{"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/15","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":15,"pages_in_order":177,"rows_per_page":100,"rows":[1401,1500],"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/14","next":"/task/language-modelling/papers/16","papers":[{"url":"/paper/worldpm-scaling-human-preference-modeling","slug":"worldpm-scaling-human-preference-modeling","title":"WorldPM: Scaling Human Preference Modeling","date":"2025-05-15","arxiv_id":"2505.10527","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-models-are-more-persuasive","slug":"large-language-models-are-more-persuasive","title":"Large Language Models Are More Persuasive Than Incentivized Human Persuaders","date":"2025-05-14","arxiv_id":"2505.09662","repositories_listed":1,"syntology":null},{"url":"/paper/layered-unlearning-for-adversarial-relearning","slug":"layered-unlearning-for-adversarial-relearning","title":"Layered Unlearning for Adversarial Relearning","date":"2025-05-14","arxiv_id":"2505.09500","repositories_listed":1,"syntology":null},{"url":"/paper/salm-a-multi-agent-framework-for-language","slug":"salm-a-multi-agent-framework-for-language","title":"SALM: A Multi-Agent Framework for Language Model-Driven Social Network Simulation","date":"2025-05-14","arxiv_id":"2505.09081","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-multi-modal-large-language-model-v","slug":"zero-shot-multi-modal-large-language-model-v","title":"Zero-Shot Multi-modal Large Language Model v.s. Supervised Deep Learning: A Comparative Study on CT-Based Intracranial Hemorrhage Subtyping","date":"2025-05-14","arxiv_id":"2505.09252","repositories_listed":1,"syntology":null},{"url":"/paper/behind-maya-building-a-multilingual-vision","slug":"behind-maya-building-a-multilingual-vision","title":"Behind Maya: Building a Multilingual Vision Language Model","date":"2025-05-13","arxiv_id":"2505.08910","repositories_listed":1,"syntology":null},{"url":"/paper/celltypeagent-trustworthy-cell-type","slug":"celltypeagent-trustworthy-cell-type","title":"CellTypeAgent: Trustworthy cell type annotation with Large Language Models","date":"2025-05-13","arxiv_id":"2505.08844","repositories_listed":1,"syntology":null},{"url":"/paper/extending-large-vision-language-model-for","slug":"extending-large-vision-language-model-for","title":"Extending Large Vision-Language Model for Diverse Interactive Tasks in Autonomous Driving","date":"2025-05-13","arxiv_id":"2505.08725","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-model-psychometrics-a","slug":"large-language-model-psychometrics-a","title":"Large Language Model Psychometrics: A Systematic Review of Evaluation, Validation, and Enhancement","date":"2025-05-13","arxiv_id":"2505.08245","repositories_listed":1,"syntology":null},{"url":"/paper/dynamicrag-leveraging-outputs-of-large","slug":"dynamicrag-leveraging-outputs-of-large","title":"DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generation","date":"2025-05-12","arxiv_id":"2505.07233","repositories_listed":1,"syntology":null},{"url":"/paper/kalman-filter-enhanced-grpo-for-reinforcement","slug":"kalman-filter-enhanced-grpo-for-reinforcement","title":"Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning","date":"2025-05-12","arxiv_id":"2505.07527","repositories_listed":1,"syntology":null},{"url":"/paper/mimo-unlocking-the-reasoning-potential-of","slug":"mimo-unlocking-the-reasoning-potential-of","title":"MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining","date":"2025-05-12","arxiv_id":"2505.07608","repositories_listed":1,"syntology":null},{"url":"/paper/symbolic-regression-with-multimodal-large","slug":"symbolic-regression-with-multimodal-large","title":"Symbolic Regression with Multimodal Large Language Models and Kolmogorov Arnold