{"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/72","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":72,"pages_in_order":142,"rows_per_page":100,"rows":[7101,7200],"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/71","next":"/task/language-modeling/papers/73","papers":[{"url":null,"slug":"investorbench-a-benchmark-for-financial","title":"INVESTORBENCH: A Benchmark for Financial Decision-Making Tasks with LLM-based Agent","date":"2024-12-24","arxiv_id":"2412.18174","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-large-language-model-good-at-triple-set","title":"Is Large Language Model Good at Triple Set Prediction? An Empirical Study","date":"2024-12-24","arxiv_id":"2412.18443","repositories_listed":0,"syntology":null},{"url":null,"slug":"kunserve-elastic-and-efficient-large-language","title":"KunServe: Efficient Parameter-centric Memory Management for LLM Serving","date":"2024-12-24","arxiv_id":"2412.18169","repositories_listed":0,"syntology":null},{"url":null,"slug":"lsaq-layer-specific-adaptive-quantization-for","title":"LSAQ: Layer-Specific Adaptive Quantization for Large Language Model Deployment","date":"2024-12-24","arxiv_id":"2412.18135","repositories_listed":0,"syntology":null},{"url":null,"slug":"molly-making-large-language-model-agents","title":"Molly: Making Large Language Model Agents Solve Python Problem More Logically","date":"2024-12-24","arxiv_id":"2412.18093","repositories_listed":0,"syntology":null},{"url":null,"slug":"pld-tree-persistent-laplacian-decision-tree","title":"PLD-Tree: Persistent Laplacian Decision Tree for Protein-Protein Binding Free Energy Prediction","date":"2024-12-24","arxiv_id":"2412.18541","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-world-deployment-and-evaluation-of","title":"Real-world Deployment and Evaluation of PErioperative AI CHatbot (PEACH) -- a Large Language Model Chatbot for Perioperative Medicine","date":"2024-12-24","arxiv_id":"2412.18096","repositories_listed":0,"syntology":null},{"url":null,"slug":"visionllm-based-multimodal-fusion-network-for","title":"VisionLLM-based Multimodal Fusion Network for Glottic Carcinoma Early Detection","date":"2024-12-24","arxiv_id":"2412.18124","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-resource-speech-translation-and","title":"Zero-resource Speech Translation and Recognition with LLMs","date":"2024-12-24","arxiv_id":"2412.18566","repositories_listed":0,"syntology":null},{"url":null,"slug":"benczechmark-a-czech-centric-multitask-and","title":"BenCzechMark : A Czech-centric Multitask and Multimetric Benchmark for Large Language Models with Duel Scoring Mechanism","date":"2024-12-23","arxiv_id":"2412.17933","repositories_listed":0,"syntology":null},{"url":null,"slug":"contrato360-2-0-a-document-and-database","title":"Contrato360 2.0: A Document and Database-Driven Question-Answer System using Large Language Models and Agents","date":"2024-12-23","arxiv_id":"2412.17942","repositories_listed":0,"syntology":null},{"url":null,"slug":"deliberation-in-latent-space-via","title":"Deliberation in Latent Space via Differentiable Cache Augmentation","date":"2024-12-23","arxiv_id":"2412.17747","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-multi-agent-orchestration-and","title":"Dynamic Multi-Agent Orchestration and Retrieval for Multi-Source Question-Answer Systems using Large Language Models","date":"2024-12-23","arxiv_id":"2412.17964","repositories_listed":0,"syntology":null},{"url":null,"slug":"fedtlu-federated-learning-with-targeted-layer","title":"FedTLU: Federated Learning with Targeted Layer Updates","date":"2024-12-23","arxiv_id":"2412.17692","repositories_listed":0,"syntology":null},{"url":null,"slug":"gcs-m3vlt-guided-context-self-attention-based","title":"GCS-M3VLT: Guided Context Self-Attention based Multi-modal Medical Vision Language Transformer for Retinal Image Captioning","date":"2024-12-23","arxiv_id":"2412.17251","repositories_listed":0,"syntology":null},{"url":null,"slug":"gqsa-group-quantization-and-sparsity-for","title":"GQSA: Group Quantization and Sparsity for Accelerating Large Language