{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/language-modelling/papers/104","list_of":"/task/language-modelling","task":"Language Modelling","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":104,"pages_in_order":177,"rows_per_page":100,"rows":[10301,10400],"of":17610,"counts":{"archive_papers_tagged":17610,"with_a_code_link":7012,"where_syntology_ran_a_sample":2428,"not_listed_spam_title":0,"listed":17610,"listed_where_code_ran":2428,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2027,"every_run_a_failure_of_syntologys_instrument":401,"listed_with_a_run_with_no_instrument_failure":2027,"listed_every_run_a_failure_of_syntologys_instrument":401,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/language-modelling","prev":"/task/language-modelling/papers/103","next":"/task/language-modelling/papers/105","papers":[{"url":null,"slug":"large-language-model-guided-document","title":"Large Language Model-guided Document Selection","date":"2024-06-07","arxiv_id":"2406.04638","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-poet-evolving-complex-environments-using","title":"LLM-POET: Evolving Complex Environments using Large Language Models","date":"2024-06-07","arxiv_id":"2406.04663","repositories_listed":0,"syntology":null},{"url":null,"slug":"matter-memory-augmented-transformer-using","title":"MATTER: Memory-Augmented Transformer Using Heterogeneous Knowledge Sources","date":"2024-06-07","arxiv_id":"2406.04670","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantifying-geospatial-in-the-common-crawl","title":"Quantifying Geospatial in the Common Crawl Corpus","date":"2024-06-07","arxiv_id":"2406.04952","repositories_listed":0,"syntology":null},{"url":null,"slug":"sales-whisperer-a-human-inconspicuous-attack","title":"LLM Whisperer: An Inconspicuous Attack to Bias LLM Responses","date":"2024-06-07","arxiv_id":"2406.04755","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-aware-learning-for-language-model","title":"Uncertainty Aware Learning for Language Model Alignment","date":"2024-06-07","arxiv_id":"2406.04854","repositories_listed":0,"syntology":null},{"url":null,"slug":"are-large-language-models-the-new-interface","title":"Are Large Language Models the New Interface for Data Pipelines?","date":"2024-06-06","arxiv_id":"2406.06596","repositories_listed":0,"syntology":null},{"url":null,"slug":"bindgpt-a-scalable-framework-for-3d-molecular","title":"BindGPT: A Scalable Framework for 3D Molecular Design via Language Modeling and Reinforcement Learning","date":"2024-06-06","arxiv_id":"2406.03686","repositories_listed":0,"syntology":null},{"url":null,"slug":"confabulation-the-surprising-value-of-large","title":"Confabulation: The Surprising Value of Large Language Model Hallucinations","date":"2024-06-06","arxiv_id":"2406.04175","repositories_listed":0,"syntology":null},{"url":"/paper/deepstack-deeply-stacking-visual-tokens-is","slug":"deepstack-deeply-stacking-visual-tokens-is","title":"DeepStack: Deeply Stacking Visual Tokens is Surprisingly Simple and Effective for LMMs","date":"2024-06-06","arxiv_id":"2406.04334","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-audio-codec-based-zero-shot-text-to","title":"Improving Audio Codec-based Zero-Shot Text-to-Speech Synthesis with Multi-Modal Context and Large Language Model","date":"2024-06-06","arxiv_id":"2406.03706","repositories_listed":0,"syntology":null},{"url":null,"slug":"llplace-the-3d-indoor-scene-layout-generation","title":"LLplace: The 3D Indoor Scene Layout Generation and Editing via Large Language Model","date":"2024-06-06","arxiv_id":"2406.03866","repositories_listed":0,"syntology":null},{"url":null,"slug":"stratified-prediction-powered-inference-for","title":"Stratified Prediction-Powered Inference for Hybrid Language Model Evaluation","date":"2024-06-06","arxiv_id":"2406.04291","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-understanding-task-agnostic-debiasing","title":"Towards Understanding Task-agnostic Debiasing Through the Lenses of Intrinsic Bias and Forgetfulness","date":"2024-06-06","arxiv_id":"2406.04146","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-languages-are-easy-to-language-model-a","title":"What Languages are Easy to Language-Model? A Perspective from Learning Probabilistic Regular Languages","date":"2024-06-06","arxiv_id":"2406.04289","repositories_listed":0,"syntology":null},{"url":null,"slug":"does-your-data-spark-joy-performance-gains","title":"Does your data spark joy? Performance gains from