Networks","date":"2025-05-12","arxiv_id":"2505.07956","repositories_listed":1,"syntology":null},{"url":"/paper/guidedquant-large-language-model-quantization","slug":"guidedquant-large-language-model-quantization","title":"GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance","date":"2025-05-11","arxiv_id":"2505.07004","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/guidedquant-large-language-model-quantization#ran","syntology_url":"https://syntology.ai/paper/2505.07004","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.07004"}},"official":{"repos":["snu-mllab/guidedquant"],"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/impact-of-smiles-notational-inconsistencies","slug":"impact-of-smiles-notational-inconsistencies","title":"Impact of SMILES Notational Inconsistencies on Chemical Language Model Performance","date":"2025-05-11","arxiv_id":"2505.07139","repositories_listed":1,"syntology":null},{"url":"/paper/web-page-classification-using-llms-for","slug":"web-page-classification-using-llms-for","title":"Web Page Classification using LLMs for Crawling Support","date":"2025-05-11","arxiv_id":"2505.06972","repositories_listed":1,"syntology":null},{"url":"/paper/mm-skin-enhancing-dermatology-vision-language","slug":"mm-skin-enhancing-dermatology-vision-language","title":"MM-Skin: Enhancing Dermatology Vision-Language Model with an Image-Text Dataset Derived from Textbooks","date":"2025-05-09","arxiv_id":"2505.06152","repositories_listed":1,"syntology":null},{"url":"/paper/summarisation-of-german-judgments-in","slug":"summarisation-of-german-judgments-in","title":"Summarisation of German Judgments in conjunction with a Class-based Evaluation","date":"2025-05-09","arxiv_id":"2505.05947","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-stragglers-in-large-model","slug":"understanding-stragglers-in-large-model","title":"Understanding Stragglers in Large Model Training Using What-if Analysis","date":"2025-05-09","arxiv_id":"2505.05713","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-large-language-models-with-faster","slug":"enhancing-large-language-models-with-faster","title":"Enhancing Large Language Models with Faster Code Preprocessing for Vulnerability Detection","date":"2025-05-08","arxiv_id":"2505.05600","repositories_listed":1,"syntology":null},{"url":"/paper/on-device-llm-for-context-aware-wi-fi-roaming","slug":"on-device-llm-for-context-aware-wi-fi-roaming","title":"On-Device LLM for Context-Aware Wi-Fi Roaming","date":"2025-05-07","arxiv_id":"2505.04174","repositories_listed":1,"syntology":null},{"url":"/paper/vita-audio-fast-interleaved-cross-modal-token","slug":"vita-audio-fast-interleaved-cross-modal-token","title":"VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model","date":"2025-05-06","arxiv_id":"2505.03739","repositories_listed":1,"syntology":null},{"url":"/paper/creopep-a-universal-deep-learning-framework","slug":"creopep-a-universal-deep-learning-framework","title":"CreoPep: A Universal Deep Learning Framework for Target-Specific Peptide Design and Optimization","date":"2025-05-05","arxiv_id":"2505.02887","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-protein-language-model-embeddings","slug":"leveraging-protein-language-model-embeddings","title":"Leveraging Protein Language Model Embeddings for Catalytic Turnover Prediction of Adenylate Kinase Orthologs in a Low-Data Regime","date":"2025-05-05","arxiv_id":"2505.03066","repositories_listed":1,"syntology":null},{"url":"/paper/teda-boosting-vision-lanuage-models-for-zero","slug":"teda-boosting-vision-lanuage-models-for-zero","title":"TeDA: Boosting Vision-Lanuage Models for Zero-Shot 3D Object Retrieval via Testing-time Distribution Alignment","date":"2025-05-05","arxiv_id":"2505.02325","repositories_listed":1,"syntology":null},{"url":"/paper/dnazen-enhanced-gene-sequence-representations","slug":"dnazen-enhanced-gene-sequence-representations","title":"DNAZEN: Enhanced Gene Sequence Representations via Mixed Granularities of Coding Units","date":"2025-05-04","arxiv_id":"2505.02206","repositories_listed":1,"syntology":null},{"url":"/paper/leceval-an-automated-metric-for-multimodal","slug":"leceval-an-automated-metric-for-multimodal","title":"LecEval: An Automated Metric for Multimodal Knowledge Acquisition in Multimedia Learning","date":"2025-05-04","arxiv_id":"2505.02078","repositories_listed":1,"syntology":null},{"url":"/paper/memengine-a-unified-and-modular-library-for","slug":"memengine-a-unified-and-modular-library-for","title":"MemEngine: A Unified and Modular Library for Developing Advanced Memory of LLM-based Agents","date":"2025-05-04","arxiv_id":"2505.02099","repositories_listed":1,"syntology":null},{"url":"/paper/intra-layer-recurrence-in-transformers-for","slug":"intra-layer-recurrence-in-transformers-for","title":"Intra-Layer Recurrence in Transformers for Language Modeling","date":"2025-05-03","arxiv_id":"2505.01855","repositories_listed":1,"syntology":null},{"url":"/paper/nesterov-method-for-asynchronous-pipeline","slug":"nesterov-method-for-asynchronous-pipeline","title":"Nesterov Method for Asynchronous Pipeline Parallel Optimization","date":"2025-05-02","arxiv_id":"2505.01099","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-on-large-language-model-based-human","slug":"a-survey-on-large-language-model-based-human","title":"A Survey on Large Language Model based Human-Agent Systems","date":"2025-05-01","arxiv_id":"2505.00753","repositories_listed":1,"syntology":null},{"url":"/paper/adcare-vlm-leveraging-large-vision-language","slug":"adcare-vlm-leveraging-large-vision-language","title":"AdCare-VLM: Leveraging Large Vision Language Model (LVLM) to Monitor Long-Term Medication Adherence and Care","date":"2025-05-01","arxiv_id":"2505.00275","repositories_listed":1,"syntology":{"n":10,"n_ran":3,"n_constructed":1,"n_ran_checked":1,"n_instrument":2,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/adcare-vlm-leveraging-large-vision-language#ran","syntology_url":"https://syntology.ai/paper/2505.00275","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.00275"}},"official":{"repos":["asad14053/AdCare-VLM"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/optimizing-deep-neural-networks-using-safety","slug":"optimizing-deep-neural-networks-using-safety","title":"Optimizing Deep Neural Networks using Safety-Guided Self Compression","date":"2025-05-01","arxiv_id":"2505.00350","repositories_listed":1,"syntology":null},{"url":"/paper/visual-test-time-scaling-for-gui-agent","slug":"visual-test-time-scaling-for-gui-agent","title":"Visual Test-time Scaling for GUI Agent Grounding","date":"2025-05-01","arxiv_id":"2505.00684","repositories_listed":1,"syntology":null},{"url":"/paper/mf-llm-simulating-collective-decision","slug":"mf-llm-simulating-collective-decision","title":"MF-LLM: Simulating Population Decision Dynamics via a Mean-Field Large Language Model Framework","date":"2025-04-30","arxiv_id":"2504.21582","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mf-llm-simulating-collective-decision#ran","syntology_url":"https://syntology.ai/paper/2504.21582","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.21582"}},"official":{"repos":["Miracle1207/Mean-Field-LLM"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/rwkv-x-a-linear-complexity-hybrid-language","slug":"rwkv-x-a-linear-complexity-hybrid-language","title":"RWKV-X: A Linear Complexity Hybrid Language Model","date":"2025-04-30","arxiv_id":"2504.21463","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"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) · 4 unverified","sample_list":"/paper/rwkv-x-a-linear-complexity-hybrid-language#ran","syntology_url":"https://syntology.ai/paper/2504.21463","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.21463"}},"official":{"repos":["howard-hou/rwkv-x"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/reviving-any-subset-autoregressive-models","slug":"reviving-any-subset-autoregressive-models","title":"Reviving Any-Subset Autoregressive Models with Principled Parallel Sampling and Speculative Decoding","date":"2025-04-29","arxiv_id":"2504.20456","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/reviving-any-subset-autoregressive-models#ran","syntology_url":"https://syntology.ai/paper/2504.20456","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.20456"}},"official":{"repos":["gabeguo/any-order-speculative-decoding"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/turing-machine-evaluation-for-large-language","slug":"turing-machine-evaluation-for-large-language","title":"Computational Reasoning of Large Language