Model Inference","date":"2024-12-23","arxiv_id":"2412.17560","repositories_listed":0,"syntology":null},{"url":null,"slug":"peptune-de-novo-generation-of-therapeutic","title":"PepTune: De Novo Generation of Therapeutic Peptides with Multi-Objective-Guided Discrete Diffusion","date":"2024-12-23","arxiv_id":"2412.17780","repositories_listed":0,"syntology":null},{"url":null,"slug":"vitro-vocabulary-inversion-for-time-series","title":"VITRO: Vocabulary Inversion for Time-series Representation Optimization","date":"2024-12-23","arxiv_id":"2412.17921","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-career-interview-dialogue-system-using","title":"A Career Interview Dialogue System using Large Language Model-based Dynamic Slot Generation","date":"2024-12-22","arxiv_id":"2412.16943","repositories_listed":0,"syntology":null},{"url":null,"slug":"autoregressive-speech-synthesis-with-next","title":"Autoregressive Speech Synthesis with Next-Distribution Prediction","date":"2024-12-22","arxiv_id":"2412.16846","repositories_listed":0,"syntology":null},{"url":null,"slug":"better-think-with-tables-leveraging-tables-to","title":"Better Think with Tables: Leveraging Tables to Enhance Large Language Model Comprehension","date":"2024-12-22","arxiv_id":"2412.17189","repositories_listed":0,"syntology":null},{"url":null,"slug":"dr-encoder-encode-low-rank-gradients-with","title":"DR-Encoder: Encode Low-rank Gradients with Random Prior for Large Language Models Differentially Privately","date":"2024-12-22","arxiv_id":"2412.17053","repositories_listed":0,"syntology":null},{"url":null,"slug":"substationai-multimodal-large-model-based","title":"SubstationAI: Multimodal Large Model-Based Approaches for Analyzing Substation Equipment Faults","date":"2024-12-22","arxiv_id":"2412.17077","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-a-unified-paradigm-integrating","title":"Towards a Unified Paradigm: Integrating Recommendation Systems as a New Language in Large Models","date":"2024-12-22","arxiv_id":"2412.16933","repositories_listed":0,"syntology":null},{"url":null,"slug":"application-of-multimodal-large-language","title":"Application of Multimodal Large Language Models in Autonomous Driving","date":"2024-12-21","arxiv_id":"2412.16410","repositories_listed":0,"syntology":null},{"url":null,"slug":"assessing-social-alignment-do-personality","title":"Assessing Social Alignment: Do Personality-Prompted Large Language Models Behave Like Humans?","date":"2024-12-21","arxiv_id":"2412.16772","repositories_listed":0,"syntology":null},{"url":null,"slug":"correcting-large-language-model-behavior-via","title":"Correcting Large Language Model Behavior via Influence Function","date":"2024-12-21","arxiv_id":"2412.16451","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-retrieval-augmented-generation-without","title":"Speech Retrieval-Augmented Generation without Automatic Speech Recognition","date":"2024-12-21","arxiv_id":"2412.16500","repositories_listed":0,"syntology":null},{"url":null,"slug":"technical-report-small-language-model-for","title":"Technical Report: Small Language Model for Japanese Clinical and Medicine","date":"2024-12-21","arxiv_id":"2412.16423","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-task-shield-enforcing-task-alignment-to","title":"The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents","date":"2024-12-21","arxiv_id":"2412.16682","repositories_listed":0,"syntology":null},{"url":null,"slug":"autoware-flex-human-instructed-dynamically","title":"Autoware.Flex: Human-Instructed Dynamically Reconfigurable Autonomous Driving Systems","date":"2024-12-20","arxiv_id":"2412.16265","repositories_listed":0,"syntology":null},{"url":null,"slug":"babyhgrn-exploring-rnns-for-sample-efficient","title":"BabyHGRN: Exploring RNNs for Sample-Efficient Training of Language Models","date":"2024-12-20","arxiv_id":"2412.15978","repositories_listed":0,"syntology":null},{"url":null,"slug":"continual-learning-using-only-large-language","title":"Continual Learning Using Only Large Language Model