{"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-modeling/papers/77","list_of":"/task/language-modeling","task":"Language Modeling","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":77,"pages_in_order":142,"rows_per_page":100,"rows":[7601,7700],"of":14182,"counts":{"archive_papers_tagged":14182,"with_a_code_link":5620,"where_syntology_ran_a_sample":1894,"not_listed_spam_title":0,"listed":14182,"listed_where_code_ran":1894,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1580,"every_run_a_failure_of_syntologys_instrument":314,"listed_with_a_run_with_no_instrument_failure":1580,"listed_every_run_a_failure_of_syntologys_instrument":314,"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-modeling","prev":"/task/language-modeling/papers/76","next":"/task/language-modeling/papers/78","papers":[{"url":null,"slug":"exploring-forgetting-in-large-language-model","title":"Exploring Forgetting in Large Language Model Pre-Training","date":"2024-10-22","arxiv_id":"2410.17018","repositories_listed":0,"syntology":null},{"url":null,"slug":"geocode-gpt-a-large-language-model-for","title":"GeoCode-GPT: A Large Language Model for Geospatial Code Generation Tasks","date":"2024-10-22","arxiv_id":"2410.17031","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-pinterest-search-relevance-using","title":"Improving Pinterest Search Relevance Using Large Language Models","date":"2024-10-22","arxiv_id":"2410.17152","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-based-augmentation-for","title":"SaVe-TAG: Semantic-aware Vicinal Risk Minimization for Long-Tailed Text-Attributed Graphs","date":"2024-10-22","arxiv_id":"2410.16882","repositories_listed":0,"syntology":null},{"url":null,"slug":"magnetic-preference-optimization-achieving","title":"Magnetic Preference Optimization: Achieving Last-iterate Convergence for Language Model Alignment","date":"2024-10-22","arxiv_id":"2410.16714","repositories_listed":0,"syntology":null},{"url":null,"slug":"memdlm-de-novo-membrane-protein-design-with","title":"MeMDLM: De Novo Membrane Protein Design with Masked Discrete Diffusion Protein Language Models","date":"2024-10-22","arxiv_id":"2410.16735","repositories_listed":0,"syntology":null},{"url":null,"slug":"remote-timing-attacks-on-efficient-language","title":"Remote Timing Attacks on Efficient Language Model Inference","date":"2024-10-22","arxiv_id":"2410.17175","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-calibration-for-language-model","title":"Self-calibration for Language Model Quantization and Pruning","date":"2024-10-22","arxiv_id":"2410.17170","repositories_listed":0,"syntology":null},{"url":null,"slug":"are-language-model-logits-calibrated","title":"Are Language Model Logits Calibrated?","date":"2024-10-21","arxiv_id":"2410.16007","repositories_listed":0,"syntology":null},{"url":null,"slug":"compo-community-preferences-for-language","title":"ComPO: Community Preferences for Language Model Personalization","date":"2024-10-21","arxiv_id":"2410.16027","repositories_listed":0,"syntology":null},{"url":null,"slug":"contamination-report-for-multilingual","title":"Contamination Report for Multilingual Benchmarks","date":"2024-10-21","arxiv_id":"2410.16186","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-continual-fine-tuning-for-enhancing","title":"Exploring Continual Fine-Tuning for Enhancing Language Ability in Large Language Model","date":"2024-10-21","arxiv_id":"2410.16006","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalized-probabilistic-attention-mechanism","title":"Generalized Probabilistic Attention Mechanism in Transformers","date":"2024-10-21","arxiv_id":"2410.15578","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-models-are-symbolic-learners-in","title":"Language Models are Symbolic Learners in Arithmetic","date":"2024-10-21","arxiv_id":"2410.15580","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-body-language-models","title":"Large Body Language Models","date":"2024-10-21","arxiv_id":"2410.16533","repositories_listed":0,"syntology":null},{"url":null,"slug":"lscodec-low-bitrate-and-speaker-decoupled","title":"LSCodec: