{"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/65","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":65,"pages_in_order":142,"rows_per_page":100,"rows":[6401,6500],"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/64","next":"/task/language-modeling/papers/66","papers":[{"url":null,"slug":"distil-xlstm-learning-attention-mechanisms","title":"Distil-xLSTM: Learning Attention Mechanisms through Recurrent Structures","date":"2025-03-24","arxiv_id":"2503.18565","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-object-interaction-with-vision-language","title":"Human-Object Interaction with Vision-Language Model Guided Relative Movement Dynamics","date":"2025-03-24","arxiv_id":"2503.18349","repositories_listed":0,"syntology":null},{"url":null,"slug":"langalign-enhancing-non-english-language","title":"LANGALIGN: Enhancing Non-English Language Models via Cross-Lingual Embedding Alignment","date":"2025-03-24","arxiv_id":"2503.18603","repositories_listed":0,"syntology":null},{"url":null,"slug":"manipulation-and-the-ai-act-large-language","title":"Manipulation and the AI Act: Large Language Model Chatbots and the Danger of Mirrors","date":"2025-03-24","arxiv_id":"2503.18387","repositories_listed":0,"syntology":null},{"url":null,"slug":"mmcr-advancing-visual-language-model-in","title":"MMCR: Advancing Visual Language Model in Multimodal Multi-Turn Contextual Reasoning","date":"2025-03-24","arxiv_id":"2503.18533","repositories_listed":0,"syntology":null},{"url":null,"slug":"modigen-a-large-language-model-based-workflow","title":"ModiGen: A Large Language Model-Based Workflow for Multi-Task Modelica Code Generation","date":"2025-03-24","arxiv_id":"2503.18460","repositories_listed":0,"syntology":null},{"url":null,"slug":"overcoming-vocabulary-mismatch-vocabulary","title":"Overcoming Vocabulary Mismatch: Vocabulary-agnostic Teacher Guided Language Modeling","date":"2025-03-24","arxiv_id":"2503.19123","repositories_listed":0,"syntology":null},{"url":null,"slug":"solving-situation-puzzles-with-large-language","title":"Solving Situation Puzzles with Large Language Model and External Reformulation","date":"2025-03-24","arxiv_id":"2503.18394","repositories_listed":0,"syntology":null},{"url":null,"slug":"teaching-llms-for-step-level-automatic-math","title":"Teaching LLMs for Step-Level Automatic Math Correction via Reinforcement Learning","date":"2025-03-24","arxiv_id":"2503.18432","repositories_listed":0,"syntology":null},{"url":null,"slug":"topv-compatible-token-pruning-with-inference","title":"TopV: Compatible Token Pruning with Inference Time Optimization for Fast and Low-Memory Multimodal Vision Language Model","date":"2025-03-24","arxiv_id":"2503.18278","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-acquisition-of-discrete","title":"Unsupervised Acquisition of Discrete Grammatical Categories","date":"2025-03-24","arxiv_id":"2503.18702","repositories_listed":0,"syntology":null},{"url":null,"slug":"detection-of-somali-written-fake-news-and","title":"Detection of Somali-written Fake News and Toxic Messages on the Social Media Using Transformer-based Language Models","date":"2025-03-23","arxiv_id":"2503.18117","repositories_listed":0,"syntology":null},{"url":null,"slug":"expertrag-efficient-rag-with-mixture-of","title":"ExpertRAG: Efficient RAG with Mixture of Experts -- Optimizing Context Retrieval for Adaptive LLM Responses","date":"2025-03-23","arxiv_id":"2504.08744","repositories_listed":0,"syntology":null},{"url":null,"slug":"lakotabert-a-transformer-based-model-for-low","title":"LakotaBERT: A Transformer-based Model for Low Resource Lakota Language","date":"2025-03-23","arxiv_id":"2503.18212","repositories_listed":0,"syntology":null},{"url":null,"slug":"mllm-for3d-adapting-multimodal-large-language","title":"MLLM-For3D: Adapting Multimodal Large Language Model for 3D Reasoning Segmentation","date":"2025-03-23","arxiv_id":"2503.18135","repositories_listed":0,"syntology":null},{"url":null,"slug":"payload-aware-intrusion-detection-with-cmae","title":"Payload-Aware