{"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/76","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":76,"pages_in_order":142,"rows_per_page":100,"rows":[7501,7600],"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/75","next":"/task/language-modeling/papers/77","papers":[{"url":null,"slug":"chattracker-enhancing-visual-tracking","title":"ChatTracker: Enhancing Visual Tracking Performance via Chatting with Multimodal Large Language Model","date":"2024-11-04","arxiv_id":"2411.01756","repositories_listed":0,"syntology":null},{"url":null,"slug":"context-parallelism-for-scalable-million","title":"Context Parallelism for Scalable Million-Token Inference","date":"2024-11-04","arxiv_id":"2411.01783","repositories_listed":0,"syntology":null},{"url":null,"slug":"graphvl-graph-enhanced-semantic-modeling-via","title":"GraphVL: Graph-Enhanced Semantic Modeling via Vision-Language Models for Generalized Class Discovery","date":"2024-11-04","arxiv_id":"2411.02074","repositories_listed":0,"syntology":null},{"url":null,"slug":"kptllm-unveiling-the-power-of-large-language","title":"KptLLM: Unveiling the Power of Large Language Model for Keypoint Comprehension","date":"2024-11-04","arxiv_id":"2411.01846","repositories_listed":0,"syntology":null},{"url":null,"slug":"wave-network-an-ultra-small-language-model","title":"Wave Network: An Ultra-Small Language Model","date":"2024-11-04","arxiv_id":"2411.02674","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-deep-dive-into-large-language-model-code","title":"A Deep Dive Into Large Language Model Code Generation Mistakes: What and Why?","date":"2024-11-03","arxiv_id":"2411.01414","repositories_listed":0,"syntology":null},{"url":null,"slug":"enriching-tabular-data-with-contextual-llm","title":"Enriching Tabular Data with Contextual LLM Embeddings: A Comprehensive Ablation Study for Ensemble Classifiers","date":"2024-11-03","arxiv_id":"2411.01645","repositories_listed":0,"syntology":null},{"url":null,"slug":"high-performance-automated-abstract-screening","title":"High-performance automated abstract screening with large language model ensembles","date":"2024-11-03","arxiv_id":"2411.02451","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-supply-chain-open","title":"Large Language Model Supply Chain: Open Problems From the Security Perspective","date":"2024-11-03","arxiv_id":"2411.01604","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-mechanistic-explanatory-strategy-for-xai","title":"A Mechanistic Explanatory Strategy for XAI","date":"2024-11-02","arxiv_id":"2411.01332","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-humans-oversee-agents-to-prevent-privacy","title":"Privacy Leakage Overshadowed by Views of AI: A Study on Human Oversight of Privacy in Language Model Agent","date":"2024-11-02","arxiv_id":"2411.01344","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-large-language-model-predict-employee","title":"Can Large Language Model Predict Employee Attrition?","date":"2024-11-02","arxiv_id":"2411.01353","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-multimodal-large-language-model-think","title":"Can Multimodal Large Language Model Think Analogically?","date":"2024-11-02","arxiv_id":"2411.01307","repositories_listed":0,"syntology":null},{"url":null,"slug":"interacting-large-language-model-agents","title":"Interacting Large Language Model Agents. Interpretable Models and Social Learning","date":"2024-11-02","arxiv_id":"2411.01271","repositories_listed":0,"syntology":null},{"url":null,"slug":"primo-progressive-induction-for-multi-hop","title":"PRIMO: Progressive Induction for Multi-hop Open Rule Generation","date":"2024-11-02","arxiv_id":"2411.01205","repositories_listed":0,"syntology":null},{"url":null,"slug":"swan-and-arabicmteb-dialect-aware-arabic","title":"Swan and ArabicMTEB: Dialect-Aware, Arabic-Centric, Cross-Lingual, and Cross-Cultural Embedding Models and Benchmarks","date":"2024-11-02","arxiv_id":"2411.01192","repositories_listed":0,"syntology":null},{"url":null,"slug":"adding-error-bars-to-evals-a-statistical","title":"Adding Error Bars to Evals: A Statistical Approach to Language Model