Models","date":"2025-04-29","arxiv_id":"2504.20771","repositories_listed":1,"syntology":null},{"url":"/paper/unidetox-universal-detoxification-of-large","slug":"unidetox-universal-detoxification-of-large","title":"UniDetox: Universal Detoxification of Large Language Models via Dataset Distillation","date":"2025-04-29","arxiv_id":"2504.20500","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/unidetox-universal-detoxification-of-large#ran","syntology_url":"https://syntology.ai/paper/2504.20500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.20500"}},"official":{"repos":["EminLU/UniDetox"],"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/codebc-a-more-secure-large-language-model-for","slug":"codebc-a-more-secure-large-language-model-for","title":"CodeBC: A More Secure Large Language Model for Smart Contract Code Generation in Blockchain","date":"2025-04-28","arxiv_id":"2504.21043","repositories_listed":1,"syntology":null},{"url":"/paper/phenoassistant-a-conversational-multi-agent","slug":"phenoassistant-a-conversational-multi-agent","title":"PhenoAssistant: A Conversational Multi-Agent AI System for Automated Plant Phenotyping","date":"2025-04-28","arxiv_id":"2504.19818","repositories_listed":1,"syntology":null},{"url":"/paper/towards-practical-second-order-optimizers-in","slug":"towards-practical-second-order-optimizers-in","title":"Towards Practical Second-Order Optimizers in Deep Learning: Insights from Fisher Information Analysis","date":"2025-04-26","arxiv_id":"2504.20096","repositories_listed":1,"syntology":null},{"url":"/paper/leam-a-prompt-only-large-language-model","slug":"leam-a-prompt-only-large-language-model","title":"LEAM: A Prompt-only Large Language Model-enabled Antenna Modeling Method","date":"2025-04-25","arxiv_id":"2504.18271","repositories_listed":1,"syntology":null},{"url":"/paper/smartfinrag-interactive-modularized-financial","slug":"smartfinrag-interactive-modularized-financial","title":"SMARTFinRAG: Interactive Modularized Financial RAG Benchmark","date":"2025-04-25","arxiv_id":"2504.18024","repositories_listed":1,"syntology":null},{"url":"/paper/datetime-a-new-benchmark-to-measure-llm","slug":"datetime-a-new-benchmark-to-measure-llm","title":"DATETIME: A new benchmark to measure LLM translation and reasoning capabilities","date":"2025-04-22","arxiv_id":"2504.16155","repositories_listed":1,"syntology":null},{"url":"/paper/longmamba-enhancing-mamba-s-long-context","slug":"longmamba-enhancing-mamba-s-long-context","title":"LongMamba: Enhancing Mamba's Long Context Capabilities via Training-Free Receptive Field Enlargement","date":"2025-04-22","arxiv_id":"2504.16053","repositories_listed":1,"syntology":null},{"url":"/paper/what-s-the-difference-supporting-users-in","slug":"what-s-the-difference-supporting-users-in","title":"What's the Difference? Supporting Users in Identifying the Effects of Prompt and Model Changes Through Token Patterns","date":"2025-04-22","arxiv_id":"2504.15815","repositories_listed":1,"syntology":null},{"url":"/paper/easyedit2-an-easy-to-use-steering-framework","slug":"easyedit2-an-easy-to-use-steering-framework","title":"EasyEdit2: An Easy-to-use Steering Framework for Editing Large Language Models","date":"2025-04-21","arxiv_id":"2504.15133","repositories_listed":1,"syntology":null},{"url":"/paper/virology-capabilities-test-vct-a-multimodal","slug":"virology-capabilities-test-vct-a-multimodal","title":"Virology Capabilities Test (VCT): A Multimodal Virology Q&A Benchmark","date":"2025-04-21","arxiv_id":"2504.16137","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/virology-capabilities-test-vct-a-multimodal#ran","syntology_url":"https://syntology.ai/paper/2504.16137","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.16137"}},"official":null}},{"url":"/paper/walk-the-talk-measuring-the-faithfulness-of","slug":"walk-the-talk-measuring-the-faithfulness-of","title":"Walk the Talk? Measuring the Faithfulness of Large Language Model Explanations","date":"2025-04-19","arxiv_id":"2504.14150","repositories_listed":1,"syntology":null},{"url":"/paper/a-mean-teacher-algorithm-for-unlearning-of","slug":"a-mean-teacher-algorithm-for-unlearning-of","title":"A