Intrusion Detection with CMAE and Large Language Models","date":"2025-03-23","arxiv_id":"2503.20798","repositories_listed":0,"syntology":null},{"url":null,"slug":"simulating-filter-bubble-on-short-video","title":"Simulating Filter Bubble on Short-video Recommender System with Large Language Model Agents","date":"2025-03-23","arxiv_id":"2504.08742","repositories_listed":0,"syntology":null},{"url":null,"slug":"wlb-llm-workload-balanced-4d-parallelism-for","title":"WLB-LLM: Workload-Balanced 4D Parallelism for Large Language Model Training","date":"2025-03-23","arxiv_id":"2503.17924","repositories_listed":0,"syntology":null},{"url":null,"slug":"countllm-towards-generalizable-repetitive","title":"CountLLM: Towards Generalizable Repetitive Action Counting via Large Language Model","date":"2025-03-22","arxiv_id":"2503.17690","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-enhanced-vision-language-modeling-with","title":"Audio-Enhanced Vision-Language Modeling with Latent Space Broadening for High Quality Data Expansion","date":"2025-03-21","arxiv_id":"2503.17551","repositories_listed":0,"syntology":null},{"url":null,"slug":"case-condition-aware-sentence-embeddings-for","title":"CASE -- Condition-Aware Sentence Embeddings for Conditional Semantic Textual Similarity Measurement","date":"2025-03-21","arxiv_id":"2503.17279","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-knowledge-distillation-via","title":"Efficient Knowledge Distillation via Curriculum Extraction","date":"2025-03-21","arxiv_id":"2503.17494","repositories_listed":0,"syntology":null},{"url":null,"slug":"federated-cross-domain-click-through-rate","title":"Federated Cross-Domain Click-Through Rate Prediction With Large Language Model Augmentation","date":"2025-03-21","arxiv_id":"2503.16875","repositories_listed":0,"syntology":null},{"url":null,"slug":"field-mediated-semantic-organization-in-large","title":"Field-Mediated Semantic Organization in Large Language Models: Evidence for Quantum-Like Properties in Artificial Neural Systems","date":"2025-03-21","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"imagine-to-hear-auditory-knowledge-generation","title":"Imagine to Hear: Auditory Knowledge Generation can be an Effective Assistant for Language Models","date":"2025-03-21","arxiv_id":"2503.16853","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-compression-via-the","title":"Large Language Model Compression via the Nested Activation-Aware Decomposition","date":"2025-03-21","arxiv_id":"2503.17101","repositories_listed":0,"syntology":null},{"url":null,"slug":"chatgpt-and-u-x-a-rapid-review-on-measuring","title":"ChatGPT and U(X): A Rapid Review on Measuring the User Experience","date":"2025-03-20","arxiv_id":"2503.15808","repositories_listed":0,"syntology":null},{"url":null,"slug":"entropy-based-exploration-conduction-for","title":"Entropy-based Exploration Conduction for Multi-step Reasoning","date":"2025-03-20","arxiv_id":"2503.15848","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-autoregressive-image-generation","title":"Improving Autoregressive Image Generation through Coarse-to-Fine Token Prediction","date":"2025-03-20","arxiv_id":"2503.16194","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-language-models-to-decipher-the","title":"Using Language Models to Decipher the Motivation Behind Human Behaviors","date":"2025-03-20","arxiv_id":"2503.15752","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-vot-r1-an-efficient-video-inference","title":"Video-VoT-R1: An efficient video inference model integrating image packing and AoE architecture","date":"2025-03-20","arxiv_id":"2503.15807","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-survey-on-architectural","title":"A Comprehensive Survey on Architectural Advances in Deep CNNs: Challenges, Applications, and Emerging Research Directions","date":"2025-03-19","arxiv_id":"2503.16546","repositories_listed":0,"syntology":null},{"url":null,"slug":"aligning-crowd-sourced-human-feedback-for","title":"Aligning Crowd-sourced