Evaluations","date":"2024-11-01","arxiv_id":"2411.00640","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-the-traditional-chinese-medicine","title":"Enhancing the Traditional Chinese Medicine Capabilities of Large Language Model through Reinforcement Learning from AI Feedback","date":"2024-11-01","arxiv_id":"2411.00897","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-few-shot-cross-domain-named-entity","title":"Improving Few-Shot Cross-Domain Named Entity Recognition by Instruction Tuning a Word-Embedding based Retrieval Augmented Large Language Model","date":"2024-11-01","arxiv_id":"2411.00451","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-kt-a-versatile-framework-for-knowledge","title":"LLM-KT: A Versatile Framework for Knowledge Transfer from Large Language Models to Collaborative Filtering","date":"2024-11-01","arxiv_id":"2411.00556","repositories_listed":0,"syntology":null},{"url":null,"slug":"radflag-a-black-box-hallucination-detection","title":"RadFlag: A Black-Box Hallucination Detection Method for Medical Vision Language Models","date":"2024-11-01","arxiv_id":"2411.00299","repositories_listed":0,"syntology":null},{"url":null,"slug":"respact-harmonizing-reasoning-speaking-and","title":"ReSpAct: Harmonizing Reasoning, Speaking, and Acting Towards Building Large Language Model-Based Conversational AI Agents","date":"2024-11-01","arxiv_id":"2411.00927","repositories_listed":0,"syntology":null},{"url":null,"slug":"unified-generative-and-discriminative","title":"Unified Generative and Discriminative Training for Multi-modal Large Language Models","date":"2024-11-01","arxiv_id":"2411.00304","repositories_listed":0,"syntology":null},{"url":null,"slug":"alise-accelerating-large-language-model","title":"ALISE: Accelerating Large Language Model Serving with Speculative Scheduling","date":"2024-10-31","arxiv_id":"2410.23537","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-label-attention-transparency-in","title":"Beyond Label Attention: Transparency in Language Models for Automated Medical Coding via Dictionary Learning","date":"2024-10-31","arxiv_id":"2411.00173","repositories_listed":0,"syntology":null},{"url":null,"slug":"derec-simpro-unlock-language-model-benefits","title":"DEREC-SIMPRO: unlock Language Model benefits to advance Synthesis in Data Clean Room","date":"2024-10-31","arxiv_id":"2411.00879","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-context-to-action-analysis-of-the-impact","title":"From Context to Action: Analysis of the Impact of State Representation and Context on the Generalization of Multi-Turn Web Navigation Agents","date":"2024-10-31","arxiv_id":"2410.23555","repositories_listed":0,"syntology":null},{"url":"/paper/matchmaker-self-improving-large-language","slug":"matchmaker-self-improving-large-language","title":"Matchmaker: Self-Improving Large Language Model Programs for Schema Matching","date":"2024-10-31","arxiv_id":"2410.24105","repositories_listed":0,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"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) · 2 unverified","sample_list":"/paper/matchmaker-self-improving-large-language#ran","syntology_url":"https://syntology.ai/paper/2410.24105","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.24105"}},"official":null}},{"url":null,"slug":"mess-energy-optimal-inferencing-in-language","title":"MESS+: Energy-Optimal Inferencing in Language Model Zoos with Service Level Guarantees","date":"2024-10-31","arxiv_id":"2411.00889","repositories_listed":0,"syntology":null},{"url":null,"slug":"morphological-typology-in-bpe-subword","title":"Morphological Typology in BPE Subword Productivity and Language Modeling","date":"2024-10-31","arxiv_id":"2410.23656","repositories_listed":0,"syntology":null},{"url":null,"slug":"p-0-a-vision-language-action-flow-model-for","title":"$π_0$: A Vision-Language-Action Flow Model for General Robot Control","date":"2024-10-31","arxiv_id":"2410.24164","repositories_listed":0,"syntology":null},{"url":null,"slug":"representative-social-choice-from-learning","title":"Representative Social Choice: From Learning Theory to AI Alignment","date":"2024-10-31","arxiv_id":"2410.23953","repositories_listed":0,"syntology":null},{"url":null,"slug":"schema-augmentation-for-zero-shot-domain","title":"Schema