{"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/18","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":18,"pages_in_order":177,"rows_per_page":100,"rows":[1701,1800],"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/17","next":"/task/language-modelling/papers/19","papers":[{"url":"/paper/healthgpt-a-medical-large-vision-language","slug":"healthgpt-a-medical-large-vision-language","title":"HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation","date":"2025-02-14","arxiv_id":"2502.09838","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/healthgpt-a-medical-large-vision-language#ran","syntology_url":"https://syntology.ai/paper/2502.09838","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.09838"}},"official":{"repos":["dcdmllm/healthgpt"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/reinforced-large-language-model-is-a-formal","slug":"reinforced-large-language-model-is-a-formal","title":"Reinforced Large Language Model is a formal theorem prover","date":"2025-02-13","arxiv_id":"2502.08908","repositories_listed":1,"syntology":null},{"url":"/paper/vision-language-in-context-learning-driven","slug":"vision-language-in-context-learning-driven","title":"Vision-Language In-Context Learning Driven Few-Shot Visual Inspection Model","date":"2025-02-13","arxiv_id":"2502.09057","repositories_listed":1,"syntology":null},{"url":"/paper/selfelicit-your-language-model-secretly-knows","slug":"selfelicit-your-language-model-secretly-knows","title":"SelfElicit: Your Language Model Secretly Knows Where is the Relevant Evidence","date":"2025-02-12","arxiv_id":"2502.08767","repositories_listed":1,"syntology":null},{"url":"/paper/vila-mil-dual-scale-vision-language-multiple-1","slug":"vila-mil-dual-scale-vision-language-multiple-1","title":"ViLa-MIL: Dual-scale Vision-Language Multiple Instance Learning for Whole Slide Image Classification","date":"2025-02-12","arxiv_id":"2502.08391","repositories_listed":1,"syntology":null},{"url":"/paper/auditing-prompt-caching-in-language-model","slug":"auditing-prompt-caching-in-language-model","title":"Auditing Prompt Caching in Language Model APIs","date":"2025-02-11","arxiv_id":"2502.07776","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/auditing-prompt-caching-in-language-model#ran","syntology_url":"https://syntology.ai/paper/2502.07776","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.07776"}},"official":{"repos":["chenchenygu/auditing-prompt-caching"],"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/jamendomaxcaps-a-large-scale-music-caption","slug":"jamendomaxcaps-a-large-scale-music-caption","title":"JamendoMaxCaps: A Large Scale Music-caption Dataset with Imputed Metadata","date":"2025-02-11","arxiv_id":"2502.07461","repositories_listed":1,"syntology":null},{"url":"/paper/mask-enhanced-autoregressive-prediction-pay","slug":"mask-enhanced-autoregressive-prediction-pay","title":"Mask-Enhanced Autoregressive Prediction: Pay Less Attention to Learn More","date":"2025-02-11","arxiv_id":"2502.07490","repositories_listed":1,"syntology":null},{"url":"/paper/metasc-test-time-safety-specification","slug":"metasc-test-time-safety-specification","title":"MetaSC: Test-Time Safety Specification Optimization for Language Models","date":"2025-02-11","arxiv_id":"2502.07985","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/metasc-test-time-safety-specification#ran","syntology_url":"https://syntology.ai/paper/2502.07985","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.07985"}},"official":{"repos":["vicgalle/meta-self-critique"],"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/mgpath-vision-language-model-with-multi","slug":"mgpath-vision-language-model-with-multi","title":"MGPATH: Vision-Language Model with Multi-Granular Prompt Learning for Few-Shot WSI Classification","date":"2025-02-11","arxiv_id":"2502.07409","repositories_listed":1,"syntology":null},{"url":"/paper/small-language-model-makes-an-effective-long","slug":"small-language-model-makes-an-effective-long","title":"Small Language Model Makes an Effective Long Text Extractor","date":"2025-02-11","arxiv_id":"2502.07286","repositories_listed":1,"syntology":null},{"url":"/paper/implicit-language-models-are-rnns-balancing","slug":"implicit-language-models-are-rnns-balancing","title":"Implicit Language Models are RNNs: Balancing Parallelization and