small","title":"Improving In-Context Learning with Small Language Model Ensembles","date":"2024-10-29","arxiv_id":"2410.21868","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/improving-in-context-learning-with-small#ran","syntology_url":"https://syntology.ai/paper/2410.21868","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.21868"}},"official":{"repos":["mehdimojarradi/Ensemble-SuperICL"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/long-context-protein-language-model","slug":"long-context-protein-language-model","title":"Long-context Protein Language Modeling Using Bidirectional Mamba with Shared Projection Layers","date":"2024-10-29","arxiv_id":"2411.08909","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-quantum-natural-language","slug":"multimodal-quantum-natural-language","title":"Multimodal Quantum Natural Language Processing: A Novel Framework for using Quantum Methods to Analyse Real Data","date":"2024-10-29","arxiv_id":"2411.05023","repositories_listed":1,"syntology":null},{"url":"/paper/online-detecting-llm-generated-texts-via","slug":"online-detecting-llm-generated-texts-via","title":"Online Detecting LLM-Generated Texts via Sequential Hypothesis Testing by Betting","date":"2024-10-29","arxiv_id":"2410.22318","repositories_listed":1,"syntology":null},{"url":"/paper/persrv-personalized-sticker-retrieval-with","slug":"persrv-personalized-sticker-retrieval-with","title":"PerSRV: Personalized Sticker Retrieval with Vision-Language Model","date":"2024-10-29","arxiv_id":"2410.21801","repositories_listed":1,"syntology":null},{"url":"/paper/protecting-privacy-in-multimodal-large","slug":"protecting-privacy-in-multimodal-large","title":"Protecting Privacy in Multimodal Large Language Models with MLLMU-Bench","date":"2024-10-29","arxiv_id":"2410.22108","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/protecting-privacy-in-multimodal-large#ran","syntology_url":"https://syntology.ai/paper/2410.22108","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.22108"}},"official":{"repos":["franciscoliu/MLLMU-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/rare-to-frequent-unlocking-compositional","slug":"rare-to-frequent-unlocking-compositional","title":"Rare-to-Frequent: Unlocking Compositional Generation Power of Diffusion Models on Rare Concepts with LLM Guidance","date":"2024-10-29","arxiv_id":"2410.22376","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/rare-to-frequent-unlocking-compositional#ran","syntology_url":"https://syntology.ai/paper/2410.22376","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.22376"}},"official":{"repos":["krafton-ai/rare-to-frequent"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/rethinking-code-refinement-learning-to-judge","slug":"rethinking-code-refinement-learning-to-judge","title":"Rethinking Code Refinement: Learning to Judge Code Efficiency","date":"2024-10-29","arxiv_id":"2410.22375","repositories_listed":1,"syntology":null},{"url":"/paper/sg-bench-evaluating-llm-safety-generalization","slug":"sg-bench-evaluating-llm-safety-generalization","title":"SG-Bench: Evaluating LLM Safety Generalization Across Diverse Tasks and Prompt Types","date":"2024-10-29","arxiv_id":"2410.21965","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/sg-bench-evaluating-llm-safety-generalization#ran","syntology_url":"https://syntology.ai/paper/2410.21965","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.21965"}},"official":{"repos":["MurrayTom/SG-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/graph-based-uncertainty-metrics-for-long-form","slug":"graph-based-uncertainty-metrics-for-long-form","title":"Graph-based Uncertainty Metrics for Long-form Language Model Outputs","date":"2024-10-28","arxiv_id":"2410.20783","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/graph-based-uncertainty-metrics-for-long-form#ran","syntology_url":"https://syntology.ai/paper/2410.20783","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.20783"}},"official":{"repos":["mingjianjiang-1/graph-based-uncertainty"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/large-language-model-guided-prediction-toward","slug":"large-language-model-guided-prediction-toward","title":"Large Language Model-Guided Prediction Toward Quantum Materials Synthesis","date":"2024-10-28","arxiv_id":"2410.20976","repositories_listed":1,"syntology":null},{"url":"/paper/llmcbench-benchmarking-large-language-model","slug":"llmcbench-benchmarking-large-language-model","title":"LLMCBench: Benchmarking Large Language Model Compression for Efficient Deployment","date":"2024-10-28","arxiv_id":"2410.21352","repositories_listed":1,"syntology":{"n":17,"n_ran":14,"n_constructed":0,"n_ran_checked":11,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":1,"phrase":"14 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; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/llmcbench-benchmarking-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2410.21352","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.21352"}},"official":{"repos":["aboveparadise/llmcbench"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/retrieval-enhanced-mutation-mastery","slug":"retrieval-enhanced-mutation-mastery","title":"Retrieval-Enhanced Mutation Mastery: Augmenting Zero-Shot