Low-Bitrate and Speaker-Decoupled Discrete Speech Codec","date":"2024-10-21","arxiv_id":"2410.15764","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-search-space-in-gboard-decoder","title":"Neural Search Space in Gboard Decoder","date":"2024-10-21","arxiv_id":"2410.15575","repositories_listed":0,"syntology":null},{"url":null,"slug":"no-more-hard-prompts-softsrv-prompting-for","title":"No more hard prompts: SoftSRV prompting for synthetic data generation","date":"2024-10-21","arxiv_id":"2410.16534","repositories_listed":0,"syntology":null},{"url":null,"slug":"opportunities-and-challenges-of-generative-ai","title":"Opportunities and Challenges of Generative-AI in Finance","date":"2024-10-21","arxiv_id":"2410.15653","repositories_listed":0,"syntology":null},{"url":null,"slug":"subword-embedding-from-bytes-gains-privacy","title":"Subword Embedding from Bytes Gains Privacy without Sacrificing Accuracy and Complexity","date":"2024-10-21","arxiv_id":"2410.16410","repositories_listed":0,"syntology":null},{"url":null,"slug":"tokenization-as-finite-state-transduction","title":"Tokenization as Finite-State Transduction","date":"2024-10-21","arxiv_id":"2410.15696","repositories_listed":0,"syntology":null},{"url":null,"slug":"xgen-mm-vid-blip-3-video-you-only-need-32","title":"xGen-MM-Vid (BLIP-3-Video): You Only Need 32 Tokens to Represent a Video Even in VLMs","date":"2024-10-21","arxiv_id":"2410.16267","repositories_listed":0,"syntology":null},{"url":null,"slug":"eva-an-embodied-world-model-for-future-video","title":"EVA: An Embodied World Model for Future Video Anticipation","date":"2024-10-20","arxiv_id":"2410.15461","repositories_listed":0,"syntology":null},{"url":null,"slug":"hallucination-detox-sensitive-neuron-dropout","title":"Hallucination Detox: Sensitivity Dropout (SenD) for Large Language Model Training","date":"2024-10-20","arxiv_id":"2410.15460","repositories_listed":0,"syntology":null},{"url":null,"slug":"mmcs-a-multimodal-medical-diagnosis-system","title":"MMDS: A Multimodal Medical Diagnosis System Integrating Image Analysis and Knowledge-based Departmental Consultation","date":"2024-10-20","arxiv_id":"2410.15403","repositories_listed":0,"syntology":null},{"url":null,"slug":"tagexplainer-narrating-graph-explanations-for","title":"TAGExplainer: Narrating Graph Explanations for Text-Attributed Graph Learning Models","date":"2024-10-20","arxiv_id":"2410.15268","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-prompt-engineering-approach-and-a-knowledge","title":"A Prompt Engineering Approach and a Knowledge Graph based Framework for Tackling Legal Implications of Large Language Model Answers","date":"2024-10-19","arxiv_id":"2410.15064","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-prompt-refinement-based-large-language","title":"A Prompt Refinement-based Large Language Model for Metro Passenger Flow Forecasting under Delay Conditions","date":"2024-10-19","arxiv_id":"2410.15111","repositories_listed":0,"syntology":null},{"url":null,"slug":"autofluka-a-large-language-model-based","title":"AutoFLUKA: A Large Language Model Based Framework for Automating Monte Carlo Simulations in FLUKA","date":"2024-10-19","arxiv_id":"2410.15222","repositories_listed":0,"syntology":null},{"url":null,"slug":"autofpdesigner-automated-flight-procedure","title":"AutoFPDesigner: Automated Flight Procedure Design Based on Multi-Agent Large Language Model","date":"2024-10-19","arxiv_id":"2410.14989","repositories_listed":0,"syntology":null},{"url":null,"slug":"chronofact-timeline-based-temporal-fact","title":"ChronoFact: Timeline-based Temporal Fact Verification","date":"2024-10-19","arxiv_id":"2410.14964","repositories_listed":0,"syntology":null},{"url":null,"slug":"cliptortionist-zero-shot-text-driven","title":"CLIPtortionist: Zero-shot Text-driven Deformation for Manufactured 3D Shapes","date":"2024-10-19","arxiv_id":"2410.15199","repositories_listed":0,"syntology":null},{"url":null,"slug":"coarse-to-fine-highlighting-reducing","title":"Coarse-to-Fine