Expressivity","date":"2025-02-10","arxiv_id":"2502.07827","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":1,"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/implicit-language-models-are-rnns-balancing#ran","syntology_url":"https://syntology.ai/paper/2502.07827","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.07827"}},"official":{"repos":["microsoft/implicit_languagemodels"],"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/jakiro-boosting-speculative-decoding-with","slug":"jakiro-boosting-speculative-decoding-with","title":"Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE","date":"2025-02-10","arxiv_id":"2502.06282","repositories_listed":1,"syntology":null},{"url":"/paper/rallrec-improving-retrieval-augmented-large","slug":"rallrec-improving-retrieval-augmented-large","title":"RALLRec: Improving Retrieval Augmented Large Language Model Recommendation with Representation Learning","date":"2025-02-10","arxiv_id":"2502.06101","repositories_listed":1,"syntology":null},{"url":"/paper/steel-llm-from-scratch-to-open-source-a","slug":"steel-llm-from-scratch-to-open-source-a","title":"Steel-LLM:From Scratch to Open Source -- A Personal Journey in Building a Chinese-Centric LLM","date":"2025-02-10","arxiv_id":"2502.06635","repositories_listed":1,"syntology":null},{"url":"/paper/dexvla-vision-language-model-with-plug-in","slug":"dexvla-vision-language-model-with-plug-in","title":"DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control","date":"2025-02-09","arxiv_id":"2502.05855","repositories_listed":1,"syntology":null},{"url":"/paper/investigating-compositional-reasoning-in-time","slug":"investigating-compositional-reasoning-in-time","title":"Investigating Compositional Reasoning in Time Series Foundation Models","date":"2025-02-09","arxiv_id":"2502.06037","repositories_listed":1,"syntology":null},{"url":"/paper/let-the-ai-conspiracy-begin-language-model","slug":"let-the-ai-conspiracy-begin-language-model","title":"HSI: Head-Specific Intervention Can Induce Misaligned AI Coordination in Large Language Models","date":"2025-02-09","arxiv_id":"2502.05945","repositories_listed":1,"syntology":null},{"url":"/paper/indextts-an-industrial-level-controllable-and","slug":"indextts-an-industrial-level-controllable-and","title":"IndexTTS: An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System","date":"2025-02-08","arxiv_id":"2502.05512","repositories_listed":1,"syntology":null},{"url":"/paper/unicms-a-unified-consistency-model-for","slug":"unicms-a-unified-consistency-model-for","title":"UniCMs: A Unified Consistency Model For Efficient Multimodal Generation and Understanding","date":"2025-02-08","arxiv_id":"2502.05415","repositories_listed":1,"syntology":null},{"url":"/paper/agentic-reasoning-reasoning-llms-with-tools","slug":"agentic-reasoning-reasoning-llms-with-tools","title":"Agentic Reasoning: Reasoning LLMs with Tools for the Deep Research","date":"2025-02-07","arxiv_id":"2502.04644","repositories_listed":1,"syntology":null},{"url":"/paper/gemstones-a-model-suite-for-multi-faceted","slug":"gemstones-a-model-suite-for-multi-faceted","title":"Gemstones: A Model Suite for Multi-Faceted Scaling Laws","date":"2025-02-07","arxiv_id":"2502.06857","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"6 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; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/gemstones-a-model-suite-for-multi-faceted#ran","syntology_url":"https://syntology.ai/paper/2502.06857","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.06857"}},"official":{"repos":["mcleish7/gemstone-scaling-laws"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/long-vita-scaling-large-multi-modal-models-to","slug":"long-vita-scaling-large-multi-modal-models-to","title":"Long-VITA: Scaling Large Multi-modal Models to 1 Million Tokens with Leading Short-Context Accuray","date":"2025-02-07","arxiv_id":"2502.05177","repositories_listed":1,"syntology":null},{"url":"/paper/position-aware-automatic-circuit-discovery","slug":"position-aware-automatic-circuit-discovery","title":"Position-aware Automatic Circuit Discovery","date":"2025-02-07","arxiv_id":"2502.04577","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":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) · 0 unverified","sample_list":"/paper/position-aware-automatic-circuit-discovery#ran","syntology_url":"https://syntology.ai/paper/2502.04577","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.04577"}},"official":{"repos":["technion-cs-nlp/peap"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/prot2chat-protein-llm-with-early-fusion-of","slug":"prot2chat-protein-llm-with-early-fusion-of","title":"Prot2Chat: Protein LLM with Early-Fusion of Text, Sequence and Structure","date":"2025-02-07","arxiv_id":"2502.06846","repositories_listed":1,"syntology":null},{"url":"/paper/adiff-explaining-audio-difference-using","slug":"adiff-explaining-audio-difference-using","title":"ADIFF: Explaining audio difference using natural language","date":"2025-02-06","arxiv_id":"2502.04476","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/adiff-explaining-audio-difference-using#ran","syntology_url":"https://syntology.ai/paper/2502.04476","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.04476"}},"official":{"repos":["soham97/adiff"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/chamaleonllm-batch-aware-dynamic-low-rank","slug":"chamaleonllm-batch-aware-dynamic-low-rank","title":"ChamaleonLLM: Batch-Aware Dynamic Low-Rank Adaptation via Inference-Time Clusters","date":"2025-02-06","arxiv_id":"2502.04315","repositories_listed":1,"syntology":null},{"url":"/paper/division-of-thoughts-harnessing-hybrid","slug":"division-of-thoughts-harnessing-hybrid","title":"Division-of-Thoughts: Harnessing Hybrid Language Model Synergy for Efficient On-Device Agents","date":"2025-02-06","arxiv_id":"2502.04392","repositories_listed":1,"syntology":null},{"url":"/paper/multi-agent-architecture-search-via-agentic","slug":"multi-agent-architecture-search-via-agentic","title":"Multi-agent Architecture Search via Agentic Supernet","date":"2025-02-06","arxiv_id":"2502.04180","repositories_listed":1,"syntology":null},{"url":"/paper/ola-pushing-the-frontiers-of-omni-modal","slug":"ola-pushing-the-frontiers-of-omni-modal","title":"Ola: Pushing the Frontiers of Omni-Modal Language Model","date":"2025-02-06","arxiv_id":"2502.04328","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/ola-pushing-the-frontiers-of-omni-modal#ran","syntology_url":"https://syntology.ai/paper/2502.04328","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.04328"}},"official":{"repos":["ola-omni/ola"],"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/robotouille-an-asynchronous-planning","slug":"robotouille-an-asynchronous-planning","title":"Robotouille: An Asynchronous Planning Benchmark for LLM Agents","date":"2025-02-06","arxiv_id":"2502.05227","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/robotouille-an-asynchronous-planning#ran","syntology_url":"https://syntology.ai/paper/2502.05227","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.05227"}},"official":{"repos":["portal-cornell/robotouille"],"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/scoreflow-mastering-llm-agent-workflows-via","slug":"scoreflow-mastering-llm-agent-workflows-via","title":"ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimization","date":"2025-02-06","arxiv_id":"2502.04306","repositories_listed":1,"syntology":null},{"url":"/paper/waferllm-a-wafer-scale-llm-inference-system","slug":"waferllm-a-wafer-scale-llm-inference-system","title":"WaferLLM: Large Language Model Inference at Wafer Scale","date":"2025-02-06","arxiv_id":"2502.04563","repositories_listed":1,"syntology":null},{"url":"/paper/do-large-language-model-benchmarks-test","slug":"do-large-language-model-benchmarks-test","title":"Do Large Language Model Benchmarks Test Reliability?","date":"2025-02-05","arxiv_id":"2502.03461","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-reasoning-to-adapt-large-language","slug":"enhancing-reasoning-to-adapt-large-language","title":"Enhancing Reasoning to Adapt Large Language Models for Domain-Specific Applications","date":"2025-02-05","arxiv_id":"2502.04384","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/enhancing-reasoning-to-adapt-large-language#ran","syntology_url":"https://syntology.ai/paper/2502.04384","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.04384"}},"official":{"repos":["wenboown/generative-ai-for-semiconductor-physical-design"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/gompertz-linear-units-leveraging-asymmetry-1","slug":"gompertz-linear-units-leveraging-asymmetry-1","title":"Gompertz Linear Units: Leveraging Asymmetry for Enhanced Learning Dynamics","date":"2025-02-05","arxiv_id":"2502.03654","repositories_listed":1,"syntology":null},{"url":"/paper/intent-representation-learning-with-large","slug":"intent-representation-learning-with-large","title":"Intent Representation Learning with Large Language Model for