{"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/large-language-model/papers/6","list_of":"/task/large-language-model","task":"Large Language Model","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":6,"pages_in_order":61,"rows_per_page":100,"rows":[501,600],"of":6097,"counts":{"archive_papers_tagged":6097,"with_a_code_link":2250,"where_syntology_ran_a_sample":801,"not_listed_spam_title":0,"listed":6097,"listed_where_code_ran":801,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":683,"every_run_a_failure_of_syntologys_instrument":118,"listed_with_a_run_with_no_instrument_failure":683,"listed_every_run_a_failure_of_syntologys_instrument":118,"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/large-language-model","prev":"/task/large-language-model/papers/5","next":"/task/large-language-model/papers/7","papers":[{"url":"/paper/docia-an-online-document-level-context","slug":"docia-an-online-document-level-context","title":"DoCIA: An Online Document-Level Context Incorporation Agent for Speech Translation","date":"2025-04-07","arxiv_id":"2504.05122","repositories_listed":1,"syntology":null},{"url":"/paper/hessian-of-perplexity-for-large-language","slug":"hessian-of-perplexity-for-large-language","title":"Hessian of Perplexity for Large Language Models by PyTorch autograd (Open Source)","date":"2025-04-06","arxiv_id":"2504.04520","repositories_listed":1,"syntology":null},{"url":"/paper/planning-safety-trajectories-with-dual-phase","slug":"planning-safety-trajectories-with-dual-phase","title":"Planning Safety Trajectories with Dual-Phase, Physics-Informed, and Transportation Knowledge-Driven Large Language Models","date":"2025-04-06","arxiv_id":"2504.04562","repositories_listed":1,"syntology":null},{"url":"/paper/thanos-a-block-wise-pruning-algorithm-for","slug":"thanos-a-block-wise-pruning-algorithm-for","title":"Thanos: A Block-wise Pruning Algorithm for Efficient Large Language Model Compression","date":"2025-04-06","arxiv_id":"2504.05346","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-dynamic-clustering-based-document","slug":"efficient-dynamic-clustering-based-document","title":"Efficient Dynamic Clustering-Based Document Compression for Retrieval-Augmented-Generation","date":"2025-04-04","arxiv_id":"2504.03165","repositories_listed":1,"syntology":null},{"url":"/paper/zclip-adaptive-spike-mitigation-for-llm-pre","slug":"zclip-adaptive-spike-mitigation-for-llm-pre","title":"ZClip: Adaptive Spike Mitigation for LLM Pre-Training","date":"2025-04-03","arxiv_id":"2504.02507","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":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/zclip-adaptive-spike-mitigation-for-llm-pre#ran","syntology_url":"https://syntology.ai/paper/2504.02507","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.02507"}},"official":{"repos":["bluorion-com/ZClip"],"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/prophet-an-inferable-future-forecasting","slug":"prophet-an-inferable-future-forecasting","title":"PROPHET: An Inferable Future Forecasting Benchmark with Causal Intervened Likelihood Estimation","date":"2025-04-02","arxiv_id":"2504.01509","repositories_listed":1,"syntology":null},{"url":"/paper/4th-pvuw-mevis-3rd-place-report-sa2va","slug":"4th-pvuw-mevis-3rd-place-report-sa2va","title":"4th PVUW MeViS 3rd Place Report: Sa2VA","date":"2025-04-01","arxiv_id":"2504.00476","repositories_listed":1,"syntology":null},{"url":"/paper/cracksql-a-hybrid-sql-dialect-translation","slug":"cracksql-a-hybrid-sql-dialect-translation","title":"CrackSQL: A Hybrid SQL Dialect Translation System Powered by Large Language Models","date":"2025-04-01","arxiv_id":"2504.00882","repositories_listed":1,"syntology":null},{"url":"/paper/chapter-llama-efficient-chaptering-in-hour-1","slug":"chapter-llama-efficient-chaptering-in-hour-1","title":"Chapter-Llama: Efficient Chaptering in Hour-Long Videos with LLMs","date":"2025-03-31","arxiv_id":"2504.00072","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-key-value-cache-compression","slug":"rethinking-key-value-cache-compression","title":"Rethinking Key-Value Cache Compression Techniques for Large Language Model