mean teacher algorithm for unlearning of language models","date":"2025-04-18","arxiv_id":"2504.13388","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-attribute-with-attention","slug":"learning-to-attribute-with-attention","title":"Learning to Attribute with Attention","date":"2025-04-18","arxiv_id":"2504.13752","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-to-attribute-with-attention#ran","syntology_url":"https://syntology.ai/paper/2504.13752","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.13752"}},"official":{"repos":["madrylab/at2"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-a-multi-agent-vision-language-system","slug":"towards-a-multi-agent-vision-language-system","title":"Towards a Multi-Agent Vision-Language System for Zero-Shot Novel Hazardous Object Detection for Autonomous Driving Safety","date":"2025-04-18","arxiv_id":"2504.13399","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/towards-a-multi-agent-vision-language-system#ran","syntology_url":"https://syntology.ai/paper/2504.13399","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.13399"}},"official":{"repos":["mi3labucm/coooler"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/zero-shot-industrial-anomaly-segmentation","slug":"zero-shot-industrial-anomaly-segmentation","title":"Zero-Shot Industrial Anomaly Segmentation with Image-Aware Prompt Generation","date":"2025-04-18","arxiv_id":"2504.13560","repositories_listed":1,"syntology":null},{"url":"/paper/chinese-vicuna-a-chinese-instruction","slug":"chinese-vicuna-a-chinese-instruction","title":"Chinese-Vicuna: A Chinese Instruction-following Llama-based Model","date":"2025-04-17","arxiv_id":"2504.12737","repositories_listed":1,"syntology":null},{"url":"/paper/energy-based-reward-models-for-robust","slug":"energy-based-reward-models-for-robust","title":"Energy-Based Reward Models for Robust Language Model Alignment","date":"2025-04-17","arxiv_id":"2504.13134","repositories_listed":1,"syntology":null},{"url":"/paper/perception-encoder-the-best-visual-embeddings","slug":"perception-encoder-the-best-visual-embeddings","title":"Perception Encoder: The best visual embeddings are not at the output of the network","date":"2025-04-17","arxiv_id":"2504.13181","repositories_listed":1,"syntology":{"n":18,"n_ran":14,"n_constructed":0,"n_ran_checked":9,"n_instrument":5,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":8,"n_pointer_only":2,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/perception-encoder-the-best-visual-embeddings#ran","syntology_url":"https://syntology.ai/paper/2504.13181","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.13181"}},"official":null}},{"url":"/paper/uncertainty-aware-trajectory-prediction-via","slug":"uncertainty-aware-trajectory-prediction-via","title":"Uncertainty-Aware Trajectory Prediction via Rule-Regularized Heteroscedastic Deep Classification","date":"2025-04-17","arxiv_id":"2504.13111","repositories_listed":1,"syntology":null},{"url":"/paper/internvl3-exploring-advanced-training-and","slug":"internvl3-exploring-advanced-training-and","title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","date":"2025-04-14","arxiv_id":"2504.10479","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/internvl3-exploring-advanced-training-and#ran","syntology_url":"https://syntology.ai/paper/2504.10479","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.10479"}},"official":{"repos":["opengvlab/internvl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/realharm-a-collection-of-real-world-language","slug":"realharm-a-collection-of-real-world-language","title":"RealHarm: A Collection of Real-World Language Model Application Failures","date":"2025-04-14","arxiv_id":"2504.10277","repositories_listed":1,"syntology":null},{"url":"/paper/silvar-med-a-speech-driven-visual-language","slug":"silvar-med-a-speech-driven-visual-language","title":"SilVar-Med: A Speech-Driven Visual Language Model for Explainable Abnormality Detection in Medical