Recommendation","date":"2025-02-05","arxiv_id":"2502.03307","repositories_listed":1,"syntology":null},{"url":"/paper/citer-collaborative-inference-for-efficient","slug":"citer-collaborative-inference-for-efficient","title":"CITER: Collaborative Inference for Efficient Large Language Model Decoding with Token-Level Routing","date":"2025-02-04","arxiv_id":"2502.01976","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/citer-collaborative-inference-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2502.01976","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.01976"}},"official":{"repos":["aiming-lab/CITER"],"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/connections-between-schedule-free-optimizers","slug":"connections-between-schedule-free-optimizers","title":"Connections between Schedule-Free Optimizers, AdEMAMix, and Accelerated SGD Variants","date":"2025-02-04","arxiv_id":"2502.02431","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/connections-between-schedule-free-optimizers#ran","syntology_url":"https://syntology.ai/paper/2502.02431","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.02431"}},"official":{"repos":["depenm/simplified-ademamix"],"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/reusing-embeddings-reproducible-reward-model","slug":"reusing-embeddings-reproducible-reward-model","title":"Reusing Embeddings: Reproducible Reward Model Research in Large Language Model Alignment without GPUs","date":"2025-02-04","arxiv_id":"2502.04357","repositories_listed":1,"syntology":null},{"url":"/paper/reviving-the-classics-active-reward-modeling","slug":"reviving-the-classics-active-reward-modeling","title":"Reviving The Classics: Active Reward Modeling in Large Language Model Alignment","date":"2025-02-04","arxiv_id":"2502.04354","repositories_listed":1,"syntology":null},{"url":"/paper/when-dimensionality-hurts-the-role-of-llm","slug":"when-dimensionality-hurts-the-role-of-llm","title":"When Dimensionality Hurts: The Role of LLM Embedding Compression for Noisy Regression Tasks","date":"2025-02-04","arxiv_id":"2502.02199","repositories_listed":1,"syntology":null},{"url":"/paper/explaining-context-length-scaling-and-bounds","slug":"explaining-context-length-scaling-and-bounds","title":"Explaining Context Length Scaling and Bounds for Language Models","date":"2025-02-03","arxiv_id":"2502.01481","repositories_listed":1,"syntology":null},{"url":"/paper/fine-tuning-discrete-diffusion-models-with","slug":"fine-tuning-discrete-diffusion-models-with","title":"Fine-Tuning Discrete Diffusion Models with Policy Gradient Methods","date":"2025-02-03","arxiv_id":"2502.01384","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":6,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/fine-tuning-discrete-diffusion-models-with#ran","syntology_url":"https://syntology.ai/paper/2502.01384","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.01384"}},"official":{"repos":["ozekri/SEPO"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/learnable-polynomial-trigonometric-and","slug":"learnable-polynomial-trigonometric-and","title":"Polynomial, trigonometric, and tropical activations","date":"2025-02-03","arxiv_id":"2502.01247","repositories_listed":1,"syntology":null},{"url":"/paper/qless-a-quantized-approach-for-data-valuation","slug":"qless-a-quantized-approach-for-data-valuation","title":"QLESS: A Quantized Approach for Data Valuation and Selection in Large Language Model Fine-Tuning","date":"2025-02-03","arxiv_id":"2502.01703","repositories_listed":1,"syntology":null},{"url":"/paper/simulating-rumor-spreading-in-social-networks","slug":"simulating-rumor-spreading-in-social-networks","title":"Simulating Rumor Spreading in Social Networks using LLM Agents","date":"2025-02-03","arxiv_id":"2502.01450","repositories_listed":1,"syntology":null},{"url":"/paper/avoiding-mathbf-exp-r-max-scaling-in-rlhf","slug":"avoiding-mathbf-exp-r-max-scaling-in-rlhf","title":"Avoiding $\\mathbf{exp(R_{max})}$ scaling in RLHF through Preference-based Exploration","date":"2025-02-02","arxiv_id":"2502.00666","repositories_listed":1,"syntology":null},{"url":"/paper/llm-safety-alignment-is-divergence-estimation","slug":"llm-safety-alignment-is-divergence-estimation","title":"LLM Safety Alignment is Divergence Estimation in Disguise","date":"2025-02-02","arxiv_id":"2502.00657","repositories_listed":1,"syntology":{"n":17,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/llm-safety-alignment-is-divergence-estimation#ran","syntology_url":"https://syntology.ai/paper/2502.00657","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.00657"}},"official":{"repos":["rhaldarpurdue/kldo"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/metaopenfoam-2-0-large-language-model-driven","slug":"metaopenfoam-2-0-large-language-model-driven","title":"MetaOpenFOAM 