Augmentation for Zero-Shot Domain Adaptation in Dialogue State Tracking","date":"2024-10-31","arxiv_id":"2411.00150","repositories_listed":0,"syntology":null},{"url":null,"slug":"stereo-talker-audio-driven-3d-human-synthesis","title":"Stereo-Talker: Audio-driven 3D Human Synthesis with Prior-Guided Mixture-of-Experts","date":"2024-10-31","arxiv_id":"2410.23836","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-npu-hwc-system-for-the-iscslp-2024","title":"The NPU-HWC System for the ISCSLP 2024 Inspirational and Convincing Audio Generation Challenge","date":"2024-10-31","arxiv_id":"2410.23815","repositories_listed":0,"syntology":null},{"url":null,"slug":"thought-space-explorer-navigating-and","title":"Thought Space Explorer: Navigating and Expanding Thought Space for Large Language Model Reasoning","date":"2024-10-31","arxiv_id":"2410.24155","repositories_listed":0,"syntology":null},{"url":null,"slug":"web-scale-visual-entity-recognition-an-llm","title":"Web-Scale Visual Entity Recognition: An LLM-Driven Data Approach","date":"2024-10-31","arxiv_id":"2410.23676","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-monte-carlo-framework-for-calibrated","title":"A Monte Carlo Framework for Calibrated Uncertainty Estimation in Sequence Prediction","date":"2024-10-30","arxiv_id":"2410.23272","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-theoretical-perspective-for-speculative","title":"A Theoretical Perspective for Speculative Decoding Algorithm","date":"2024-10-30","arxiv_id":"2411.00841","repositories_listed":0,"syntology":null},{"url":null,"slug":"all-or-none-identifiable-linear-properties-of","title":"All or None: Identifiable Linear Properties of Next-token Predictors in Language Modeling","date":"2024-10-30","arxiv_id":"2410.23501","repositories_listed":0,"syntology":null},{"url":null,"slug":"constructing-multimodal-datasets-from-scratch","title":"Constructing Multimodal Datasets from Scratch for Rapid Development of a Japanese Visual Language Model","date":"2024-10-30","arxiv_id":"2410.22736","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-information-sub-selection-for","title":"Dynamic Information Sub-Selection for Decision Support","date":"2024-10-30","arxiv_id":"2410.23423","repositories_listed":0,"syntology":null},{"url":null,"slug":"explainable-behavior-cloning-teaching-large","title":"Explainable Behavior Cloning: Teaching Large Language Model Agents through Learning by Demonstration","date":"2024-10-30","arxiv_id":"2410.22916","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-and-transferring-sparse-contextual","title":"Learning and Transferring Sparse Contextual Bigrams with Linear Transformers","date":"2024-10-30","arxiv_id":"2410.23438","repositories_listed":0,"syntology":null},{"url":null,"slug":"prove-your-point-bringing-proof-enhancement","title":"Prove Your Point!: Bringing Proof-Enhancement Principles to Argumentative Essay Generation","date":"2024-10-30","arxiv_id":"2410.22642","repositories_listed":0,"syntology":null},{"url":null,"slug":"robotic-state-recognition-with-image-to-text","title":"Robotic State Recognition with Image-to-Text Retrieval Task of Pre-Trained Vision-Language Model and Black-Box Optimization","date":"2024-10-30","arxiv_id":"2410.22707","repositories_listed":0,"syntology":null},{"url":null,"slug":"smaller-large-language-models-can-do-moral","title":"Smaller Large Language Models Can Do Moral Self-Correction","date":"2024-10-30","arxiv_id":"2410.23496","repositories_listed":0,"syntology":null},{"url":null,"slug":"teaching-a-language-model-to-distinguish","title":"Teaching a Language Model to Distinguish Between Similar Details using a Small Adversarial Training Set","date":"2024-10-30","arxiv_id":"2410.23118","repositories_listed":0,"syntology":null},{"url":"/paper/toward-understanding-in-context-vs-in-weight","slug":"toward-understanding-in-context-vs-in-weight","title":"Toward Understanding In-context vs. In-weight Learning","date":"2024-10-30","arxiv_id":"2410.23042","repositories_listed":0,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":12,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/toward-understanding-in-context-vs-in-weight#ran","syntology_url":"https://syntology.ai/paper/2410.23042","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.23042"}},"official":null}},{"url":null,"slug":"visualpredicator-learning-abstract-world","title":"VisualPredicator: Learning Abstract World Models with Neuro-Symbolic Predicates for Robot Planning","date":"2024-10-30","arxiv_id":"2410.23156","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-hierarchical-language-model-for","title":"A Hierarchical Language Model For Interpretable Graph Reasoning","date":"2024-10-29","arxiv_id":"2410.22372","repositories_listed":0,"syntology":null},{"url":"/paper/abrupt-learning-in-transformers-a-case-study","slug":"abrupt-learning-in-transformers-a-case-study","title":"Abrupt Learning in Transformers: A Case Study on Matrix Completion","date":"2024-10-29","arxiv_id":"2410.22244","repositories_listed":0,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/abrupt-learning-in-transformers-a-case-study#ran","syntology_url":"https://syntology.ai/paper/2410.22244","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.22244"}},"official":null}},{"url":null,"slug":"anticipating-future-with-large-language-model","title":"Anticipating Future with Large Language Model for Simultaneous Machine Translation","date":"2024-10-29","arxiv_id":"2410.22499","repositories_listed":0,"syntology":null},{"url":null,"slug":"auto-intent-automated-intent-discovery-and","title":"Auto-Intent: Automated Intent Discovery and Self-Exploration for Large Language Model Web Agents","date":"2024-10-29","arxiv_id":"2410.22552","repositories_listed":0,"syntology":null},{"url":null,"slug":"curategpt-a-flexible-language-model-assisted","title":"CurateGPT: A flexible language-model assisted biocuration tool","date":"2024-10-29","arxiv_id":"2411.00046","repositories_listed":0,"syntology":null},{"url":null,"slug":"democratizing-reward-design-for-personal-and","title":"Democratizing Reward Design for Personal and Representative Value-Alignment","date":"2024-10-29","arxiv_id":"2410.22203","repositories_listed":0,"syntology":null},{"url":null,"slug":"discrete-modeling-via-boundary-conditional","title":"Discrete Modeling via Boundary Conditional Diffusion Processes","date":"2024-10-29","arxiv_id":"2410.22380","repositories_listed":0,"syntology":null},{"url":null,"slug":"factbench-a-dynamic-benchmark-for-in-the-wild","title":"FactBench: A Dynamic Benchmark for In-the-Wild Language Model Factuality Evaluation","date":"2024-10-29","arxiv_id":"2410.22257","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-melodic-note-sequences-to-pitches-using","title":"From melodic note sequences to pitches using word2vec","date":"2024-10-29","arxiv_id":"2410.22285","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-and-unlearning-of-fabricated","title":"Learning and Unlearning of Fabricated Knowledge in Language Models","date":"2024-10-29","arxiv_id":"2410.21750","repositories_listed":0,"syntology":null},{"url":null,"slug":"marco-multi-agent-real-time-chat","title":"MARCO: Multi-Agent Real-time Chat Orchestration","date":"2024-10-29","arxiv_id":"2410.21784","repositories_listed":0,"syntology":null},{"url":null,"slug":"motiongpt-2-a-general-purpose-motion-language","title":"MotionGPT-2: A General-Purpose Motion-Language Model for Motion Generation and Understanding","date":"2024-10-29","arxiv_id":"2410.21747","repositories_listed":0,"syntology":null},{"url":null,"slug":"reliable-semantic-understanding-for-real","title":"Reliable Semantic Understanding for Real World Zero-shot Object Goal Navigation","date":"2024-10-29","arxiv_id":"2410.21926","repositories_listed":0,"syntology":null},{"url":null,"slug":"vl-cache-sparsity-and-modality-aware-kv-cache","title":"VL-Cache: Sparsity and Modality-Aware KV Cache Compression for Vision-Language Model Inference Acceleration","date":"2024-10-29","arxiv_id":"2410.23317","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-actor-critic-approach-to-boosting-text-to","title":"An Actor-Critic Approach to Boosting Text-to-SQL Large Language Model","date":"2024-10-28","arxiv_id":"2410.22082","repositories_listed":0,"syntology":null},{"url":null,"slug":"bongllama-llama-for-bangla-language","title":"BongLLaMA: LLaMA for Bangla