Human Feedback for Reinforcement Learning on Code Generation by Large Language Models","date":"2025-03-19","arxiv_id":"2503.15129","repositories_listed":0,"syntology":null},{"url":null,"slug":"graspcorrect-robotic-grasp-correction-via","title":"GraspCorrect: Robotic Grasp Correction via Vision-Language Model-Guided Feedback","date":"2025-03-19","arxiv_id":"2503.15035","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-moe-based-large-language-model-for","title":"Leveraging MoE-based Large Language Model for Zero-Shot Multi-Task Semantic Communication","date":"2025-03-19","arxiv_id":"2503.15722","repositories_listed":0,"syntology":null},{"url":null,"slug":"probing-the-topology-of-the-space-of-tokens","title":"Probing the topology of the space of tokens with structured prompts","date":"2025-03-19","arxiv_id":"2503.15421","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-transmission-of-punctured-text-with","title":"Robust Transmission of Punctured Text with Large Language Model-based Recovery","date":"2025-03-19","arxiv_id":"2503.14831","repositories_listed":0,"syntology":null},{"url":null,"slug":"shushing-let-s-imagine-an-authentic-speech","title":"Shushing! Let's Imagine an Authentic Speech from the Silent Video","date":"2025-03-19","arxiv_id":"2503.14928","repositories_listed":0,"syntology":null},{"url":null,"slug":"upme-an-unsupervised-peer-review-framework","title":"UPME: An Unsupervised Peer Review Framework for Multimodal Large Language Model Evaluation","date":"2025-03-19","arxiv_id":"2503.14941","repositories_listed":0,"syntology":null},{"url":null,"slug":"chatbev-a-visual-language-model-that","title":"ChatBEV: A Visual Language Model that Understands BEV Maps","date":"2025-03-18","arxiv_id":"2503.13938","repositories_listed":0,"syntology":null},{"url":null,"slug":"enabling-inclusive-systematic-reviews","title":"Enabling Inclusive Systematic Reviews: Incorporating Preprint Articles with Large Language Model-Driven Evaluations","date":"2025-03-18","arxiv_id":"2503.13857","repositories_listed":0,"syntology":null},{"url":null,"slug":"good-evil-reputation-judgment-of-celebrities","title":"Good/Evil Reputation Judgment of Celebrities by LLMs via Retrieval Augmented Generation","date":"2025-03-18","arxiv_id":"2503.14382","repositories_listed":0,"syntology":null},{"url":null,"slug":"layer-wise-adaptive-gradient-norm-penalizing","title":"Layer-wise Adaptive Gradient Norm Penalizing Method for Efficient and Accurate Deep Learning","date":"2025-03-18","arxiv_id":"2503.14205","repositories_listed":0,"syntology":null},{"url":null,"slug":"mok-rag-mixture-of-knowledge-paths-enhanced","title":"MoK-RAG: Mixture of Knowledge Paths Enhanced Retrieval-Augmented Generation for Embodied AI Environments","date":"2025-03-18","arxiv_id":"2503.13882","repositories_listed":0,"syntology":null},{"url":null,"slug":"spacevllm-endowing-multimodal-large-language","title":"SpaceVLLM: Endowing Multimodal Large Language Model with Spatio-Temporal Video Grounding Capability","date":"2025-03-18","arxiv_id":"2503.13983","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-empty-chair-using-llms-to-raise-missing","title":"The Empty Chair: Using LLMs to Raise Missing Perspectives in Policy Deliberations","date":"2025-03-18","arxiv_id":"2503.13812","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-a-barrier-free-geoqa-portal-natural","title":"Towards a Barrier-free GeoQA Portal: Natural Language Interaction with Geospatial Data Using Multi-Agent LLMs and Semantic Search","date":"2025-03-18","arxiv_id":"2503.14251","repositories_listed":0,"syntology":null},{"url":null,"slug":"varp-reinforcement-learning-from-vision","title":"VARP: Reinforcement Learning from Vision-Language Model Feedback with Agent Regularized Preferences","date":"2025-03-18","arxiv_id":"2503.13817","repositories_listed":0,"syntology":null},{"url":null,"slug":"agents-play-thousands-of-3d-video-games","title":"Agents Play Thousands of 3D Video