2.0: Large Language Model Driven Chain of Thought for Automating CFD Simulation and Post-Processing","date":"2025-02-01","arxiv_id":"2502.00498","repositories_listed":1,"syntology":null},{"url":"/paper/speculative-ensemble-fast-large-language","slug":"speculative-ensemble-fast-large-language","title":"Speculative Ensemble: Fast Large Language Model Ensemble via Speculation","date":"2025-02-01","arxiv_id":"2502.01662","repositories_listed":1,"syntology":null},{"url":"/paper/improving-the-robustness-of-representation","slug":"improving-the-robustness-of-representation","title":"Improving LLM Unlearning Robustness via Random Perturbations","date":"2025-01-31","arxiv_id":"2501.19202","repositories_listed":1,"syntology":null},{"url":"/paper/llmdet-learning-strong-open-vocabulary-object","slug":"llmdet-learning-strong-open-vocabulary-object","title":"LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models","date":"2025-01-31","arxiv_id":"2501.18954","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":11,"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) · 1 unverified","sample_list":"/paper/llmdet-learning-strong-open-vocabulary-object#ran","syntology_url":"https://syntology.ai/paper/2501.18954","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.18954"}},"official":{"repos":["isee-laboratory/llmdet"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/partially-rewriting-a-transformer-in-natural","slug":"partially-rewriting-a-transformer-in-natural","title":"Partially Rewriting a Transformer in Natural Language","date":"2025-01-31","arxiv_id":"2501.18838","repositories_listed":1,"syntology":null},{"url":"/paper/scalable-softmax-is-superior-for-attention","slug":"scalable-softmax-is-superior-for-attention","title":"Scalable-Softmax Is Superior for Attention","date":"2025-01-31","arxiv_id":"2501.19399","repositories_listed":1,"syntology":null},{"url":"/paper/differentially-private-steering-for-large","slug":"differentially-private-steering-for-large","title":"Differentially Private Steering for Large Language Model Alignment","date":"2025-01-30","arxiv_id":"2501.18532","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/differentially-private-steering-for-large#ran","syntology_url":"https://syntology.ai/paper/2501.18532","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.18532"}},"official":{"repos":["ukplab/iclr2025-psa"],"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/wildchat-50m-a-deep-dive-into-the-role-of","slug":"wildchat-50m-a-deep-dive-into-the-role-of","title":"WILDCHAT-50M: A Deep Dive Into the Role of Synthetic Data in Post-Training","date":"2025-01-30","arxiv_id":"2501.18511","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/wildchat-50m-a-deep-dive-into-the-role-of#ran","syntology_url":"https://syntology.ai/paper/2501.18511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.18511"}},"official":{"repos":["penfever/wildchat-50m"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/2ssp-a-two-stage-framework-for-structured","slug":"2ssp-a-two-stage-framework-for-structured","title":"2SSP: A Two-Stage Framework for Structured Pruning of LLMs","date":"2025-01-29","arxiv_id":"2501.17771","repositories_listed":1,"syntology":null},{"url":"/paper/can-generative-llms-create-query-variants-for","slug":"can-generative-llms-create-query-variants-for","title":"Can Generative LLMs Create Query Variants for Test Collections? An Exploratory Study","date":"2025-01-29","arxiv_id":"2501.17981","repositories_listed":1,"syntology":null},{"url":"/paper/is-conversational-xai-all-you-need-human-ai","slug":"is-conversational-xai-all-you-need-human-ai","title":"Is Conversational XAI All You Need? Human-AI Decision Making With a Conversational XAI Assistant","date":"2025-01-29","arxiv_id":"2501.17546","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-multimodal-llm-for-inspirational","slug":"leveraging-multimodal-llm-for-inspirational","title":"Leveraging Multimodal LLM for Inspirational User Interface