Highlighting: Reducing Knowledge Hallucination in Large Language Models","date":"2024-10-19","arxiv_id":"2410.15116","repositories_listed":0,"syntology":null},{"url":null,"slug":"langgfm-a-large-language-model-alone-can-be-a","title":"LangGFM: A Large Language Model Alone Can be a Powerful Graph Foundation Model","date":"2024-10-19","arxiv_id":"2410.14961","repositories_listed":0,"syntology":null},{"url":null,"slug":"llava-ultra-large-chinese-language-and-vision","title":"LLaVA-Ultra: Large Chinese Language and Vision Assistant for Ultrasound","date":"2024-10-19","arxiv_id":"2410.15074","repositories_listed":0,"syntology":null},{"url":null,"slug":"morphagent-empowering-agents-through-self","title":"MorphAgent: Empowering Agents through Self-Evolving Profiles and Decentralized Collaboration","date":"2024-10-19","arxiv_id":"2410.15048","repositories_listed":0,"syntology":null},{"url":null,"slug":"transit-pulse-utilizing-social-media-as-a","title":"Transit Pulse: Utilizing Social Media as a Source for Customer Feedback and Information Extraction with Large Language Model","date":"2024-10-19","arxiv_id":"2410.15016","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-large-language-model-driven-reward-design","title":"A Large Language Model-Driven Reward Design Framework via Dynamic Feedback for Reinforcement Learning","date":"2024-10-18","arxiv_id":"2410.14660","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-genre-aware-article-scoring-and","title":"Automated Genre-Aware Article Scoring and Feedback Using Large Language Models","date":"2024-10-18","arxiv_id":"2410.14165","repositories_listed":0,"syntology":null},{"url":null,"slug":"celi-controller-embedded-language-model","title":"CELI: Controller-Embedded Language Model Interactions","date":"2024-10-18","arxiv_id":"2410.14627","repositories_listed":0,"syntology":null},{"url":null,"slug":"dflow-diverse-dialogue-flow-simulation-with","title":"DFlow: Diverse Dialogue Flow Simulation with Large Language Models","date":"2024-10-18","arxiv_id":"2410.14853","repositories_listed":0,"syntology":null},{"url":null,"slug":"e3d-gpt-enhanced-3d-visual-foundation-for","title":"E3D-GPT: Enhanced 3D Visual Foundation for Medical Vision-Language Model","date":"2024-10-18","arxiv_id":"2410.14200","repositories_listed":0,"syntology":null},{"url":null,"slug":"electrocardiogram-language-model-for-few-shot","title":"Electrocardiogram-Language Model for Few-Shot Question Answering with Meta Learning","date":"2024-10-18","arxiv_id":"2410.14464","repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-joint-multimodal-entity-relation","title":"Few-Shot Joint Multimodal Entity-Relation Extraction via Knowledge-Enhanced Cross-modal Prompt Model","date":"2024-10-18","arxiv_id":"2410.14225","repositories_listed":0,"syntology":null},{"url":null,"slug":"good-parenting-is-all-you-need-multi-agentic","title":"Good Parenting is all you need -- Multi-agentic LLM Hallucination Mitigation","date":"2024-10-18","arxiv_id":"2410.14262","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-verification-and-refinement-of-language","title":"Joint Verification and Refinement of Language Models for Safety-Constrained Planning","date":"2024-10-18","arxiv_id":"2410.14865","repositories_listed":0,"syntology":null},{"url":null,"slug":"ptr-a-pre-trained-language-model-for","title":"PTR: A Pre-trained Language Model for Trajectory Recovery","date":"2024-10-18","arxiv_id":"2410.14281","repositories_listed":0,"syntology":null},{"url":null,"slug":"rationale-behind-essay-scores-enhancing-s-llm","title":"Rationale Behind Essay Scores: Enhancing S-LLM's Multi-Trait Essay Scoring with Rationale Generated by LLMs","date":"2024-10-18","arxiv_id":"2410.14202","repositories_listed":0,"syntology":null},{"url":null,"slug":"reasoning-memorization-and-fine-tuning","title":"Reasoning, Memorization, and Fine-Tuning Language Models for Non-Cooperative Games","date":"2024-10-18","arxiv_id":"2410.14890","repositories_listed":0,"syntology":null},{"url":null,"slug":"sudolm-learning-access-control-of-parametric","title":"SudoLM: Learning Access Control of Parametric Knowledge with Authorization Alignment","date":"2024-10-18","arxiv_id":"2410.14676","repositories_listed":0,"syntology":null},{"url":null,"slug":"accounting-for-sycophancy-in-language-model","title":"Accounting for Sycophancy in Language Model Uncertainty Estimation","date":"2024-10-17","arxiv_id":"2410.14746","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-large-language-model-attribution","title":"Advancing Large Language Model Attribution through Self-Improving","date":"2024-10-17","arxiv_id":"2410.13298","repositories_listed":0,"syntology":null},{"url":null,"slug":"breaking-chains-unraveling-the-links-in-multi","title":"Breaking Chains: Unraveling the Links in Multi-Hop Knowledge Unlearning","date":"2024-10-17","arxiv_id":"2410.13274","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparing-the-utility-preference-and","title":"Comparing the Utility, Preference, and Performance of Course Material Search Functionality and Retrieval-Augmented Generation Large Language Model (RAG-LLM) AI Chatbots in Information-Seeking Tasks","date":"2024-10-17","arxiv_id":"2410.13326","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-sentiment-analysis-with","title":"Collaborative AI in Sentiment Analysis: System Architecture, Data Prediction and Deployment Strategies","date":"2024-10-17","arxiv_id":"2410.13247","repositories_listed":0,"syntology":null},{"url":"/paper/improving-multi-modal-large-language-model","slug":"improving-multi-modal-large-language-model","title":"Improving Multi-modal Large Language Model through Boosting Vision Capabilities","date":"2024-10-17","arxiv_id":"2410.13733","repositories_listed":0,"syntology":null},{"url":null,"slug":"instruction-driven-game-engine-a-poker-case","title":"Instruction-Driven Game Engine: A Poker Case Study","date":"2024-10-17","arxiv_id":"2410.13441","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-agent-honeypot-monitoring-ai-hacking","title":"LLM Agent Honeypot: Monitoring AI Hacking Agents in the Wild","date":"2024-10-17","arxiv_id":"2410.13919","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-biases-to-embrace-diversity-a","title":"Mitigating Biases to Embrace Diversity: A Comprehensive Annotation Benchmark for Toxic Language","date":"2024-10-17","arxiv_id":"2410.13313","repositories_listed":0,"syntology":null},{"url":null,"slug":"proof-flow-preliminary-study-on-generative","title":"Proof Flow: Preliminary Study on Generative Flow Network Language Model Tuning for Formal Reasoning","date":"2024-10-17","arxiv_id":"2410.13224","repositories_listed":0,"syntology":null},{"url":null,"slug":"retrieval-enhanced-named-entity-recognition","title":"Retrieval-Enhanced Named Entity Recognition","date":"2024-10-17","arxiv_id":"2410.13118","repositories_listed":0,"syntology":null},{"url":null,"slug":"slm-mod-small-language-models-surpass-llms-at","title":"SLM-Mod: Small Language Models Surpass LLMs at Content Moderation","date":"2024-10-17","arxiv_id":"2410.13155","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-guided-multi-property-molecular","title":"Text-Guided Multi-Property Molecular Optimization with a Diffusion Language Model","date":"2024-10-17","arxiv_id":"2410.13597","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-hybrid-intelligence-in-journalism","title":"Towards Hybrid Intelligence in Journalism: Findings and Lessons Learnt from a Collaborative Analysis of Greek Political Rhetoric by ChatGPT and Humans","date":"2024-10-17","arxiv_id":"2410.13400","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformer-guided-coevolution-improved-team","title":"Transformer Guided Coevolution: Improved Team Selection in Multiagent Adversarial Team Games","date":"2024-10-17","arxiv_id":"2410.13769","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarkcards-large-language-model-and-risk","title":"BenchmarkCards: Large Language Model and Risk Reporting","date":"2024-10-16","arxiv_id":"2410.12974","repositories_listed":0,"syntology":null},{"url":"/paper/developing-question-answering-models-in-low","slug":"developing-question-answering-models-in-low","title":"Developing