Games","date":"2025-03-17","arxiv_id":"2503.13356","repositories_listed":0,"syntology":null},{"url":null,"slug":"analytic-subspace-routing-how-recursive-least","title":"Analytic Subspace Routing: How Recursive Least Squares Works in Continual Learning of Large Language Model","date":"2025-03-17","arxiv_id":"2503.13575","repositories_listed":0,"syntology":null},{"url":null,"slug":"hide-llava-hierarchical-decoupling-for","title":"HiDe-LLaVA: Hierarchical Decoupling for Continual Instruction Tuning of Multimodal Large Language Model","date":"2025-03-17","arxiv_id":"2503.12941","repositories_listed":0,"syntology":null},{"url":null,"slug":"high-entropy-advantage-in-neural-networks","title":"High-entropy Advantage in Neural Networks' Generalizability","date":"2025-03-17","arxiv_id":"2503.13145","repositories_listed":0,"syntology":null},{"url":null,"slug":"hybridgen-vlm-guided-hybrid-planning-for","title":"HybridGen: VLM-Guided Hybrid Planning for Scalable Data Generation of Imitation Learning","date":"2025-03-17","arxiv_id":"2503.13171","repositories_listed":0,"syntology":null},{"url":null,"slug":"kvshare-semantic-aware-key-value-cache","title":"KVShare: An LLM Service System with Efficient and Effective Multi-Tenant KV Cache Reuse","date":"2025-03-17","arxiv_id":"2503.16525","repositories_listed":0,"syntology":null},{"url":null,"slug":"pandora-diffusion-policy-learning-for","title":"PANDORA: Diffusion Policy Learning for Dexterous Robotic Piano Playing","date":"2025-03-17","arxiv_id":"2503.14545","repositories_listed":0,"syntology":null},{"url":null,"slug":"georsmllm-a-multimodal-large-language-model","title":"GeoRSMLLM: A Multimodal Large Language Model for Vision-Language Tasks in Geoscience and Remote Sensing","date":"2025-03-16","arxiv_id":"2503.12490","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-mediated-guidance-of-marl-systems","title":"LLM-Mediated Guidance of MARL Systems","date":"2025-03-16","arxiv_id":"2503.13553","repositories_listed":0,"syntology":null},{"url":null,"slug":"state-fourier-diffusion-language-model-sfdlm","title":"State Fourier Diffusion Language Model (SFDLM): A Scalable, Novel Iterative Approach to Language Modeling","date":"2025-03-16","arxiv_id":"2503.17382","repositories_listed":0,"syntology":null},{"url":null,"slug":"applications-of-large-language-model","title":"Applications of Large Language Model Reasoning in Feature Generation","date":"2025-03-15","arxiv_id":"2503.11989","repositories_listed":0,"syntology":null},{"url":null,"slug":"interpretation-gaps-in-llm-assisted","title":"Interpretation Gaps in LLM-Assisted Comprehension of Privacy Documents","date":"2025-03-15","arxiv_id":"2503.12225","repositories_listed":0,"syntology":null},{"url":null,"slug":"maritime-mission-planning-for-unmanned","title":"Maritime Mission Planning for Unmanned Surface Vessel using Large Language Model","date":"2025-03-15","arxiv_id":"2503.12065","repositories_listed":0,"syntology":null},{"url":null,"slug":"research-on-large-language-model-cross-cloud","title":"Research on Large Language Model Cross-Cloud Privacy Protection and Collaborative Training based on Federated Learning","date":"2025-03-15","arxiv_id":"2503.12226","repositories_listed":0,"syntology":null},{"url":null,"slug":"tailor-an-integrated-text-driven-cg-ready","title":"Tailor: An Integrated Text-Driven CG-Ready Human and Garment Generation System","date":"2025-03-15","arxiv_id":"2503.12052","repositories_listed":0,"syntology":null},{"url":null,"slug":"brillm-brain-inspired-large-language-model","title":"BriLLM: Brain-inspired Large Language Model","date":"2025-03-14","arxiv_id":"2503.11299","repositories_listed":0,"syntology":null},{"url":null,"slug":"don-t-forget-it-conditional-sparse","title":"Don't Forget It! Conditional Sparse Autoencoder Clamping Works for Unlearning","date":"2025-03-14","arxiv_id":"2503.11127","repositories_listed":0,"syntology":null},{"url":null,"slug":"empowering-time-series-analysis-with","title":"Empowering Time Series Analysis with Synthetic Data: A Survey and Outlook in the Era of Foundation