Language","date":"2024-10-28","arxiv_id":"2410.21200","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-machines-think-like-humans-a-behavioral","title":"Can Machines Think Like Humans? A Behavioral Evaluation of LLM-Agents in Dictator Games","date":"2024-10-28","arxiv_id":"2410.21359","repositories_listed":0,"syntology":null},{"url":null,"slug":"electionsim-massive-population-election","title":"ElectionSim: Massive Population Election Simulation Powered by Large Language Model Driven Agents","date":"2024-10-28","arxiv_id":"2410.20746","repositories_listed":0,"syntology":null},{"url":"/paper/energy-based-diffusion-language-models-for","slug":"energy-based-diffusion-language-models-for","title":"Energy-Based Diffusion Language Models for Text Generation","date":"2024-10-28","arxiv_id":"2410.21357","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-knowledge-graph-construction","title":"Hierarchical Knowledge Graph Construction from Images for Scalable E-Commerce","date":"2024-10-28","arxiv_id":"2410.21237","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-assisted-speech-and","title":"Large Language Model-assisted Speech and Pointing Benefits Multiple 3D Object Selection in Virtual Reality","date":"2024-10-28","arxiv_id":"2410.21091","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-benchmarks-in-medical","title":"Large Language Model Benchmarks in Medical Tasks","date":"2024-10-28","arxiv_id":"2410.21348","repositories_listed":0,"syntology":null},{"url":null,"slug":"pepdora-a-unified-peptide-language-model-via","title":"PepDoRA: A Unified Peptide Language Model via Weight-Decomposed Low-Rank Adaptation","date":"2024-10-28","arxiv_id":"2410.20667","repositories_listed":0,"syntology":null},{"url":null,"slug":"rephrasing-natural-text-data-with-different","title":"Rephrasing natural text data with different languages and quality levels for Large Language Model pre-training","date":"2024-10-28","arxiv_id":"2410.20796","repositories_listed":0,"syntology":null},{"url":null,"slug":"stealthy-jailbreak-attacks-on-large-language","title":"Stealthy Jailbreak Attacks on Large Language Models via Benign Data Mirroring","date":"2024-10-28","arxiv_id":"2410.21083","repositories_listed":0,"syntology":null},{"url":null,"slug":"visualizing-attention-zones-in-machine","title":"Visualizing attention zones in machine reading comprehension models","date":"2024-10-28","arxiv_id":"2410.20652","repositories_listed":0,"syntology":null},{"url":null,"slug":"inevitable-trade-off-between-watermark","title":"Inevitable Trade-off between Watermark Strength and Speculative Sampling Efficiency for Language Models","date":"2024-10-27","arxiv_id":"2410.20418","repositories_listed":0,"syntology":null},{"url":null,"slug":"medgo-a-chinese-medical-large-language-model","title":"MedGo: A Chinese Medical Large Language Model","date":"2024-10-27","arxiv_id":"2410.20428","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-data-synthesis-a-teacher-model","title":"Rethinking Data Synthesis: A Teacher Model Training Recipe with Interpretation","date":"2024-10-27","arxiv_id":"2410.20362","repositories_listed":0,"syntology":null},{"url":null,"slug":"autonomous-building-cyber-physical-systems","title":"Autonomous Building Cyber-Physical Systems Using Decentralized Autonomous Organizations, Digital Twins, and Large Language Model","date":"2024-10-25","arxiv_id":"2410.19262","repositories_listed":0,"syntology":null},{"url":null,"slug":"computational-bottlenecks-of-training-small","title":"Computational Bottlenecks of Training Small-scale Large Language Models","date":"2024-10-25","arxiv_id":"2410.19456","repositories_listed":0,"syntology":null},{"url":null,"slug":"ippon-common-sense-guided-informative-path","title":"IPPON: Common Sense Guided Informative Path Planning for Object Goal Navigation","date":"2024-10-25","arxiv_id":"2410.19697","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-little-help-goes-a-long-way-efficient-llm","title":"A Little Help Goes a Long Way: Efficient LLM Training by Leveraging Small LMs","date":"2024-10-24","arxiv_id":"2410.18779","repositories_listed":0,"syntology":null},{"url":null,"slug":"aligncap-aligning-speech-emotion-captioning","title":"AlignCap: Aligning Speech Emotion Captioning to Human