domain upsampling at the end of training","date":"2024-06-05","arxiv_id":"2406.03476","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-robustness-in-doctor-patient","title":"Exploring Robustness in Doctor-Patient Conversation Summarization: An Analysis of Out-of-Domain SOAP Notes","date":"2024-06-05","arxiv_id":"2406.02826","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-tarzan-to-tolkien-controlling-the","title":"From Tarzan to Tolkien: Controlling the Language Proficiency Level of LLMs for Content Generation","date":"2024-06-05","arxiv_id":"2406.03030","repositories_listed":0,"syntology":null},{"url":null,"slug":"item-language-model-for-conversational","title":"Item-Language Model for Conversational Recommendation","date":"2024-06-05","arxiv_id":"2406.02844","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-infused-legal-wisdom-navigating-llm","title":"Knowledge-Infused Legal Wisdom: Navigating LLM Consultation through the Lens of Diagnostics and Positive-Unlabeled Reinforcement Learning","date":"2024-06-05","arxiv_id":"2406.03600","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-model-can-do-knowledge-tracing","title":"Language Model Can Do Knowledge Tracing: Simple but Effective Method to Integrate Language Model and Knowledge Tracing Task","date":"2024-06-05","arxiv_id":"2406.02893","repositories_listed":0,"syntology":null},{"url":null,"slug":"plad-preference-based-large-language-model","title":"PLaD: Preference-based Large Language Model Distillation with Pseudo-Preference Pairs","date":"2024-06-05","arxiv_id":"2406.02886","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompt-based-visual-alignment-for-zero-shot","title":"Prompt-based Visual Alignment for Zero-shot Policy Transfer","date":"2024-06-05","arxiv_id":"2406.03250","repositories_listed":0,"syntology":null},{"url":null,"slug":"radbartsum-domain-specific-adaption-of","title":"RadBARTsum: Domain Specific Adaption of Denoising Sequence-to-Sequence Models for Abstractive Radiology Report Summarization","date":"2024-06-05","arxiv_id":"2406.03062","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-task-oriented-queries-benchmark-toqb","title":"The Task-oriented Queries Benchmark (ToQB)","date":"2024-06-05","arxiv_id":"2406.02943","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-independence-promoting-loss-for-music","title":"An Independence-promoting Loss for Music Generation with Language Models","date":"2024-06-04","arxiv_id":"2406.02315","repositories_listed":0,"syntology":null},{"url":null,"slug":"assessing-the-performance-of-chinese-open","title":"Assessing the Performance of Chinese Open Source Large Language Models in Information Extraction Tasks","date":"2024-06-04","arxiv_id":"2406.02079","repositories_listed":0,"syntology":null},{"url":null,"slug":"discrete-multimodal-transformers-with-a","title":"Discrete Multimodal Transformers with a Pretrained Large Language Model for Mixed-Supervision Speech Processing","date":"2024-06-04","arxiv_id":"2406.06582","repositories_listed":0,"syntology":null},{"url":null,"slug":"disentangling-logic-the-role-of-context-in","title":"Disentangling Logic: The Role of Context in Large Language Model Reasoning Capabilities","date":"2024-06-04","arxiv_id":"2406.02787","repositories_listed":0,"syntology":null},{"url":null,"slug":"diver-large-language-model-decoding-with-span","title":"Diver: Large Language Model Decoding with Span-Level Mutual Information Verification","date":"2024-06-04","arxiv_id":"2406.02120","repositories_listed":0,"syntology":null},{"url":null,"slug":"dreureka-language-model-guided-sim-to-real","title":"DrEureka: Language Model Guided Sim-To-Real Transfer","date":"2024-06-04","arxiv_id":"2406.01967","repositories_listed":0,"syntology":null},{"url":null,"slug":"edit-distance-robust-watermarks-for-language","title":"Edit Distance Robust Watermarks via Indexing Pseudorandom Codes","date":"2024-06-04","arxiv_id":"2406.02633","repositories_listed":0,"syntology":null},{"url":null,"slug":"honeygpt-breaking-the-trilemma-in-terminal","title":"HoneyGPT: Breaking the Trilemma in Terminal Honeypots with Large Language Model","date":"2024-06-04","arxiv_id":"2406.01882","repositories_listed":0,"syntology":null},{"url":null,"slug":"hpe-cogvlm-new-head-pose-grounding-task","title":"HPE-CogVLM: Advancing Vision Language Models with a Head Pose Grounding Task","date":"2024-06-04","arxiv_id":"2406.01914","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-enabled-multi-agent","title":"Large