Prompting","date":"2024-12-20","arxiv_id":"2412.15479","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-driven-mechanism-design-jointly","title":"Data-Driven Mechanism Design: Jointly Eliciting Preferences and Information","date":"2024-12-20","arxiv_id":"2412.16132","repositories_listed":0,"syntology":null},{"url":null,"slug":"development-of-a-large-scale-dataset-of-chest","title":"Development of a Large-scale Dataset of Chest Computed Tomography Reports in Japanese and a High-performance Finding Classification Model","date":"2024-12-20","arxiv_id":"2412.15907","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-label-name-refinement-for-few-shot","title":"Dynamic Label Name Refinement for Few-Shot Dialogue Intent Classification","date":"2024-12-20","arxiv_id":"2412.15603","repositories_listed":0,"syntology":null},{"url":null,"slug":"ensembling-large-language-models-with-process","title":"Ensembling Large Language Models with Process Reward-Guided Tree Search for Better Complex Reasoning","date":"2024-12-20","arxiv_id":"2412.15797","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-general-to-specific-tailoring-large","title":"From General to Specific: Tailoring Large Language Models for Personalized Healthcare","date":"2024-12-20","arxiv_id":"2412.15957","repositories_listed":0,"syntology":null},{"url":null,"slug":"interleaved-speech-text-language-models-are","title":"Interleaved Speech-Text Language Models are Simple Streaming Text to Speech Synthesizers","date":"2024-12-20","arxiv_id":"2412.16102","repositories_listed":0,"syntology":null},{"url":null,"slug":"j-edi-qa-benchmark-for-deep-sea-organism","title":"J-EDI QA: Benchmark for deep-sea organism-specific multimodal LLM","date":"2024-12-20","arxiv_id":"2412.15574","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-modal-agent-tuning-building-a-vlm","title":"Multi-modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool Usage","date":"2024-12-20","arxiv_id":"2412.15606","repositories_listed":0,"syntology":null},{"url":null,"slug":"polysmart-and-vireo-trecvid-2024-ad-hoc-video","title":"PolySmart and VIREO @ TRECVid 2024 Ad-hoc Video Search","date":"2024-12-20","arxiv_id":"2412.15494","repositories_listed":0,"syntology":null},{"url":null,"slug":"promptoptme-error-aware-prompt-compression","title":"PromptOptMe: Error-Aware Prompt Compression for LLM-based MT Evaluation Metrics","date":"2024-12-20","arxiv_id":"2412.16120","repositories_listed":0,"syntology":null},{"url":null,"slug":"quart-online-latency-free-large-multimodal","title":"QUART-Online: Latency-Free Large Multimodal Language Model for Quadruped Robot Learning","date":"2024-12-20","arxiv_id":"2412.15576","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparative-study-of-dspy-teleprompter","title":"A Comparative Study of DSPy Teleprompter Algorithms for Aligning Large Language Models Evaluation Metrics to Human Evaluation","date":"2024-12-19","arxiv_id":"2412.15298","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-root-cause-analysis-system-for","title":"Automated Root Cause Analysis System for Complex Data Products","date":"2024-12-19","arxiv_id":"2412.15374","repositories_listed":0,"syntology":null},{"url":null,"slug":"directorllm-for-human-centric-video","title":"DirectorLLM for Human-Centric Video Generation","date":"2024-12-19","arxiv_id":"2412.14484","repositories_listed":0,"syntology":null},{"url":null,"slug":"disentangling-reasoning-tokens-and","title":"Disentangling Reasoning Tokens and Boilerplate Tokens For Language Model Fine-tuning","date":"2024-12-19","arxiv_id":"2412.14780","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-convolutional-networks-named-entity","title":"Graph-Convolutional Networks: Named Entity Recognition and Large Language Model Embedding in Document Clustering","date":"2024-12-19","arxiv_id":"2412.14867","repositories_listed":0,"syntology":null},{"url":null,"slug":"harmoniceval-multi-modal-multi-task-multi","title":"HarmonicEval: Multi-modal, Multi-task, Multi-criteria Automatic Evaluation Using a Vision Language Model","date":"2024-12-19","arxiv_id":"2412.14613","repositories_listed":0,"syntology":null},{"url":null,"slug":"hpc-coder-v2-studying-code-llms-across-low","title":"HPC-Coder-V2: Studying Code LLMs Across Low-Resource Parallel Languages","date":"2024-12-19","arxiv_id":"2412.15178","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowing-where-to-focus-attention-guided","title":"Knowing Where to Focus: Attention-Guided Alignment for Text-based Person Search","date":"2024-12-19","arxiv_id":"2412.15106","repositories_listed":0,"syntology":null},{"url":null,"slug":"movie2story-a-framework-for-understanding","title":"Movie2Story: A framework for understanding videos and telling stories in the form of novel text","date":"2024-12-19","arxiv_id":"2412.14965","repositories_listed":0,"syntology":null},{"url":null,"slug":"moving-beyond-lda-a-comparison-of","title":"Moving Beyond LDA: A Comparison of Unsupervised Topic Modelling Techniques for Qualitative Data Analysis of Online Communities","date":"2024-12-19","arxiv_id":"2412.14486","repositories_listed":0,"syntology":null},{"url":null,"slug":"vlm-ad-end-to-end-autonomous-driving-through","title":"VLM-AD: End-to-End Autonomous Driving through Vision-Language Model Supervision","date":"2024-12-19","arxiv_id":"2412.14446","repositories_listed":0,"syntology":null},{"url":null,"slug":"cad-assistant-tool-augmented-vllms-as-generic","title":"CAD-Assistant: Tool-Augmented VLLMs as Generic CAD Task Solvers","date":"2024-12-18","arxiv_id":"2412.13810","repositories_listed":0,"syntology":null},{"url":null,"slug":"genx-mastering-code-and-test-generation-with","title":"GenX: Mastering Code and Test Generation with Execution Feedback","date":"2024-12-18","arxiv_id":"2412.13464","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-sem-a-sentiment-based-student-engagement","title":"LLM-SEM: A Sentiment-Based Student Engagement Metric Using LLMS for E-Learning Platforms","date":"2024-12-18","arxiv_id":"2412.13765","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-enhancing-root-cause-analysis-with-sql","title":"On Enhancing Root Cause Analysis with SQL Summaries for Failures in Database Workload Replays at SAP HANA","date":"2024-12-18","arxiv_id":"2412.13679","repositories_listed":0,"syntology":null},{"url":null,"slug":"read-like-a-radiologist-efficient-vision","title":"Read Like a Radiologist: Efficient Vision-Language Model for 3D Medical Imaging Interpretation","date":"2024-12-18","arxiv_id":"2412.13558","repositories_listed":0,"syntology":null},{"url":null,"slug":"songeditor-adapting-zero-shot-song-generation","title":"SongEditor: Adapting Zero-Shot Song Generation Language Model as a Multi-Task Editor","date":"2024-12-18","arxiv_id":"2412.13786","repositories_listed":0,"syntology":null},{"url":null,"slug":"core-context-aware-attention-for-long-context","title":"Core Context Aware Attention for Long Context Language Modeling","date":"2024-12-17","arxiv_id":"2412.12465","repositories_listed":0,"syntology":null},{"url":null,"slug":"feather-the-throttle-revisiting-visual-token","title":"Feather the Throttle: Revisiting Visual Token Pruning for Vision-Language Model Acceleration","date":"2024-12-17","arxiv_id":"2412.13180","repositories_listed":0,"syntology":null},{"url":null,"slug":"focuschat-text-guided-long-video","title":"FocusChat: Text-guided Long Video Understanding via Spatiotemporal Information Filtering","date":"2024-12-17","arxiv_id":"2412.12833","repositories_listed":0,"syntology":null},{"url":null,"slug":"iprop-interactive-prompt-optimization-for","title":"iPrOp: Interactive Prompt Optimization for Large Language Models with a Human in the Loop","date":"2024-12-17","arxiv_id":"2412.12644","repositories_listed":0,"syntology":null},{"url":null,"slug":"lmunit-fine-grained-evaluation-with-natural","title":"LMUnit: Fine-grained Evaluation with Natural Language Unit Tests","date":"2024-12-17","arxiv_id":"2412.13091","repositories_listed":0,"syntology":null},{"url":null,"slug":"make-imagination-clearer-stable-diffusion","title":"Make Imagination Clearer! Stable Diffusion-based Visual Imagination for Multimodal Machine