Imaging","date":"2025-04-14","arxiv_id":"2504.10642","repositories_listed":1,"syntology":null},{"url":"/paper/the-scalability-of-simplicity-empirical","slug":"the-scalability-of-simplicity-empirical","title":"The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer","date":"2025-04-14","arxiv_id":"2504.10462","repositories_listed":1,"syntology":{"n":9,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 2 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) · 7 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/the-scalability-of-simplicity-empirical#ran","syntology_url":"https://syntology.ai/paper/2504.10462","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.10462"}},"official":{"repos":["bytedance/sail"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/clinicalgpt-r1-pushing-reasoning-capability","slug":"clinicalgpt-r1-pushing-reasoning-capability","title":"ClinicalGPT-R1: Pushing reasoning capability of generalist disease diagnosis with large language model","date":"2025-04-13","arxiv_id":"2504.09421","repositories_listed":1,"syntology":null},{"url":"/paper/fine-tuning-an-large-language-model-for","slug":"fine-tuning-an-large-language-model-for","title":"Fine-tuning a Large Language Model for Automating Computational Fluid Dynamics Simulations","date":"2025-04-13","arxiv_id":"2504.09602","repositories_listed":1,"syntology":null},{"url":"/paper/segearth-r1-geospatial-pixel-reasoning-via","slug":"segearth-r1-geospatial-pixel-reasoning-via","title":"SegEarth-R1: Geospatial Pixel Reasoning via Large Language Model","date":"2025-04-13","arxiv_id":"2504.09644","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":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) · 2 unverified","sample_list":"/paper/segearth-r1-geospatial-pixel-reasoning-via#ran","syntology_url":"https://syntology.ai/paper/2504.09644","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.09644"}},"official":{"repos":["earth-insights/segearth-r1"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/vision-language-model-for-object-detection","slug":"vision-language-model-for-object-detection","title":"Vision-Language Model for Object Detection and Segmentation: A Review and Evaluation","date":"2025-04-13","arxiv_id":"2504.09480","repositories_listed":1,"syntology":null},{"url":"/paper/2504-09184","slug":"2504-09184","title":"Parameterized Synthetic Text Generation with SimpleStories","date":"2025-04-12","arxiv_id":"2504.09184","repositories_listed":1,"syntology":null},{"url":"/paper/medrep-medical-concept-representation-for","slug":"medrep-medical-concept-representation-for","title":"MedRep: Medical Concept Representation for General Electronic Health Record Foundation Models","date":"2025-04-11","arxiv_id":"2504.08329","repositories_listed":1,"syntology":null},{"url":"/paper/pact-pruning-and-clustering-based-token","slug":"pact-pruning-and-clustering-based-token","title":"PACT: Pruning and Clustering-Based Token Reduction for Faster Visual Language Models","date":"2025-04-11","arxiv_id":"2504.08966","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/pact-pruning-and-clustering-based-token#ran","syntology_url":"https://syntology.ai/paper/2504.08966","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.08966"}},"official":{"repos":["orailix/pact"],"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/glus-global-local-reasoning-unified-into-a","slug":"glus-global-local-reasoning-unified-into-a","title":"GLUS: Global-Local Reasoning Unified into A Single Large Language Model for Video Segmentation","date":"2025-04-10","arxiv_id":"2504.07962","repositories_listed":1,"syntology":{"n":12,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":12,"phrase":"3 ran (of which 3 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) · 9 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/glus-global-local-reasoning-unified-into-a#ran","syntology_url":"https://syntology.ai/paper/2504.07962","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.07962"}},"official":null}},{"url":"/paper/lauratse-target-speaker-extraction-using-auto","slug":"lauratse-target-speaker-extraction-using-auto","title":"LauraTSE: Target Speaker Extraction using Auto-Regressive Decoder-Only Language