Serving","date":"2025-03-31","arxiv_id":"2503.24000","repositories_listed":1,"syntology":null},{"url":"/paper/teleantifraud-28k-a-audio-text-slow-thinking","slug":"teleantifraud-28k-a-audio-text-slow-thinking","title":"TeleAntiFraud-28k: An Audio-Text Slow-Thinking Dataset for Telecom Fraud Detection","date":"2025-03-31","arxiv_id":"2503.24115","repositories_listed":1,"syntology":null},{"url":"/paper/promptdistill-query-based-selective-token","slug":"promptdistill-query-based-selective-token","title":"PromptDistill: Query-based Selective Token Retention in Intermediate Layers for Efficient Large Language Model Inference","date":"2025-03-30","arxiv_id":"2503.23274","repositories_listed":1,"syntology":null},{"url":"/paper/astroagents-a-multi-agent-ai-for-hypothesis","slug":"astroagents-a-multi-agent-ai-for-hypothesis","title":"AstroAgents: A Multi-Agent AI for Hypothesis Generation from Mass Spectrometry Data","date":"2025-03-29","arxiv_id":"2503.23170","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/astroagents-a-multi-agent-ai-for-hypothesis#ran","syntology_url":"https://syntology.ai/paper/2503.23170","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.23170"}},"official":{"repos":["amirgroup-codes/astroagents"],"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/imagine-all-the-relevance-scenario-profiled","slug":"imagine-all-the-relevance-scenario-profiled","title":"Imagine All The Relevance: Scenario-Profiled Indexing with Knowledge Expansion for Dense Retrieval","date":"2025-03-29","arxiv_id":"2503.23033","repositories_listed":1,"syntology":null},{"url":"/paper/leaking-lora-an-evaluation-of-password-leaks","slug":"leaking-lora-an-evaluation-of-password-leaks","title":"Leaking LoRa: An Evaluation of Password Leaks and Knowledge Storage in Large Language Models","date":"2025-03-29","arxiv_id":"2504.00031","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-the-effectiveness-of-multi-stage","slug":"exploring-the-effectiveness-of-multi-stage","title":"Exploring the Effectiveness of Multi-stage Fine-tuning for Cross-encoder Re-rankers","date":"2025-03-28","arxiv_id":"2503.22672","repositories_listed":1,"syntology":null},{"url":"/paper/boosting-large-language-models-with-mask-fine","slug":"boosting-large-language-models-with-mask-fine","title":"Boosting Large Language Models with Mask Fine-Tuning","date":"2025-03-27","arxiv_id":"2503.22764","repositories_listed":1,"syntology":null},{"url":"/paper/controlling-large-language-model-with-latent","slug":"controlling-large-language-model-with-latent","title":"Controlling Large Language Model with Latent Actions","date":"2025-03-27","arxiv_id":"2503.21383","repositories_listed":1,"syntology":null},{"url":"/paper/eq-negotiator-an-emotion-reasoning-llm-agent","slug":"eq-negotiator-an-emotion-reasoning-llm-agent","title":"EQ-Negotiator: An Emotion-Reasoning LLM Agent in Credit Dialogues","date":"2025-03-27","arxiv_id":"2503.21080","repositories_listed":1,"syntology":null},{"url":"/paper/internvl-x-advancing-and-accelerating","slug":"internvl-x-advancing-and-accelerating","title":"InternVL-X: Advancing and Accelerating InternVL Series with Efficient Visual Token Compression","date":"2025-03-27","arxiv_id":"2503.21307","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-model-agent-a-survey-on","slug":"large-language-model-agent-a-survey-on","title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","date":"2025-03-27","arxiv_id":"2503.21460","repositories_listed":1,"syntology":null},{"url":"/paper/openhueval-evaluating-large-language-model-on","slug":"openhueval-evaluating-large-language-model-on","title":"OpenHuEval: Evaluating Large Language Model on Hungarian Specifics","date":"2025-03-27","arxiv_id":"2503.21500","repositories_listed":1,"syntology":null},{"url":"/paper/a-multilingual-culture-first-approach-to","slug":"a-multilingual-culture-first-approach-to","title":"A Multilingual, Culture-First Approach to Addressing Misgendering in LLM Applications","date":"2025-03-26","arxiv_id":"2503.20302","repositories_listed":1,"syntology":null},{"url":"/paper/injecting-adrenaline-into-llm-serving","slug":"injecting-adrenaline-into-llm-serving","title":"Injecting Adrenaline into LLM Serving: Boosting Resource Utilization and Throughput via Attention Disaggregation","date":"2025-03-26","arxiv_id":"2503.20552","repositories_listed":1,"syntology":null},{"url":"/paper/more-llm-mixture-of-rule-experts-guided-by-a","slug":"more-llm-mixture-of-rule-experts-guided-by-a","title":"MoRE-LLM: Mixture of Rule Experts Guided by a Large Language Model","date":"2025-03-26","arxiv_id":"2503.22731","repositories_listed":1,"syntology":null},{"url":"/paper/qwen2-5-omni-technical-report","slug":"qwen2-5-omni-technical-report","title":"Qwen2.5-Omni Technical Report","date":"2025-03-26","arxiv_id":"2503.20215","repositories_listed":1,"syntology":null},{"url":"/paper/rallrec-retrieval-augmented-large-language","slug":"rallrec-retrieval-augmented-large-language","title":"RALLRec+: Retrieval Augmented Large Language Model Recommendation with Reasoning","date":"2025-03-26","arxiv_id":"2503.20430","repositories_listed":1,"syntology":null},{"url":"/paper/collm-a-large-language-model-for-composed","slug":"collm-a-large-language-model-for-composed","title":"CoLLM: A Large Language Model for Composed Image Retrieval","date":"2025-03-25","arxiv_id":"2503.19910","repositories_listed":1,"syntology":null},{"url":"/paper/cross-tokenizer-distillation-via-approximate","slug":"cross-tokenizer-distillation-via-approximate","title":"Cross-Tokenizer Distillation via Approximate Likelihood Matching","date":"2025-03-25","arxiv_id":"2503.20083","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":1,"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; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/cross-tokenizer-distillation-via-approximate#ran","syntology_url":"https://syntology.ai/paper/2503.20083","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.20083"}},"official":{"repos":["bminixhofer/alm"],"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":["found_in_text","official"]}}},{"url":"/paper/logquant-log-distributed-2-bit-quantization","slug":"logquant-log-distributed-2-bit-quantization","title":"LogQuant: Log-Distributed 2-Bit Quantization of KV Cache with Superior Accuracy Preservation","date":"2025-03-25","arxiv_id":"2503.19950","repositories_listed":1,"syntology":null},{"url":"/paper/lrsclip-a-vision-language-foundation-model","slug":"lrsclip-a-vision-language-foundation-model","title":"LRSCLIP: A Vision-Language Foundation Model for Aligning Remote Sensing Image with Longer Text","date":"2025-03-25","arxiv_id":"2503.19311","repositories_listed":1,"syntology":null},{"url":"/paper/optimizing-photonic-structures-with-large","slug":"optimizing-photonic-structures-with-large","title":"Optimizing Photonic Structures with Large Language Model Driven Algorithm Discovery","date":"2025-03-25","arxiv_id":"2503.19742","repositories_listed":1,"syntology":null},{"url":"/paper/sun-shine-a-large-language-model-for-tibetan","slug":"sun-shine-a-large-language-model-for-tibetan","title":"Sun-Shine: A Large Language Model for Tibetan Culture","date":"2025-03-24","arxiv_id":"2503.18288","repositories_listed":1,"syntology":null},{"url":"/paper/trajectory-balance-with-asynchrony-decoupling","slug":"trajectory-balance-with-asynchrony-decoupling","title":"Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training","date":"2025-03-24","arxiv_id":"2503.18929","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/trajectory-balance-with-asynchrony-decoupling#ran","syntology_url":"https://syntology.ai/paper/2503.18929","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.18929"}},"official":null}},{"url":"/paper/mepnet-medical-entity-balanced-prompting","slug":"mepnet-medical-entity-balanced-prompting","title":"MEPNet: Medical Entity-balanced Prompting Network for Brain CT Report Generation","date":"2025-03-22","arxiv_id":"2503.17784","repositories_listed":1,"syntology":null},{"url":"/paper/cve-bench-a-benchmark-for-ai-agents-ability","slug":"cve-bench-a-benchmark-for-ai-agents-ability","title":"CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application Vulnerabilities","date":"2025-03-21","arxiv_id":"2503.17332","repositories_listed":1,"syntology":null},{"url":"/paper/modifying-large-language-model-post-training","slug":"modifying-large-language-model-post-training","title":"Modifying