Language Model-Enabled Multi-Agent Manufacturing Systems","date":"2024-06-04","arxiv_id":"2406.01893","repositories_listed":0,"syntology":null},{"url":null,"slug":"longssm-on-the-length-extension-of-state","title":"LongSSM: On the Length Extension of State-space Models in Language Modelling","date":"2024-06-04","arxiv_id":"2406.02080","repositories_listed":0,"syntology":null},{"url":null,"slug":"masksr-masked-language-model-for-full-band","title":"MaskSR: Masked Language Model for Full-band Speech Restoration","date":"2024-06-04","arxiv_id":"2406.02092","repositories_listed":0,"syntology":null},{"url":null,"slug":"meta-designing-quantum-experiments-with","title":"Meta-Designing Quantum Experiments with Language Models","date":"2024-06-04","arxiv_id":"2406.02470","repositories_listed":0,"syntology":null},{"url":null,"slug":"occamllm-fast-and-exact-language-model","title":"OccamLLM: Fast and Exact Language Model Arithmetic in a Single Step","date":"2024-06-04","arxiv_id":"2406.06576","repositories_listed":0,"syntology":null},{"url":null,"slug":"phonetic-enhanced-language-modeling-for-text","title":"Phonetic Enhanced Language Modeling for Text-to-Speech Synthesis","date":"2024-06-04","arxiv_id":"2406.02009","repositories_listed":0,"syntology":null},{"url":null,"slug":"radar-spectra-language-model-for-automotive","title":"Radar Spectra-Language Model for Automotive Scene Parsing","date":"2024-06-04","arxiv_id":"2406.02158","repositories_listed":0,"syntology":null},{"url":null,"slug":"rkld-reverse-kl-divergence-based-knowledge","title":"RKLD: Reverse KL-Divergence-based Knowledge Distillation for Unlearning Personal Information in Large Language Models","date":"2024-06-04","arxiv_id":"2406.01983","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-singing-voice-pre-training","title":"Self-Supervised Singing Voice Pre-Training towards Speech-to-Singing Conversion","date":"2024-06-04","arxiv_id":"2406.02429","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-effective-time-aware-language","title":"Towards Effective Time-Aware Language Representation: Exploring Enhanced Temporal Understanding in Language Models","date":"2024-06-04","arxiv_id":"2406.01863","repositories_listed":0,"syntology":null},{"url":null,"slug":"why-would-you-suggest-that-human-trust-in","title":"Why Would You Suggest That? Human Trust in Language Model Responses","date":"2024-06-04","arxiv_id":"2406.02018","repositories_listed":0,"syntology":null},{"url":null,"slug":"asynchronous-multi-server-federated-learning","title":"Asynchronous Multi-Server Federated Learning for Geo-Distributed Clients","date":"2024-06-03","arxiv_id":"2406.01439","repositories_listed":0,"syntology":null},{"url":null,"slug":"ed-sam-an-efficient-diffusion-sampling","title":"ED-SAM: An Efficient Diffusion Sampling Approach to Domain Generalization in Vision-Language Foundation Models","date":"2024-06-03","arxiv_id":"2406.01432","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-neural-network-enhanced-retrieval-for","title":"Graph Neural Network Enhanced Retrieval for Question Answering of LLMs","date":"2024-06-03","arxiv_id":"2406.06572","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-to-understand-whole-software-repository","title":"Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Exploration","date":"2024-06-03","arxiv_id":"2406.01422","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-assisted-optimal-bidding","title":"Large Language Model Assisted Optimal Bidding of BESS in FCAS Market: An AI-agent based Approach","date":"2024-06-03","arxiv_id":"2406.00974","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-and-gnn-are-complementary-distilling-llm","title":"LLM and GNN are Complementary: Distilling LLM for Multimodal Graph Learning","date":"2024-06-03","arxiv_id":"2406.01032","repositories_listed":0,"syntology":null},{"url":null,"slug":"luna-an-evaluation-foundation-model-to-catch","title":"Luna: An Evaluation Foundation Model to Catch Language Model Hallucinations with High Accuracy and Low Cost","date":"2024-06-03","arxiv_id":"2406.00975","repositories_listed":0,"syntology":null},{"url":null,"slug":"olora-orthonormal-low-rank-adaptation-of","title":"OLoRA: Orthonormal Low-Rank Adaptation of Large Language Models","date":"2024-06-03","arxiv_id":"2406.01775","repositories_listed":0,"syntology":null},{"url":null,"slug":"revolutionizing-large-language-model-training","title":"SwitchLoRA: Switched Low-Rank Adaptation Can Learn Full-Rank