Models","date":"2025-04-10","arxiv_id":"2504.07402","repositories_listed":1,"syntology":null},{"url":"/paper/vlm-r1-a-stable-and-generalizable-r1-style","slug":"vlm-r1-a-stable-and-generalizable-r1-style","title":"VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model","date":"2025-04-10","arxiv_id":"2504.07615","repositories_listed":1,"syntology":null},{"url":"/paper/payador-a-minimalist-approach-to-grounding","slug":"payador-a-minimalist-approach-to-grounding","title":"PAYADOR: A Minimalist Approach to Grounding Language Models on Structured Data for Interactive Storytelling and Role-playing Games","date":"2025-04-09","arxiv_id":"2504.07304","repositories_listed":1,"syntology":null},{"url":"/paper/ruopinionne-2024-extraction-of-opinion-tuples","slug":"ruopinionne-2024-extraction-of-opinion-tuples","title":"RuOpinionNE-2024: Extraction of Opinion Tuples from Russian News Texts","date":"2025-04-09","arxiv_id":"2504.06947","repositories_listed":1,"syntology":null},{"url":"/paper/skywork-r1v-pioneering-multimodal-reasoning","slug":"skywork-r1v-pioneering-multimodal-reasoning","title":"Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thought","date":"2025-04-08","arxiv_id":"2504.05599","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/skywork-r1v-pioneering-multimodal-reasoning#ran","syntology_url":"https://syntology.ai/paper/2504.05599","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.05599"}},"official":null}},{"url":"/paper/collab-rag-boosting-retrieval-augmented","slug":"collab-rag-boosting-retrieval-augmented","title":"Collab-RAG: Boosting Retrieval-Augmented Generation for Complex Question Answering via White-Box and Black-Box LLM Collaboration","date":"2025-04-07","arxiv_id":"2504.04915","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/collab-rag-boosting-retrieval-augmented#ran","syntology_url":"https://syntology.ai/paper/2504.04915","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.04915"}},"official":{"repos":["ritaranx/collab-rag"],"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/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/co-bench-benchmarking-language-model-agents","slug":"co-bench-benchmarking-language-model-agents","title":"CO-Bench: Benchmarking Language Model Agents in Algorithm Search for Combinatorial Optimization","date":"2025-04-06","arxiv_id":"2504.04310","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/co-bench-benchmarking-language-model-agents#ran","syntology_url":"https://syntology.ai/paper/2504.04310","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.04310"}},"official":{"repos":["sunnweiwei/co-bench"],"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/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/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/msl-not-all-tokens-are-what-you-need-for","slug":"msl-not-all-tokens-are-what-you-need-for","title":"MSL: Not All Tokens Are What You Need for Tuning LLM as a Recommender","date":"2025-04-05","arxiv_id":"2504.04178","repositories_listed":1,"syntology":null},{"url":"/paper/beyond-the-next-token-towards-prompt-robust","slug":"beyond-the-next-token-towards-prompt-robust","title":"Beyond the Next Token: Towards Prompt-Robust Zero-Shot Classification via Efficient Multi-Token Prediction","date":"2025-04-04","arxiv_id":"2504.03159","repositories_listed":1,"syntology":null},{"url":"/paper/distillation-and-refinement-of-reasoning-in","slug":"distillation-and-refinement-of-reasoning-in","title":"Distillation and Refinement of Reasoning in Small Language Models for Document Re-ranking","date":"2025-04-04","arxiv_id":"2504.03947","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/language-models-are-implicitly-continuous","slug":"language-models-are-implicitly-continuous","title":"Language Models Are Implicitly Continuous","date":"2025-04-04","arxiv_id":"2504.03933","repositories_listed":1,"syntology":{"n":16,"n_ran":12,"n_constructed":0,"n_ran_checked":12,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":16,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/language-models-are-implicitly-continuous#ran","syntology_url":"https://syntology.ai/paper/2504.03933","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.03933"}},"official":{"repos":["samuelemarro/continuous-llm-experiments"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/noise-augmented-fine-tuning-for-mitigating","slug":"noise-augmented-fine-tuning-for-mitigating","title":"Noise