Search","date":"2025-01-29","arxiv_id":"2501.17799","repositories_listed":1,"syntology":null},{"url":"/paper/axbench-steering-llms-even-simple-baselines","slug":"axbench-steering-llms-even-simple-baselines","title":"AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders","date":"2025-01-28","arxiv_id":"2501.17148","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/axbench-steering-llms-even-simple-baselines#ran","syntology_url":"https://syntology.ai/paper/2501.17148","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.17148"}},"official":{"repos":["stanfordnlp/axbench"],"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/document-screenshot-retrievers-are-vulnerable","slug":"document-screenshot-retrievers-are-vulnerable","title":"Document Screenshot Retrievers are Vulnerable to Pixel Poisoning Attacks","date":"2025-01-28","arxiv_id":"2501.16902","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-model-critics-for-execution","slug":"large-language-model-critics-for-execution","title":"Large Language Model Critics for Execution-Free Evaluation of Code Changes","date":"2025-01-28","arxiv_id":"2501.16655","repositories_listed":1,"syntology":null},{"url":"/paper/radiollm-introducing-large-language-model","slug":"radiollm-introducing-large-language-model","title":"RadioLLM: Introducing Large Language Model into Cognitive Radio via Hybrid Prompt and Token Reprogrammings","date":"2025-01-28","arxiv_id":"2501.17888","repositories_listed":1,"syntology":null},{"url":"/paper/saferag-benchmarking-security-in-retrieval","slug":"saferag-benchmarking-security-in-retrieval","title":"SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language Model","date":"2025-01-28","arxiv_id":"2501.18636","repositories_listed":1,"syntology":null},{"url":"/paper/cilp-fgdi-exploiting-vision-language-model","slug":"cilp-fgdi-exploiting-vision-language-model","title":"CILP-FGDI: Exploiting Vision-Language Model for Generalizable Person Re-Identification","date":"2025-01-27","arxiv_id":"2501.16065","repositories_listed":1,"syntology":null},{"url":"/paper/is-it-navajo-accurate-language-detection-in","slug":"is-it-navajo-accurate-language-detection-in","title":"Is It Navajo? Accurate Language Detection in Endangered Athabaskan Languages","date":"2025-01-27","arxiv_id":"2501.15773","repositories_listed":1,"syntology":null},{"url":"/paper/arwkv-pretrain-is-not-what-we-need-an-rnn","slug":"arwkv-pretrain-is-not-what-we-need-an-rnn","title":"ARWKV: Pretrain is not what we need, an RNN-Attention-Based Language Model Born from Transformer","date":"2025-01-26","arxiv_id":"2501.15570","repositories_listed":1,"syntology":null},{"url":"/paper/ocean-ocr-towards-general-ocr-application-via","slug":"ocean-ocr-towards-general-ocr-application-via","title":"Ocean-OCR: Towards General OCR Application via a Vision-Language Model","date":"2025-01-26","arxiv_id":"2501.15558","repositories_listed":1,"syntology":null},{"url":"/paper/patchrec-multi-grained-patching-for-efficient","slug":"patchrec-multi-grained-patching-for-efficient","title":"Multi-Grained Patch Training for Efficient LLM-based Recommendation","date":"2025-01-25","arxiv_id":"2501.15087","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/patchrec-multi-grained-patching-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2501.15087","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.15087"}},"official":{"repos":["ljy0ustc/patchrec"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-zero-shot-llm-framework-for-automatic","slug":"a-zero-shot-llm-framework-for-automatic","title":"A Zero-Shot LLM Framework for Automatic Assignment Grading in Higher Education","date":"2025-01-24","arxiv_id":"2501.14305","repositories_listed":1,"syntology":null},{"url":"/paper/dressing-up-llm-efficient-stylized-question","slug":"dressing-up-llm-efficient-stylized-question","title":"DRESSing Up LLM: Efficient Stylized Question-Answering via Style Subspace Editing","date":"2025-01-24","arxiv_id":"2501.14371","repositories_listed":1,"syntology":null},{"url":"/paper/fast-think-on-graph-wider-deeper-and-faster","slug":"fast-think-on-graph-wider-deeper-and-faster","title":"Fast Think-on-Graph: Wider, Deeper and Faster Reasoning of Large Language Model on Knowledge Graph","date":"2025-01-24","arxiv_id":"2501.14300","repositories_listed":1,"syntology":null},{"url":"/paper/hermes-a-unified-self-driving-world-model-for","slug":"hermes-a-unified-self-driving-world-model-for","title":"HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generation","date":"2025-01-24","arxiv_id":"2501.14729","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/hermes-a-unified-self-driving-world-model-for#ran","syntology_url":"https://syntology.ai/paper/2501.14729","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.14729"}},"official":{"repos":["lmd0311/hermes"],"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/realcritic-towards-effectiveness-driven","slug":"realcritic-towards-effectiveness-driven","title":"RealCritic: Towards Effectiveness-Driven Evaluation of Language Model Critiques","date":"2025-01-24","arxiv_id":"2501.14492","repositories_listed":1,"syntology":null},{"url":"/paper/wormhole-memory-a-rubik-s-cube-for-cross","slug":"wormhole-memory-a-rubik-s-cube-for-cross","title":"Wormhole Memory: A Rubik's Cube for Cross-Dialogue Retrieval","date":"2025-01-24","arxiv_id":"2501.14846","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-biomedical-relation-extraction-with-1","slug":"enhancing-biomedical-relation-extraction-with-1","title":"Enhancing Biomedical Relation Extraction with Directionality","date":"2025-01-23","arxiv_id":"2501.14079","repositories_listed":1,"syntology":null},{"url":"/paper/multi-aspect-knowledge-distillation-with","slug":"multi-aspect-knowledge-distillation-with","title":"Multi-aspect Knowledge Distillation with Large Language Model","date":"2025-01-23","arxiv_id":"2501.13341","repositories_listed":1,"syntology":null},{"url":"/paper/ostquant-refining-large-language-model","slug":"ostquant-refining-large-language-model","title":"OstQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting","date":"2025-01-23","arxiv_id":"2501.13987","repositories_listed":1,"syntology":{"n":15,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/ostquant-refining-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2501.13987","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.13987"}},"official":{"repos":["brotherhappy/ostquant"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/the-breeze-2-herd-of-models-traditional","slug":"the-breeze-2-herd-of-models-traditional","title":"The Breeze 2 Herd of Models: Traditional Chinese LLMs Based on Llama with Vision-Aware and Function-Calling Capabilities","date":"2025-01-23","arxiv_id":"2501.13921","repositories_listed":1,"syntology":null},{"url":"/paper/accessible-smart-contracts-verification","slug":"accessible-smart-contracts-verification","title":"Accessible Smart Contracts Verification: Synthesizing Formal Models with Tamed LLMs","date":"2025-01-22","arxiv_id":"2501.12972","repositories_listed":1,"syntology":null},{"url":"/paper/viddar-vision-language-model-based-task","slug":"viddar-vision-language-model-based-task","title":"ViDDAR: Vision Language Model-Based Task-Detrimental Content Detection for Augmented Reality","date":"2025-01-22","arxiv_id":"2501.12553","repositories_listed":1,"syntology":null},{"url":"/paper/aloftrag-automatic-local-fine-tuning-for","slug":"aloftrag-automatic-local-fine-tuning-for","title":"ALoFTRAG: Automatic Local Fine Tuning for Retrieval Augmented Generation","date":"2025-01-21","arxiv_id":"2501.11929","repositories_listed":1,"syntology":null},{"url":"/paper/network-informed-prompt-engineering-against","slug":"network-informed-prompt-engineering-against","title":"Network-informed Prompt Engineering against Organized Astroturf Campaigns under Extreme Class Imbalance","date":"2025-01-21","arxiv_id":"2501.11849","repositories_listed":1,"syntology":null},{"url":"/paper/panoramic-interests-stylistic-content-aware-1","slug":"panoramic-interests-stylistic-content-aware-1","title":"Panoramic Interests: Stylistic-Content Aware Personalized Headline Generation","date":"2025-01-21","arxiv_id":"2501.11900","repositories_listed":1,"syntology":null},{"url":"/paper/advancing-language-model-reasoning-through","slug":"advancing-language-model-reasoning-through","title":"Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling","date":"2025-01-20","arxiv_id":"2501.11651","repositories_listed":1,"syntology":null},{"url":"/paper/agent-r-training-language-model-agents-to","slug":"agent-r-training-language-model-agents-to","title":"Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training","date":"2025-01-20","arxiv_id":"2501.11425","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":6,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/agent-r-training-language-model-agents-to#ran","syntology_url":"https://syntology.ai/paper/2501.11425","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.11425"}},"official":{"repos":["bytedance/agent-r"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/endochat-grounded-multimodal-large-language","slug":"endochat-grounded-multimodal-large-language","title":"EndoChat: Grounded Multimodal