Question-Answering Models in Low-Resource Languages: A Case Study on Turkish Medical Texts Using Transformer-Based Approaches","date":"2024-10-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-planner-training-for-language","title":"End-to-end Planner Training for Language Modeling","date":"2024-10-16","arxiv_id":"2410.12492","repositories_listed":0,"syntology":null},{"url":null,"slug":"explainable-moral-values-a-neuro-symbolic","title":"Explainable Moral Values: a neuro-symbolic approach to value classification","date":"2024-10-16","arxiv_id":"2410.12631","repositories_listed":0,"syntology":null},{"url":null,"slug":"helm-hierarchical-encoding-for-mrna-language","title":"HELM: Hierarchical Encoding for mRNA Language Modeling","date":"2024-10-16","arxiv_id":"2410.12459","repositories_listed":0,"syntology":null},{"url":null,"slug":"iter-ahmcl-alleviate-hallucination-for-large","title":"Iter-AHMCL: Alleviate Hallucination for Large Language Model via Iterative Model-level Contrastive Learning","date":"2024-10-16","arxiv_id":"2410.12130","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-driven-multi-agent","title":"Large Language Model-driven Multi-Agent Simulation for News Diffusion Under Different Network Structures","date":"2024-10-16","arxiv_id":"2410.13909","repositories_listed":0,"syntology":null},{"url":null,"slug":"mechanistic-unlearning-robust-knowledge","title":"Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization","date":"2024-10-16","arxiv_id":"2410.12949","repositories_listed":0,"syntology":null},{"url":null,"slug":"medaide-towards-an-omni-medical-aide-via","title":"MedAide: Towards an Omni Medical Aide via Specialized LLM-based Multi-Agent Collaboration","date":"2024-10-16","arxiv_id":"2410.12532","repositories_listed":0,"syntology":null},{"url":null,"slug":"negative-prompt-driven-alignment-for","title":"Negative-Prompt-driven Alignment for Generative Language Model","date":"2024-10-16","arxiv_id":"2410.12194","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-low-resource-language-model","title":"Optimizing Low-Resource Language Model Training: Comprehensive Analysis of Multi-Epoch, Multi-Lingual, and Two-Stage Approaches","date":"2024-10-16","arxiv_id":"2410.12325","repositories_listed":0,"syntology":null},{"url":null,"slug":"refine-on-scarce-data-retrieval-enhancement","title":"REFINE on Scarce Data: Retrieval Enhancement through Fine-Tuning via Model Fusion of Embedding Models","date":"2024-10-16","arxiv_id":"2410.12890","repositories_listed":0,"syntology":null},{"url":null,"slug":"retrieval-reasoning-large-language-model","title":"Retrieval-Reasoning Large Language Model-based Synthetic Clinical Trial Generation","date":"2024-10-16","arxiv_id":"2410.12476","repositories_listed":0,"syntology":null},{"url":null,"slug":"revisited-large-language-model-for-time","title":"Revisited Large Language Model for Time Series Analysis through Modality Alignment","date":"2024-10-16","arxiv_id":"2410.12326","repositories_listed":0,"syntology":null},{"url":null,"slug":"shapefilegpt-a-multi-agent-large-language","title":"ShapefileGPT: A Multi-Agent Large Language Model Framework for Automated Shapefile Processing","date":"2024-10-16","arxiv_id":"2410.12376","repositories_listed":0,"syntology":null},{"url":null,"slug":"styledistance-stronger-content-independent","title":"StyleDistance: Stronger Content-Independent Style Embeddings with Synthetic Parallel Examples","date":"2024-10-16","arxiv_id":"2410.12757","repositories_listed":0,"syntology":null},{"url":null,"slug":"table-llm-specialist-language-model","title":"Table-LLM-Specialist: Language Model Specialists for Tables using Iterative Generator-Validator Fine-tuning","date":"2024-10-16","arxiv_id":"2410.12164","repositories_listed":0,"syntology":null},{"url":null,"slug":"tracking-universal-features-through-fine","title":"Tracking Universal Features Through Fine-Tuning and Model