Preferences","date":"2024-10-24","arxiv_id":"2410.19134","repositories_listed":0,"syntology":null},{"url":null,"slug":"bielik-7b-v0-1-a-polish-language-model","title":"Bielik 7B v0.1: A Polish Language Model -- Development, Insights, and Evaluation","date":"2024-10-24","arxiv_id":"2410.18565","repositories_listed":0,"syntology":null},{"url":null,"slug":"fedbaf-federated-learning-aggregation-biased","title":"FedBaF: Federated Learning Aggregation Biased by a Foundation Model","date":"2024-10-24","arxiv_id":"2410.18352","repositories_listed":0,"syntology":null},{"url":null,"slug":"ferret-ui-2-mastering-universal-user","title":"Ferret-UI 2: Mastering Universal User Interface Understanding Across Platforms","date":"2024-10-24","arxiv_id":"2410.18967","repositories_listed":0,"syntology":null},{"url":null,"slug":"interpretable-bilingual-multimodal-large","title":"Interpretable Bilingual Multimodal Large Language Model for Diverse Biomedical Tasks","date":"2024-10-24","arxiv_id":"2410.18387","repositories_listed":0,"syntology":null},{"url":null,"slug":"provably-robust-watermarks-for-open-source","title":"Provably Robust Watermarks for Open-Source Language Models","date":"2024-10-24","arxiv_id":"2410.18861","repositories_listed":0,"syntology":null},{"url":"/paper/structure-language-models-for-protein","slug":"structure-language-models-for-protein","title":"Structure Language Models for Protein Conformation Generation","date":"2024-10-24","arxiv_id":"2410.18403","repositories_listed":0,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":11,"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) · 3 unverified","sample_list":"/paper/structure-language-models-for-protein#ran","syntology_url":"https://syntology.ai/paper/2410.18403","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.18403"}},"official":null}},{"url":null,"slug":"taipan-efficient-and-expressive-state-space","title":"Taipan: Efficient and Expressive State Space Language Models with Selective Attention","date":"2024-10-24","arxiv_id":"2410.18572","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-object-navigation-with-vision","title":"Zero-shot Object Navigation with Vision-Language Models Reasoning","date":"2024-10-24","arxiv_id":"2410.18570","repositories_listed":0,"syntology":null},{"url":null,"slug":"coreinfer-accelerating-large-language-model","title":"CoreInfer: Accelerating Large Language Model Inference with Semantics-Inspired Adaptive Sparse Activation","date":"2024-10-23","arxiv_id":"2410.18311","repositories_listed":0,"syntology":null},{"url":null,"slug":"lego-language-model-building-blocks","title":"LEGO: Language Model Building Blocks","date":"2024-10-23","arxiv_id":"2410.18287","repositories_listed":0,"syntology":null},{"url":null,"slug":"lightweight-neural-app-control","title":"Lightweight Neural App Control","date":"2024-10-23","arxiv_id":"2410.17883","repositories_listed":0,"syntology":null},{"url":null,"slug":"lmlpa-language-model-linguistic-personality","title":"LMLPA: Language Model Linguistic Personality Assessment","date":"2024-10-23","arxiv_id":"2410.17632","repositories_listed":0,"syntology":null},{"url":null,"slug":"mojobench-language-modeling-and-benchmarks","title":"MojoBench: Language Modeling and Benchmarks for Mojo","date":"2024-10-23","arxiv_id":"2410.17736","repositories_listed":0,"syntology":null},{"url":null,"slug":"chatting-with-bots-ai-speech-acts-and-the","title":"Chatting with Bots: AI, Speech Acts, and the Edge of Assertion","date":"2024-10-22","arxiv_id":"2410.16645","repositories_listed":0,"syntology":null},{"url":null,"slug":"dellirium-a-large-language-model-for-delirium","title":"DeLLiriuM: A large language model for delirium prediction in the ICU using structured EHR","date":"2024-10-22","arxiv_id":"2410.17363","repositories_listed":0,"syntology":null},{"url":null,"slug":"diri-adversarial-patient-reidentification","title":"DIRI: Adversarial Patient Reidentification with Large Language Models for Evaluating Clinical Text Anonymization","date":"2024-10-22","arxiv_id":"2410.17035","repositories_listed":0,"syntology":null}],"record_sha256":"fb6aeea9a260a143bdf03b6bb522db6b4de1083cb8875ed51cf0bea903e45c28","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}