Large Language Model for Endoscopic Surgery","date":"2025-01-20","arxiv_id":"2501.11347","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/endochat-grounded-multimodal-large-language#ran","syntology_url":"https://syntology.ai/paper/2501.11347","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.11347"}},"official":{"repos":["gkw0010/endochat"],"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/glinthawk-a-two-tiered-architecture-for-high","slug":"glinthawk-a-two-tiered-architecture-for-high","title":"Glinthawk: A Two-Tiered Architecture for Offline LLM Inference","date":"2025-01-20","arxiv_id":"2501.11779","repositories_listed":1,"syntology":null},{"url":"/paper/pike-rag-specialized-knowledge-and-rationale","slug":"pike-rag-specialized-knowledge-and-rationale","title":"PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation","date":"2025-01-20","arxiv_id":"2501.11551","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/pike-rag-specialized-knowledge-and-rationale#ran","syntology_url":"https://syntology.ai/paper/2501.11551","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.11551"}},"official":{"repos":["microsoft/pike-rag"],"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/adaptivelog-an-adaptive-log-analysis","slug":"adaptivelog-an-adaptive-log-analysis","title":"AdaptiveLog: An Adaptive Log Analysis Framework with the Collaboration of Large and Small Language Model","date":"2025-01-19","arxiv_id":"2501.11031","repositories_listed":1,"syntology":null},{"url":"/paper/bok-introducing-bag-of-keywords-loss-for","slug":"bok-introducing-bag-of-keywords-loss-for","title":"BoK: Introducing Bag-of-Keywords Loss for Interpretable Dialogue Response Generation","date":"2025-01-17","arxiv_id":"2501.10328","repositories_listed":1,"syntology":null},{"url":"/paper/clip-pcqa-exploring-subjective-aligned-vision","slug":"clip-pcqa-exploring-subjective-aligned-vision","title":"CLIP-PCQA: Exploring Subjective-Aligned Vision-Language Modeling for Point Cloud Quality Assessment","date":"2025-01-17","arxiv_id":"2501.10071","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-reward-hacking-causal-rewards-for","slug":"beyond-reward-hacking-causal-rewards-for","title":"Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment","date":"2025-01-16","arxiv_id":"2501.09620","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/beyond-reward-hacking-causal-rewards-for#ran","syntology_url":"https://syntology.ai/paper/2501.09620","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.09620"}},"official":{"repos":["tatsu-lab/alpaca_farm"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/monte-carlo-tree-search-for-comprehensive","slug":"monte-carlo-tree-search-for-comprehensive","title":"Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Design","date":"2025-01-15","arxiv_id":"2501.08603","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":1,"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) · 2 unverified","sample_list":"/paper/monte-carlo-tree-search-for-comprehensive#ran","syntology_url":"https://syntology.ai/paper/2501.08603","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.08603"}},"official":{"repos":["zz1358m/mcts-ahd-master"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/whispa-semantically-and-psychologically","slug":"whispa-semantically-and-psychologically","title":"WhiSPA: Semantically and Psychologically Aligned Whisper with Self-Supervised Contrastive and Student-Teacher Learning","date":"2025-01-15","arxiv_id":"2501.16344","repositories_listed":1,"syntology":null},{"url":"/paper/3ur-llm-an-end-to-end-multimodal-large","slug":"3ur-llm-an-end-to-end-multimodal-large","title":"3UR-LLM: An End-to-End Multimodal Large Language Model for 3D Scene Understanding","date":"2025-01-14","arxiv_id":"2501.07819","repositories_listed":1,"syntology":null},{"url":"/paper/gandalf-the-red-adaptive-security-for-llms","slug":"gandalf-the-red-adaptive-security-for-llms","title":"Gandalf the Red: Adaptive Security for LLMs","date":"2025-01-14","arxiv_id":"2501.07927","repositories_listed":1,"syntology":null},{"url":"/paper/in-situ-graph-reasoning-and-knowledge","slug":"in-situ-graph-reasoning-and-knowledge","title":"In-situ graph reasoning and knowledge expansion using Graph-PReFLexOR","date":"2025-01-14","arxiv_id":"2501.08120","repositories_listed":1,"syntology":null}],"record_sha256":"6f2b46477bfed8466f769431c9b9a4a40fe2da0a4b7baf83285fae0b6ddfec05","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}