Augmented Fine Tuning for Mitigating Hallucinations in Large Language Models","date":"2025-04-04","arxiv_id":"2504.03302","repositories_listed":1,"syntology":null},{"url":"/paper/sarlang-1m-a-benchmark-for-vision-language","slug":"sarlang-1m-a-benchmark-for-vision-language","title":"SARLANG-1M: A Benchmark for Vision-Language Modeling in SAR Image Understanding","date":"2025-04-04","arxiv_id":"2504.03254","repositories_listed":1,"syntology":null},{"url":"/paper/ipa-childes-g2p-feature-rich-resources-for","slug":"ipa-childes-g2p-feature-rich-resources-for","title":"IPA-CHILDES & G2P+: Feature-Rich Resources for Cross-Lingual Phonology and Phonemic Language Modeling","date":"2025-04-03","arxiv_id":"2504.03036","repositories_listed":1,"syntology":null},{"url":"/paper/jaildam-jailbreak-detection-with-adaptive","slug":"jaildam-jailbreak-detection-with-adaptive","title":"JailDAM: Jailbreak Detection with Adaptive Memory for Vision-Language Model","date":"2025-04-03","arxiv_id":"2504.03770","repositories_listed":1,"syntology":null},{"url":"/paper/low-rank-factorizations-are-indirect","slug":"low-rank-factorizations-are-indirect","title":"Low Rank Factorizations are Indirect Encodings for Deep Neuroevolution","date":"2025-04-03","arxiv_id":"2504.03037","repositories_listed":1,"syntology":null},{"url":"/paper/mg-motionllm-a-unified-framework-for-motion","slug":"mg-motionllm-a-unified-framework-for-motion","title":"MG-MotionLLM: A Unified Framework for Motion Comprehension and Generation across Multiple Granularities","date":"2025-04-03","arxiv_id":"2504.02478","repositories_listed":1,"syntology":null},{"url":"/paper/scaling-video-language-models-to-10k-frames","slug":"scaling-video-language-models-to-10k-frames","title":"Scaling Video-Language Models to 10K Frames via Hierarchical Differential Distillation","date":"2025-04-03","arxiv_id":"2504.02438","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/scaling-video-language-models-to-10k-frames#ran","syntology_url":"https://syntology.ai/paper/2504.02438","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.02438"}},"official":{"repos":["steven-ccq/vilamp"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/sting-bee-towards-vision-language-model-for","slug":"sting-bee-towards-vision-language-model-for","title":"STING-BEE: Towards Vision-Language Model for Real-World X-ray Baggage Security Inspection","date":"2025-04-03","arxiv_id":"2504.02823","repositories_listed":1,"syntology":null},{"url":"/paper/investigating-and-scaling-up-code-switching","slug":"investigating-and-scaling-up-code-switching","title":"Investigating and Scaling up Code-Switching for Multilingual Language Model Pre-Training","date":"2025-04-02","arxiv_id":"2504.01801","repositories_listed":1,"syntology":null},{"url":"/paper/stpnet-scale-aware-text-prompt-network-for","slug":"stpnet-scale-aware-text-prompt-network-for","title":"STPNet: Scale-aware Text Prompt Network for Medical Image Segmentation","date":"2025-04-02","arxiv_id":"2504.01561","repositories_listed":1,"syntology":null},{"url":"/paper/tic-lm-a-web-scale-benchmark-for-time","slug":"tic-lm-a-web-scale-benchmark-for-time","title":"TiC-LM: A Web-Scale Benchmark for Time-Continual LLM Pretraining","date":"2025-04-02","arxiv_id":"2504.02107","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/crowdvlm-r1-expanding-r1-ability-to-vision","slug":"crowdvlm-r1-expanding-r1-ability-to-vision","title":"CrowdVLM-R1: Expanding R1 Ability to Vision Language Model for Crowd Counting using Fuzzy Group Relative Policy Reward","date":"2025-03-31","arxiv_id":"2504.03724","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/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}],"record_sha256":"de3489db522e121e7c2675b9b6eeab844da5020e396c5348769676a9898c304c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}