Prediction of Protein Language Model","date":"2024-10-28","arxiv_id":"2410.21127","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/retrieval-enhanced-mutation-mastery#ran","syntology_url":"https://syntology.ai/paper/2410.21127","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.21127"}},"official":{"repos":["tyang816/protrem"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/segmenting-watermarked-texts-from-language","slug":"segmenting-watermarked-texts-from-language","title":"Segmenting Watermarked Texts From Language Models","date":"2024-10-28","arxiv_id":"2410.20670","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/segmenting-watermarked-texts-from-language#ran","syntology_url":"https://syntology.ai/paper/2410.20670","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.20670"}},"official":{"repos":["doccstat/llm-watermark-cpd"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/thank-you-stingray-multilingual-large","slug":"thank-you-stingray-multilingual-large","title":"Thank You, Stingray: Multilingual Large Language Models Can Not (Yet) Disambiguate Cross-Lingual Word Sense","date":"2024-10-28","arxiv_id":"2410.21573","repositories_listed":1,"syntology":null},{"url":"/paper/llama-scope-extracting-millions-of-features","slug":"llama-scope-extracting-millions-of-features","title":"Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders","date":"2024-10-27","arxiv_id":"2410.20526","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/llama-scope-extracting-millions-of-features#ran","syntology_url":"https://syntology.ai/paper/2410.20526","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.20526"}},"official":{"repos":["openmoss/language-model-saes"],"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/sequential-large-language-model-based-hyper","slug":"sequential-large-language-model-based-hyper","title":"Sequential Large Language Model-Based Hyper-parameter Optimization","date":"2024-10-27","arxiv_id":"2410.20302","repositories_listed":1,"syntology":null},{"url":"/paper/trajagent-an-agent-framework-for-unified","slug":"trajagent-an-agent-framework-for-unified","title":"TrajAgent: An Agent Framework for Unified Trajectory Modelling","date":"2024-10-27","arxiv_id":"2410.20445","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/trajagent-an-agent-framework-for-unified#ran","syntology_url":"https://syntology.ai/paper/2410.20445","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.20445"}},"official":{"repos":["tsinghua-fib-lab/trajagent"],"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/centaur-a-foundation-model-of-human-cognition","slug":"centaur-a-foundation-model-of-human-cognition","title":"Centaur: a foundation model of human cognition","date":"2024-10-26","arxiv_id":"2410.20268","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":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) · 0 unverified","sample_list":"/paper/centaur-a-foundation-model-of-human-cognition#ran","syntology_url":"https://syntology.ai/paper/2410.20268","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.20268"}},"official":{"repos":["marcelbinz/Llama-3.1-Centaur-70B"],"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/chemical-language-model-linker-blending-text","slug":"chemical-language-model-linker-blending-text","title":"Chemical Language Model Linker: blending text and molecules with modular adapters","date":"2024-10-26","arxiv_id":"2410.20182","repositories_listed":1,"syntology":null},{"url":"/paper/a-multimodal-approach-for-endoscopic-vce","slug":"a-multimodal-approach-for-endoscopic-vce","title":"A Multimodal Approach For Endoscopic VCE Image Classification Using BiomedCLIP-PubMedBERT","date":"2024-10-25","arxiv_id":"2410.19944","repositories_listed":1,"syntology":null},{"url":"/paper/coat-compressing-optimizer-states-and","slug":"coat-compressing-optimizer-states-and","title":"COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training","date":"2024-10-25","arxiv_id":"2410.19313","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/coat-compressing-optimizer-states-and#ran","syntology_url":"https://syntology.ai/paper/2410.19313","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.19313"}},"official":{"repos":["nvlabs/coat"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/peptide-gpt-generative-design-of-peptides","slug":"peptide-gpt-generative-design-of-peptides","title":"Peptide-GPT: Generative Design of Peptides using Generative Pre-trained Transformers and Bio-informatic Supervision","date":"2024-10-25","arxiv_id":"2410.19222","repositories_listed":1,"syntology":null},{"url":"/paper/gcoder-improving-large-language-model-for","slug":"gcoder-improving-large-language-model-for","title":"GCoder: Improving Large Language Model for Generalized Graph Problem Solving","date":"2024-10-24","arxiv_id":"2410.19084","repositories_listed":1,"syntology":null},{"url":"/paper/logo-long-context-alignment-via-efficient","slug":"logo-long-context-alignment-via-efficient","title":"LOGO -- Long cOntext aliGnment via efficient preference Optimization","date":"2024-10-24","arxiv_id":"2410.18533","repositories_listed":1,"syntology":null}],"record_sha256":"a7ea48d39a1814544940f63ce47033471be6a365e475ea845ad1f570e6626a78","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}