Models","date":"2025-03-14","arxiv_id":"2503.11411","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-powered-ai-systems","title":"Large language model-powered AI systems achieve self-replication with no human intervention","date":"2025-03-14","arxiv_id":"2503.17378","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-agents-for-education-advances-and","title":"LLM Agents for Education: Advances and Applications","date":"2025-03-14","arxiv_id":"2503.11733","repositories_listed":0,"syntology":null},{"url":null,"slug":"potential-of-large-language-model-powered","title":"Potential of large language model-powered nudges for promoting daily water and energy conservation","date":"2025-03-14","arxiv_id":"2503.11531","repositories_listed":0,"syntology":null},{"url":null,"slug":"rule-guided-feedback-enhancing-reasoning-by","title":"Rule-Guided Feedback: Enhancing Reasoning by Enforcing Rule Adherence in Large Language Models","date":"2025-03-14","arxiv_id":"2503.11336","repositories_listed":0,"syntology":null},{"url":null,"slug":"test-time-training-provably-improves","title":"Test-Time Training Provably Improves Transformers as In-context Learners","date":"2025-03-14","arxiv_id":"2503.11842","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-compression-for-efficient-language","title":"Text Compression for Efficient Language Generation","date":"2025-03-14","arxiv_id":"2503.11426","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-extreme-pruning-of-llms-with-plug-and","title":"Towards Extreme Pruning of LLMs with Plug-and-Play Mixed Sparsity","date":"2025-03-14","arxiv_id":"2503.11164","repositories_listed":0,"syntology":null},{"url":null,"slug":"hybrid-agents-for-image-restoration","title":"Hybrid Agents for Image Restoration","date":"2025-03-13","arxiv_id":"2503.10120","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-models-graph-searching-and","title":"Language Models, Graph Searching, and Supervision Adulteration: When More Supervision is Less and How to Make More More","date":"2025-03-13","arxiv_id":"2503.10542","repositories_listed":0,"syntology":null},{"url":null,"slug":"llms-working-in-harmony-a-survey-on-the","title":"LLMs Working in Harmony: A Survey on the Technological Aspects of Building Effective LLM-Based Multi Agent Systems","date":"2025-03-13","arxiv_id":"2504.01963","repositories_listed":0,"syntology":null},{"url":null,"slug":"mmlu-prox-a-multilingual-benchmark-for","title":"MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation","date":"2025-03-13","arxiv_id":"2503.10497","repositories_listed":0,"syntology":null},{"url":null,"slug":"mousegpt-a-large-scale-vision-language-model","title":"MouseGPT: A Large-scale Vision-Language Model for Mouse Behavior Analysis","date":"2025-03-13","arxiv_id":"2503.10212","repositories_listed":0,"syntology":null},{"url":null,"slug":"neurips-2023-llm-efficiency-fine-tuning","title":"NeurIPS 2023 LLM Efficiency Fine-tuning Competition","date":"2025-03-13","arxiv_id":"2503.13507","repositories_listed":0,"syntology":null},{"url":null,"slug":"prism-preference-refinement-via-implicit","title":"PRISM: Preference Refinement via Implicit Scene Modeling for 3D Vision-Language Preference-Based Reinforcement Learning","date":"2025-03-13","arxiv_id":"2503.10177","repositories_listed":0,"syntology":null},{"url":null,"slug":"representation-based-reward-modeling-for","title":"Representation-based Reward Modeling for Efficient Safety Alignment of Large Language Model","date":"2025-03-13","arxiv_id":"2503.10093","repositories_listed":0,"syntology":null},{"url":null,"slug":"sce-scalable-consistency-ensembles-make","title":"SCE: Scalable Consistency Ensembles Make Blackbox Large Language Model Generation More Reliable","date":"2025-03-13","arxiv_id":"2503.10881","repositories_listed":0,"syntology":null},{"url":null,"slug":"siege-autonomous-multi-turn-jailbreaking-of","title":"Tempest: Autonomous Multi-Turn Jailbreaking of Large Language Models with Tree Search","date":"2025-03-13","arxiv_id":"2503.10619","repositories_listed":0,"syntology":null},{"url":null,"slug":"smartway-enhanced-waypoint-prediction-and","title":"SmartWay: Enhanced Waypoint Prediction and Backtracking for Zero-Shot Vision-and-Language Navigation","date":"2025-03-13","arxiv_id":"2503.10069","repositories_listed":0,"syntology":null},{"url":null,"slug":"tacticexpert-spatial-temporal-graph-language","title":"TacticExpert: Spatial-Temporal Graph Language Model for Basketball Tactics","date":"2025-03-13","arxiv_id":"2503.10722","repositories_listed":0,"syntology":null},{"url":null,"slug":"bambi-developing-baby-language-models-for","title":"BAMBI: Developing Baby Language Models for Italian","date":"2025-03-12","arxiv_id":"2503.09481","repositories_listed":0,"syntology":null},{"url":null,"slug":"communication-efficient-language-model","title":"Communication-Efficient Language Model Training Scales Reliably and Robustly: Scaling Laws for DiLoCo","date":"2025-03-12","arxiv_id":"2503.09799","repositories_listed":0,"syntology":null},{"url":null,"slug":"global-position-aware-group-choreography","title":"Global Position Aware Group Choreography using Large Language Model","date":"2025-03-12","arxiv_id":"2503.09645","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-knowledge-graphs-and-llms-for","title":"Leveraging Knowledge Graphs and LLMs for Context-Aware Messaging","date":"2025-03-12","arxiv_id":"2503.13499","repositories_listed":0,"syntology":null},{"url":null,"slug":"medical-large-language-model-benchmarks","title":"Medical Large Language Model Benchmarks Should Prioritize Construct Validity","date":"2025-03-12","arxiv_id":"2503.10694","repositories_listed":0,"syntology":null},{"url":null,"slug":"membership-inference-attacks-fueled-by-few","title":"Membership Inference Attacks fueled by Few-Short Learning to detect privacy leakage tackling data integrity","date":"2025-03-12","arxiv_id":"2503.09365","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforcement-learning-is-all-you-need","title":"Reinforcement Learning is all You Need","date":"2025-03-12","arxiv_id":"2503.09512","repositories_listed":0,"syntology":null},{"url":null,"slug":"saebench-a-comprehensive-benchmark-for-sparse","title":"SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability","date":"2025-03-12","arxiv_id":"2503.09532","repositories_listed":0,"syntology":null},{"url":null,"slug":"sometimes-painful-but-certainly-promising","title":"Sometimes Painful but Certainly Promising: Feasibility and Trade-offs of Language Model Inference at the Edge","date":"2025-03-12","arxiv_id":"2503.09114","repositories_listed":0,"syntology":null},{"url":null,"slug":"toward-a-method-for-llm-enabled-indoor","title":"Toward a method for LLM-enabled Indoor Navigation","date":"2025-03-12","arxiv_id":"2503.11702","repositories_listed":0,"syntology":null},{"url":null,"slug":"why-llms-cannot-think-and-how-to-fix-it","title":"Why LLMs Cannot Think and How to Fix It","date":"2025-03-12","arxiv_id":"2503.09211","repositories_listed":0,"syntology":null},{"url":null,"slug":"xvlm2vec-adapting-lvlm-based-embedding-models","title":"xVLM2Vec: Adapting LVLM-based embedding models to multilinguality using Self-Knowledge Distillation","date":"2025-03-12","arxiv_id":"2503.09313","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-cascading-cooperative-multi-agent-framework","title":"A Cascading Cooperative Multi-agent Framework for On-ramp Merging Control Integrating Large Language Models","date":"2025-03-11","arxiv_id":"2503.08199","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerating-moe-model-inference-with-expert","title":"Accelerating MoE Model Inference with Expert Sharding","date":"2025-03-11","arxiv_id":"2503.08467","repositories_listed":0,"syntology":null},{"url":null,"slug":"bring-remote-sensing-object-detect-into","title":"Bring Remote Sensing Object Detect Into Nature Language Model: Using SFT Method","date":"2025-03-11","arxiv_id":"2503.08144","repositories_listed":0,"syntology":null}],"record_sha256":"b0434040fe2fdddac93b215548a7f42febe5c0c57fa71af550065c2d9deb54ad","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}