Translation","date":"2024-12-17","arxiv_id":"2412.12627","repositories_listed":0,"syntology":null},{"url":"/paper/posterior-mean-matching-generative-modeling","slug":"posterior-mean-matching-generative-modeling","title":"Posterior Mean Matching: Generative Modeling through Online Bayesian Inference","date":"2024-12-17","arxiv_id":"2412.13286","repositories_listed":0,"syntology":null},{"url":null,"slug":"swan-preprocessing-sgd-enables-adam-level","title":"SWAN: SGD with Normalization and Whitening Enables Stateless LLM Training","date":"2024-12-17","arxiv_id":"2412.13148","repositories_listed":0,"syntology":null},{"url":null,"slug":"task-agnostic-language-model-watermarking-via","title":"Task-Agnostic Language Model Watermarking via High Entropy Passthrough Layers","date":"2024-12-17","arxiv_id":"2412.12563","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-reliability-paradox-exploring-how","title":"The Reliability Paradox: Exploring How Shortcut Learning Undermines Language Model Calibration","date":"2024-12-17","arxiv_id":"2412.15269","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-aware-hybrid-inference-with-on","title":"Uncertainty-Aware Hybrid Inference with On-Device Small and Remote Large Language Models","date":"2024-12-17","arxiv_id":"2412.12687","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-mathematical-reasoning-in-the-era","title":"A Survey of Mathematical Reasoning in the Era of Multimodal Large Language Model: Benchmark, Method & Challenges","date":"2024-12-16","arxiv_id":"2412.11936","repositories_listed":0,"syntology":null},{"url":null,"slug":"bias-vector-mitigating-biases-in-language","title":"Bias Vector: Mitigating Biases in Language Models with Task Arithmetic Approach","date":"2024-12-16","arxiv_id":"2412.11679","repositories_listed":0,"syntology":null},{"url":null,"slug":"cpath-omni-a-unified-multimodal-foundation","title":"CPath-Omni: A Unified Multimodal Foundation Model for Patch and Whole Slide Image Analysis in Computational Pathology","date":"2024-12-16","arxiv_id":"2412.12077","repositories_listed":0,"syntology":null},{"url":"/paper/efficient-policy-adaptation-with-contrastive-1","slug":"efficient-policy-adaptation-with-contrastive-1","title":"Efficient Policy Adaptation with Contrastive Prompt Ensemble for Embodied Agents","date":"2024-12-16","arxiv_id":"2412.11484","repositories_listed":0,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/efficient-policy-adaptation-with-contrastive-1#ran","syntology_url":"https://syntology.ai/paper/2412.11484","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.11484"}},"official":null}},{"url":null,"slug":"krony-pt-gpt2-compressed-with-kronecker","title":"Krony-PT: GPT2 compressed with Kronecker Products","date":"2024-12-16","arxiv_id":"2412.12351","repositories_listed":0,"syntology":null},{"url":null,"slug":"lmm-regularized-clip-embeddings-for-image","title":"LMM-Regularized CLIP Embeddings for Image Classification","date":"2024-12-16","arxiv_id":"2412.11663","repositories_listed":0,"syntology":null},{"url":null,"slug":"omnivlm-a-token-compressed-sub-billion","title":"OmniVLM: A Token-Compressed, Sub-Billion-Parameter Vision-Language Model for Efficient On-Device Inference","date":"2024-12-16","arxiv_id":"2412.11475","repositories_listed":0,"syntology":null},{"url":null,"slug":"openreviewer-a-specialized-large-language","title":"OpenReviewer: A Specialized Large Language Model for Generating Critical Scientific Paper Reviews","date":"2024-12-16","arxiv_id":"2412.11948","repositories_listed":0,"syntology":null},{"url":null,"slug":"private-yet-social-how-llm-chatbots-support","title":"Private Yet Social: How LLM Chatbots Support and Challenge Eating Disorder Recovery","date":"2024-12-16","arxiv_id":"2412.11656","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-impact-of-token-granularity-on-the","title":"The Impact of Token Granularity on the Predictive Power of Language Model Surprisal","date":"2024-12-16","arxiv_id":"2412.11940","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-a-speech-foundation-model-for","title":"MERaLiON-SpeechEncoder: Towards a Speech Foundation Model for Singapore and