Large Language Model Post-Training for Diverse Creative Writing","date":"2025-03-21","arxiv_id":"2503.17126","repositories_listed":1,"syntology":null},{"url":"/paper/variance-control-via-weight-rescaling-in-llm","slug":"variance-control-via-weight-rescaling-in-llm","title":"Variance Control via Weight Rescaling in LLM Pre-training","date":"2025-03-21","arxiv_id":"2503.17500","repositories_listed":1,"syntology":null},{"url":"/paper/code-evolution-graphs-understanding-large","slug":"code-evolution-graphs-understanding-large","title":"Code Evolution Graphs: Understanding Large Language Model Driven Design of Algorithms","date":"2025-03-20","arxiv_id":"2503.16668","repositories_listed":1,"syntology":null},{"url":"/paper/distributed-llms-and-multimodal-large","slug":"distributed-llms-and-multimodal-large","title":"Distributed LLMs and Multimodal Large Language Models: A Survey on Advances, Challenges, and Future Directions","date":"2025-03-20","arxiv_id":"2503.16585","repositories_listed":1,"syntology":null},{"url":"/paper/fin-r1-a-large-language-model-for-financial","slug":"fin-r1-a-large-language-model-for-financial","title":"Fin-R1: A Large Language Model for Financial Reasoning through Reinforcement Learning","date":"2025-03-20","arxiv_id":"2503.16252","repositories_listed":1,"syntology":null},{"url":"/paper/how-robust-are-router-llms-analysis-of-the","slug":"how-robust-are-router-llms-analysis-of-the","title":"How Robust Are Router-LLMs? Analysis of the Fragility of LLM Routing Capabilities","date":"2025-03-20","arxiv_id":"2504.07113","repositories_listed":1,"syntology":null},{"url":"/paper/the-emperor-s-new-clothes-in-benchmarking-a","slug":"the-emperor-s-new-clothes-in-benchmarking-a","title":"The Emperor's New Clothes in Benchmarking? A Rigorous Examination of Mitigation Strategies for LLM Benchmark Data Contamination","date":"2025-03-20","arxiv_id":"2503.16402","repositories_listed":1,"syntology":null},{"url":"/paper/does-context-matter-contextualjudgebench-for","slug":"does-context-matter-contextualjudgebench-for","title":"Does Context Matter? ContextualJudgeBench for Evaluating LLM-based Judges in Contextual Settings","date":"2025-03-19","arxiv_id":"2503.15620","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/does-context-matter-contextualjudgebench-for#ran","syntology_url":"https://syntology.ai/paper/2503.15620","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.15620"}},"official":{"repos":["salesforceairesearch/contextualjudgebench"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/sweet-rl-training-multi-turn-llm-agents-on","slug":"sweet-rl-training-multi-turn-llm-agents-on","title":"SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks","date":"2025-03-19","arxiv_id":"2503.15478","repositories_listed":1,"syntology":null},{"url":"/paper/gricean-norms-as-a-basis-for-effective","slug":"gricean-norms-as-a-basis-for-effective","title":"Gricean Norms as a Basis for Effective Collaboration","date":"2025-03-18","arxiv_id":"2503.14484","repositories_listed":1,"syntology":null},{"url":"/paper/leavs-an-llm-based-labeler-for-abdominal-ct","slug":"leavs-an-llm-based-labeler-for-abdominal-ct","title":"LEAVS: An LLM-based Labeler for Abdominal CT Supervision","date":"2025-03-17","arxiv_id":"2503.13330","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-on-the-optimization-of-large","slug":"a-survey-on-the-optimization-of-large","title":"A Survey on the Optimization of Large Language Model-based Agents","date":"2025-03-16","arxiv_id":"2503.12434","repositories_listed":1,"syntology":null},{"url":"/paper/svd-llm-v2-optimizing-singular-value","slug":"svd-llm-v2-optimizing-singular-value","title":"SVD-LLM V2: Optimizing Singular Value Truncation for Large Language Model Compression","date":"2025-03-16","arxiv_id":"2503.12340","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":3,"n_honours":1,"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; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/svd-llm-v2-optimizing-singular-value#ran","syntology_url":"https://syntology.ai/paper/2503.12340","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.12340"}},"official":{"repos":["aiot-mlsys-lab/svd-llm"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/collmlight-cooperative-large-language-model","slug":"collmlight-cooperative-large-language-model","title":"CoLLMLight: Cooperative Large Language Model Agents for Network-Wide Traffic Signal Control","date":"2025-03-14","arxiv_id":"2503.11739","repositories_listed":1,"syntology":null},{"url":"/paper/generative-modelling-for-mathematical","slug":"generative-modelling-for-mathematical","title":"Generative Modeling for Mathematical Discovery","date":"2025-03-14","arxiv_id":"2503.11061","repositories_listed":1,"syntology":null},{"url":"/paper/mms-llama-efficient-llm-based-audio-visual-1","slug":"mms-llama-efficient-llm-based-audio-visual-1","title":"MMS-LLaMA: Efficient LLM-based Audio-Visual Speech Recognition with Minimal Multimodal Speech Tokens","date":"2025-03-14","arxiv_id":"2503.11315","repositories_listed":1,"syntology":null},{"url":"/paper/open3dvqa-a-benchmark-for-comprehensive","slug":"open3dvqa-a-benchmark-for-comprehensive","title":"Open3DVQA: A Benchmark for Comprehensive Spatial Reasoning with Multimodal Large Language Model in Open Space","date":"2025-03-14","arxiv_id":"2503.11094","repositories_listed":1,"syntology":null},{"url":"/paper/reasoning-grounded-natural-language","slug":"reasoning-grounded-natural-language","title":"Reasoning-Grounded Natural Language Explanations for Language Models","date":"2025-03-14","arxiv_id":"2503.11248","repositories_listed":1,"syntology":null},{"url":"/paper/4d-langsplat-4d-language-gaussian-splatting","slug":"4d-langsplat-4d-language-gaussian-splatting","title":"4D LangSplat: 4D Language Gaussian Splatting via Multimodal Large Language Models","date":"2025-03-13","arxiv_id":"2503.10437","repositories_listed":1,"syntology":null},{"url":"/paper/got-unleashing-reasoning-capability-of","slug":"got-unleashing-reasoning-capability-of","title":"GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing","date":"2025-03-13","arxiv_id":"2503.10639","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/got-unleashing-reasoning-capability-of#ran","syntology_url":"https://syntology.ai/paper/2503.10639","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.10639"}},"official":{"repos":["rongyaofang/got"],"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/or-llm-agent-automating-modeling-and-solving","slug":"or-llm-agent-automating-modeling-and-solving","title":"OR-LLM-Agent: Automating Modeling and Solving of Operations Research Optimization Problem with Reasoning Large Language Model","date":"2025-03-13","arxiv_id":"2503.10009","repositories_listed":1,"syntology":null},{"url":"/paper/maneuvergpt-agentic-control-for-safe","slug":"maneuvergpt-agentic-control-for-safe","title":"ManeuverGPT Agentic Control for Safe Autonomous Stunt Maneuvers","date":"2025-03-12","arxiv_id":"2503.09035","repositories_listed":1,"syntology":null},{"url":"/paper/nvp-hri-zero-shot-natural-voice-and-posture","slug":"nvp-hri-zero-shot-natural-voice-and-posture","title":"NVP-HRI: Zero Shot Natural Voice and Posture-based Human-Robot Interaction via Large Language Model","date":"2025-03-12","arxiv_id":"2503.09335","repositories_listed":1,"syntology":null},{"url":"/paper/a-neural-symbolic-model-for-space-physics","slug":"a-neural-symbolic-model-for-space-physics","title":"A Neural Symbolic Model for Space Physics","date":"2025-03-11","arxiv_id":"2503.07994","repositories_listed":1,"syntology":null},{"url":"/paper/referring-to-any-person","slug":"referring-to-any-person","title":"Referring to Any Person","date":"2025-03-11","arxiv_id":"2503.08507","repositories_listed":1,"syntology":null},{"url":"/paper/lshan-1-0-technical-report","slug":"lshan-1-0-technical-report","title":"Lshan-1.0 Technical Report","date":"2025-03-10","arxiv_id":"2503.06949","repositories_listed":1,"syntology":null},{"url":"/paper/seedream-2-0-a-native-chinese-english","slug":"seedream-2-0-a-native-chinese-english","title":"Seedream 2.0: A Native Chinese-English Bilingual Image Generation Foundation