Merging","date":"2024-10-16","arxiv_id":"2410.12391","repositories_listed":0,"syntology":null},{"url":null,"slug":"tuning-language-models-by-mixture-of-depths","title":"Tuning Language Models by Mixture-of-Depths Ensemble","date":"2024-10-16","arxiv_id":"2410.13077","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-low-shot-vision-language-model","title":"A Survey of Low-shot Vision-Language Model Adaptation via Representer Theorem","date":"2024-10-15","arxiv_id":"2410.11686","repositories_listed":0,"syntology":null},{"url":null,"slug":"emotioncaps-enhancing-audio-captioning","title":"EmotionCaps: Enhancing Audio Captioning Through Emotion-Augmented Data Generation","date":"2024-10-15","arxiv_id":"2410.12028","repositories_listed":0,"syntology":null},{"url":null,"slug":"largepig-your-large-language-model-is","title":"LargePiG: Your Large Language Model is Secretly a Pointer Generator","date":"2024-10-15","arxiv_id":"2410.11366","repositories_listed":0,"syntology":null},{"url":null,"slug":"light-weight-fault-tolerant-attention-for","title":"ATTNChecker: Highly-Optimized Fault Tolerant Attention for Large Language Model Training","date":"2024-10-15","arxiv_id":"2410.11720","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-frequency-bias-and-anisotropy-in","title":"Mitigating Frequency Bias and Anisotropy in Language Model Pre-Training with Syntactic Smoothing","date":"2024-10-15","arxiv_id":"2410.11462","repositories_listed":0,"syntology":null},{"url":null,"slug":"mochat-joints-grouped-spatio-temporal","title":"MoChat: Joints-Grouped Spatio-Temporal Grounding LLM for Multi-Turn Motion Comprehension and Description","date":"2024-10-15","arxiv_id":"2410.11404","repositories_listed":0,"syntology":null},{"url":null,"slug":"moe-pruner-pruning-mixture-of-experts-large","title":"MoE-Pruner: Pruning Mixture-of-Experts Large Language Model using the Hints from Its Router","date":"2024-10-15","arxiv_id":"2410.12013","repositories_listed":0,"syntology":null},{"url":null,"slug":"o-edit-orthogonal-subspace-editing-for","title":"O-Edit: Orthogonal Subspace Editing for Language Model Sequential Editing","date":"2024-10-15","arxiv_id":"2410.11469","repositories_listed":0,"syntology":null},{"url":null,"slug":"pavlm-advancing-point-cloud-based-affordance","title":"PAVLM: Advancing Point Cloud based Affordance Understanding Via Vision-Language Model","date":"2024-10-15","arxiv_id":"2410.11564","repositories_listed":0,"syntology":null},{"url":null,"slug":"retrieval-augmented-spelling-correction-for-e","title":"Retrieval Augmented Spelling Correction for E-Commerce Applications","date":"2024-10-15","arxiv_id":"2410.11655","repositories_listed":0,"syntology":null},{"url":null,"slug":"sabia-3-technical-report","title":"Sabiá-3 Technical Report","date":"2024-10-15","arxiv_id":"2410.12049","repositories_listed":0,"syntology":null},{"url":null,"slug":"sequential-llm-framework-for-fashion","title":"Sequential LLM Framework for Fashion Recommendation","date":"2024-10-15","arxiv_id":"2410.11327","repositories_listed":0,"syntology":null},{"url":"/paper/shakti-a-2-5-billion-parameter-small-language","slug":"shakti-a-2-5-billion-parameter-small-language","title":"SHAKTI: A 2.5 Billion Parameter Small Language Model Optimized for Edge AI and Low-Resource Environments","date":"2024-10-15","arxiv_id":"2410.11331","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetic-interlocutors-experiments-with","title":"Synthetic Interlocutors. Experiments with Generative AI to Prolong Ethnographic Encounters","date":"2024-10-15","arxiv_id":"2410.11395","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-fair-language-model-paradox","title":"The Fair Language Model Paradox","date":"2024-10-15","arxiv_id":"2410.11985","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-moral-case-for-using-language-model","title":"The Moral Case for Using Language Model Agents for Recommendation","date":"2024-10-15","arxiv_id":"2410.12123","repositories_listed":0,"syntology":null}],"record_sha256":"9308cded224171e0c0d038d4e4b171b7fdcae292d1286ad839802d2331050b22","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}