Beyond","date":"2024-12-16","arxiv_id":"2412.11538","repositories_listed":0,"syntology":null},{"url":null,"slug":"whisper-gpt-a-hybrid-representation-audio","title":"Whisper-GPT: A Hybrid Representation Audio Large Language Model","date":"2024-12-16","arxiv_id":"2412.11449","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-progressive-transformer-for-unifying-binary","title":"A Progressive Transformer for Unifying Binary Code Embedding and Knowledge Transfer","date":"2024-12-15","arxiv_id":"2412.11177","repositories_listed":0,"syntology":null},{"url":null,"slug":"active-large-language-model-based-knowledge","title":"Active Large Language Model-based Knowledge Distillation for Session-based Recommendation","date":"2024-12-15","arxiv_id":"2502.15685","repositories_listed":0,"syntology":null},{"url":null,"slug":"embracing-large-language-models-in-traffic","title":"Embracing Large Language Models in Traffic Flow Forecasting","date":"2024-12-15","arxiv_id":"2412.12201","repositories_listed":0,"syntology":null},{"url":null,"slug":"finding-a-wolf-in-sheep-s-clothing-combating","title":"Finding a Wolf in Sheep's Clothing: Combating Adversarial Text-To-Image Prompts with Text Summarization","date":"2024-12-15","arxiv_id":"2412.12212","repositories_listed":0,"syntology":null},{"url":null,"slug":"law-legal-agentic-workflows-for-custody-and","title":"LAW: Legal Agentic Workflows for Custody and Fund Services Contracts","date":"2024-12-15","arxiv_id":"2412.11063","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-large-vision-language-model-as","title":"Leveraging Large Vision-Language Model as User Intent-aware Encoder for Composed Image Retrieval","date":"2024-12-15","arxiv_id":"2412.11087","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-vision-and-language-modeling","title":"Bridging Vision and Language: Modeling Causality and Temporality in Video Narratives","date":"2024-12-14","arxiv_id":"2412.10720","repositories_listed":0,"syntology":null},{"url":null,"slug":"inference-scaling-for-bridging-retrieval-and","title":"Inference Scaling for Bridging Retrieval and Augmented Generation","date":"2024-12-14","arxiv_id":"2412.10684","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-vision-language-interactions","title":"Optimizing Vision-Language Interactions Through Decoder-Only Models","date":"2024-12-14","arxiv_id":"2412.10758","repositories_listed":0,"syntology":null},{"url":null,"slug":"superhuman-performance-of-a-large-language","title":"Superhuman performance of a large language model on the reasoning tasks of a physician","date":"2024-12-14","arxiv_id":"2412.10849","repositories_listed":0,"syntology":null},{"url":null,"slug":"wepo-web-element-preference-optimization-for","title":"WEPO: Web Element Preference Optimization for LLM-based Web Navigation","date":"2024-12-14","arxiv_id":"2412.10742","repositories_listed":0,"syntology":null},{"url":null,"slug":"evlm-self-reflective-multimodal-reasoning-for","title":"EVLM: Self-Reflective Multimodal Reasoning for Cross-Dimensional Visual Editing","date":"2024-12-13","arxiv_id":"2412.10566","repositories_listed":0,"syntology":null},{"url":null,"slug":"small-language-model-as-data-prospector-for","title":"Small Language Model as Data Prospector for Large Language Model","date":"2024-12-13","arxiv_id":"2412.09990","repositories_listed":0,"syntology":null},{"url":null,"slug":"solving-the-inverse-alignment-problem-for","title":"Solving the Inverse Alignment Problem for Efficient RLHF","date":"2024-12-13","arxiv_id":"2412.10529","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-if-exploring-branching-narratives-by","title":"WHAT-IF: Exploring Branching Narratives by Meta-Prompting Large Language Models","date":"2024-12-13","arxiv_id":"2412.10582","repositories_listed":0,"syntology":null},{"url":null,"slug":"agenttrek-agent-trajectory-synthesis-via","title":"AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials","date":"2024-12-12","arxiv_id":"2412.09605","repositories_listed":0,"syntology":null}],"record_sha256":"07d7ce48a7214462fcdfd1ea7de4a97233652db6df4c83830d1e7b0ab9d7e66e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}