Model","date":"2025-03-10","arxiv_id":"2503.07703","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":2,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/seedream-2-0-a-native-chinese-english#ran","syntology_url":"https://syntology.ai/paper/2503.07703","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.07703"}},"official":null}},{"url":"/paper/v2flow-unifying-visual-tokenization-and-large","slug":"v2flow-unifying-visual-tokenization-and-large","title":"V2Flow: Unifying Visual Tokenization and Large Language Model Vocabularies for Autoregressive Image Generation","date":"2025-03-10","arxiv_id":"2503.07493","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-updates-for-language-adaptation-in","slug":"dynamic-updates-for-language-adaptation-in","title":"Dynamic Updates for Language Adaptation in Visual-Language Tracking","date":"2025-03-09","arxiv_id":"2503.06621","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/dynamic-updates-for-language-adaptation-in#ran","syntology_url":"https://syntology.ai/paper/2503.06621","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.06621"}},"official":{"repos":["gxnu-zhonglab/dutrack"],"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/dsgbench-a-diverse-strategic-game-benchmark","slug":"dsgbench-a-diverse-strategic-game-benchmark","title":"DSGBench: A Diverse Strategic Game Benchmark for Evaluating LLM-based Agents in Complex Decision-Making Environments","date":"2025-03-08","arxiv_id":"2503.06047","repositories_listed":1,"syntology":null},{"url":"/paper/next-token-is-enough-realistic-image-quality","slug":"next-token-is-enough-realistic-image-quality","title":"Next Token Is Enough: Realistic Image Quality and Aesthetic Scoring with Multimodal Large Language Model","date":"2025-03-08","arxiv_id":"2503.06141","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-of-large-language-model-empowered","slug":"a-survey-of-large-language-model-empowered","title":"A Survey of Large Language Model Empowered Agents for Recommendation and Search: Towards Next-Generation Information Retrieval","date":"2025-03-07","arxiv_id":"2503.05659","repositories_listed":1,"syntology":null},{"url":"/paper/gema-score-granular-explainable-multi-agent","slug":"gema-score-granular-explainable-multi-agent","title":"GEMA-Score: Granular Explainable Multi-Agent Score for Radiology Report Evaluation","date":"2025-03-07","arxiv_id":"2503.05347","repositories_listed":1,"syntology":null},{"url":"/paper/r1-omni-explainable-omni-multimodal-emotion","slug":"r1-omni-explainable-omni-multimodal-emotion","title":"R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcement Learning","date":"2025-03-07","arxiv_id":"2503.05379","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"0 ran · 3 unverified","sample_list":"/paper/r1-omni-explainable-omni-multimodal-emotion#ran","syntology_url":"https://syntology.ai/paper/2503.05379","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.05379"}},"official":null}},{"url":"/paper/this-is-your-doge-if-it-please-you-exploring","slug":"this-is-your-doge-if-it-please-you-exploring","title":"This Is Your Doge, If It Please You: Exploring Deception and Robustness in Mixture of LLMs","date":"2025-03-07","arxiv_id":"2503.05856","repositories_listed":1,"syntology":null},{"url":"/paper/an-egocentric-vision-language-model-based","slug":"an-egocentric-vision-language-model-based","title":"An Egocentric Vision-Language Model based Portable Real-time Smart Assistant","date":"2025-03-06","arxiv_id":"2503.04250","repositories_listed":1,"syntology":null},{"url":"/paper/keeping-yourself-is-important-in-downstream","slug":"keeping-yourself-is-important-in-downstream","title":"Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model","date":"2025-03-06","arxiv_id":"2503.04543","repositories_listed":1,"syntology":null},{"url":"/paper/kidneytalk-open-no-code-deployment-of-a","slug":"kidneytalk-open-no-code-deployment-of-a","title":"KidneyTalk-open: No-code Deployment of a Private Large Language Model with Medical Documentation-Enhanced Knowledge Database for Kidney Disease","date":"2025-03-06","arxiv_id":"2503.04153","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-large-language-models-to-address","slug":"leveraging-large-language-models-to-address","title":"Leveraging Large Language Models to Address Data Scarcity in Machine Learning: Applications in Graphene Synthesis","date":"2025-03-06","arxiv_id":"2503.04870","repositories_listed":1,"syntology":null},{"url":"/paper/pp-docbee-improving-multimodal-document","slug":"pp-docbee-improving-multimodal-document","title":"PP-DocBee: Improving Multimodal Document Understanding Through a Bag of Tricks","date":"2025-03-06","arxiv_id":"2503.04065","repositories_listed":1,"syntology":null},{"url":"/paper/collaborative-expert-llms-guided-multi","slug":"collaborative-expert-llms-guided-multi","title":"Collaborative Expert LLMs Guided Multi-Objective Molecular Optimization","date":"2025-03-05","arxiv_id":"2503.03503","repositories_listed":1,"syntology":null},{"url":"/paper/pair-a-novel-large-language-model-guided","slug":"pair-a-novel-large-language-model-guided","title":"PAIR: A Novel Large Language Model-Guided Selection Strategy for Evolutionary Algorithms","date":"2025-03-05","arxiv_id":"2503.03239","repositories_listed":1,"syntology":null},{"url":"/paper/parallelized-planning-acting-for-efficient","slug":"parallelized-planning-acting-for-efficient","title":"Parallelized Planning-Acting for Efficient LLM-based Multi-Agent Systems","date":"2025-03-05","arxiv_id":"2503.03505","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/parallelized-planning-acting-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2503.03505","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.03505"}},"official":{"repos":["zju-vipa/odyssey"],"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/divprune-diversity-based-visual-token-pruning","slug":"divprune-diversity-based-visual-token-pruning","title":"DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models","date":"2025-03-04","arxiv_id":"2503.02175","repositories_listed":1,"syntology":null},{"url":"/paper/generator-assistant-stepwise-rollback","slug":"generator-assistant-stepwise-rollback","title":"Generator-Assistant Stepwise Rollback Framework for Large Language Model Agent","date":"2025-03-04","arxiv_id":"2503.02519","repositories_listed":1,"syntology":null},{"url":"/paper/haste-makes-waste-evaluating-planning","slug":"haste-makes-waste-evaluating-planning","title":"Haste Makes Waste: Evaluating Planning Abilities of LLMs for Efficient and Feasible Multitasking with Time Constraints Between Actions","date":"2025-03-04","arxiv_id":"2503.02238","repositories_listed":1,"syntology":null},{"url":"/paper/infinisst-simultaneous-translation-of","slug":"infinisst-simultaneous-translation-of","title":"InfiniSST: Simultaneous Translation of Unbounded Speech with Large Language Model","date":"2025-03-04","arxiv_id":"2503.02969","repositories_listed":1,"syntology":null},{"url":"/paper/llm-tabflow-synthetic-tabular-data-generation","slug":"llm-tabflow-synthetic-tabular-data-generation","title":"LLM-TabFlow: Synthetic Tabular Data Generation with Inter-column Logical Relationship Preservation","date":"2025-03-04","arxiv_id":"2503.02161","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-ai-predicts-clinical-outcomes-of","slug":"multimodal-ai-predicts-clinical-outcomes-of","title":"Multimodal AI predicts clinical outcomes of drug combinations from preclinical data","date":"2025-03-04","arxiv_id":"2503.02781","repositories_listed":1,"syntology":null},{"url":"/paper/2503-01273","slug":"2503-01273","title":"OptMetaOpenFOAM: Large Language Model Driven Chain of Thought for Sensitivity Analysis and Parameter Optimization based on CFD","date":"2025-03-03","arxiv_id":"2503.01273","repositories_listed":1,"syntology":null},{"url":"/paper/can-a-i-change-your-mind","slug":"can-a-i-change-your-mind","title":"Can (A)I Change Your Mind?","date":"2025-03-03","arxiv_id":"2503.01844","repositories_listed":1,"syntology":null},{"url":"/paper/llms-as-educational-analysts-transforming","slug":"llms-as-educational-analysts-transforming","title":"LLMs as Educational Analysts: Transforming Multimodal Data Traces into Actionable Reading Assessment Reports","date":"2025-03-03","arxiv_id":"2503.02099","repositories_listed":1,"syntology":null},{"url":"/paper/modeling-fine-grained-hand-object-dynamics","slug":"modeling-fine-grained-hand-object-dynamics","title":"Modeling Fine-Grained Hand-Object Dynamics for Egocentric Video Representation Learning","date":"2025-03-02","arxiv_id":"2503.00986","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/modeling-fine-grained-hand-object-dynamics#ran","syntology_url":"https://syntology.ai/paper/2503.00986","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.00986"}},"official":{"repos":["openrobotlab/egohod"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/patient-level-anatomy-meets-scanning-level","slug":"patient-level-anatomy-meets-scanning-level","title":"Patient-Level Anatomy Meets Scanning-Level Physics: Personalized Federated Low-Dose CT Denoising Empowered by Large Language Model","date":"2025-03-02","arxiv_id":"2503.00908","repositories_listed":1,"syntology":null},{"url":"/paper/2503-00555","slug":"2503-00555","title":"Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable","date":"2025-03-01","arxiv_id":"2503.00555","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"4 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/2503-00555#ran","syntology_url":"https://syntology.ai/paper/2503.00555","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.00555"}},"official":{"repos":["git-disl/safety-tax"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/sgc-net-stratified-granular-comparison","slug":"sgc-net-stratified-granular-comparison","title":"SGC-Net: Stratified Granular Comparison Network for Open-Vocabulary HOI Detection","date":"2025-03-01","arxiv_id":"2503.00414","repositories_listed":1,"syntology":null},{"url":"/paper/2503-00084","slug":"2503-00084","title":"InspireMusic: Integrating Super Resolution and Large Language Model for High-Fidelity Long-Form Music Generation","date":"2025-02-28","arxiv_id":"2503.00084","repositories_listed":1,"syntology":null},{"url":"/paper/towards-general-visual-linguistic-face-1","slug":"towards-general-visual-linguistic-face-1","title":"Towards General Visual-Linguistic Face Forgery Detection(V2)","date":"2025-02-28","arxiv_id":"2502.20698","repositories_listed":1,"syntology":null},{"url":"/paper/udora-a-unified-red-teaming-framework-against","slug":"udora-a-unified-red-teaming-framework-against","title":"UDora: A Unified Red Teaming Framework against LLM Agents by Dynamically Hijacking Their Own Reasoning","date":"2025-02-28","arxiv_id":"2503.01908","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 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; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/udora-a-unified-red-teaming-framework-against#ran","syntology_url":"https://syntology.ai/paper/2503.01908","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.01908"}},"official":{"repos":["ai-secure/udora"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/adaptive-attacks-break-defenses-against","slug":"adaptive-attacks-break-defenses-against","title":"Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents","date":"2025-02-27","arxiv_id":"2503.00061","repositories_listed":1,"syntology":null},{"url":"/paper/asymlora-harmonizing-data-conflicts-and","slug":"asymlora-harmonizing-data-conflicts-and","title":"AsymLoRA: Harmonizing Data Conflicts and Commonalities in MLLMs","date":"2025-02-27","arxiv_id":"2502.20035","repositories_listed":1,"syntology":null},{"url":"/paper/collaborative-stance-detection-via-small","slug":"collaborative-stance-detection-via-small","title":"Collaborative Stance Detection via Small-Large Language Model Consistency Verification","date":"2025-02-27","arxiv_id":"2502.19954","repositories_listed":1,"syntology":null},{"url":"/paper/playing-pokemon-red-via-deep-reinforcement","slug":"playing-pokemon-red-via-deep-reinforcement","title":"Playing Pokémon Red via Deep Reinforcement Learning","date":"2025-02-27","arxiv_id":"2502.19920","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/playing-pokemon-red-via-deep-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2502.19920","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.19920"}},"official":{"repos":["MarcoMeter/neroRL"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}}],"record_sha256":"94567dcd2cf0a98b026310dab8905472b71536a88e67be2b630fb03269c1a626","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}