Information","date":"2024-06-03","arxiv_id":"2406.06564","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-ensembling-for-mitigating-reward","title":"Scalable Ensembling For Mitigating Reward Overoptimisation","date":"2024-06-03","arxiv_id":"2406.01013","repositories_listed":0,"syntology":null},{"url":null,"slug":"superhuman-performance-in-urology-board","title":"Superhuman performance in urology board questions by an explainable large language model enabled for context integration of the European Association of Urology guidelines: the UroBot study","date":"2024-06-03","arxiv_id":"2406.01428","repositories_listed":0,"syntology":null},{"url":null,"slug":"synergizing-unsupervised-and-supervised","title":"Synergizing Unsupervised and Supervised Learning: A Hybrid Approach for Accurate Natural Language Task Modeling","date":"2024-06-03","arxiv_id":"2406.01096","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-token-probability-encoding-in","title":"Understanding Token Probability Encoding in Output Embeddings","date":"2024-06-03","arxiv_id":"2406.01468","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-distractor-generation-via-large","title":"Unsupervised Distractor Generation via Large Language Model Distilling and Counterfactual Contrastive Decoding","date":"2024-06-03","arxiv_id":"2406.01306","repositories_listed":0,"syntology":null},{"url":null,"slug":"distortion-free-watermarks-are-not-truly","title":"Distortion-free Watermarks are not Truly Distortion-free under Watermark Key Collisions","date":"2024-06-02","arxiv_id":"2406.02603","repositories_listed":0,"syntology":null},{"url":null,"slug":"focus-forging-originality-through-contrastive","title":"FOCUS: Forging Originality through Contrastive Use in Self-Plagiarism for Language Models","date":"2024-06-02","arxiv_id":"2406.00839","repositories_listed":0,"syntology":null},{"url":null,"slug":"harnessing-business-and-media-insights-with","title":"Harnessing Business and Media Insights with Large Language Models","date":"2024-06-02","arxiv_id":"2406.06559","repositories_listed":0,"syntology":null},{"url":null,"slug":"longskywork-a-training-recipe-for-efficiently","title":"LongSkywork: A Training Recipe for Efficiently Extending Context Length in Large Language Models","date":"2024-06-02","arxiv_id":"2406.00605","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-a-copilot-in-bim-authoring-tool-using","title":"Towards a copilot in BIM authoring tool using a large language model-based agent for intelligent human-machine interaction","date":"2024-06-02","arxiv_id":"2406.16903","repositories_listed":0,"syntology":null},{"url":null,"slug":"controlling-large-language-model-agents-with","title":"Controlling Large Language Model Agents with Entropic Activation Steering","date":"2024-06-01","arxiv_id":"2406.00244","repositories_listed":0,"syntology":null},{"url":null,"slug":"henasy-learning-to-assemble-scene-entities","title":"HENASY: Learning to Assemble Scene-Entities for Egocentric Video-Language Model","date":"2024-06-01","arxiv_id":"2406.00307","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-confidence-estimation","title":"Large Language Model Confidence Estimation via Black-Box Access","date":"2024-06-01","arxiv_id":"2406.04370","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-overcoming-miscalibrated-conversational","title":"On Overcoming Miscalibrated Conversational Priors in LLM-based Chatbots","date":"2024-06-01","arxiv_id":"2406.01633","repositories_listed":0,"syntology":null},{"url":null,"slug":"wav2prompt-end-to-end-speech-prompt","title":"Wav2Prompt: End-to-End Speech Prompt Generation and Tuning For LLM in Zero and Few-shot Learning","date":"2024-06-01","arxiv_id":"2406.00522","repositories_listed":0,"syntology":null},{"url":null,"slug":"dyna-disease-specific-language-model-for","title":"DYNA: Disease-Specific Language Model for Variant Pathogenicity","date":"2024-05-31","arxiv_id":"2406.00164","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploratory-preference-optimization","title":"Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF","date":"2024-05-31","arxiv_id":"2405.21046","repositories_listed":0,"syntology":null},{"url":null,"slug":"fineradscore-a-radiology-report-line-by-line","title":"FineRadScore: A Radiology Report Line-by-Line Evaluation Technique Generating Corrections with Severity Scores","date":"2024-05-31","arxiv_id":"2405.20613","repositories_listed":0,"syntology":null},{"url":null,"slug":"kaleido-diffusion-improving-conditional","title":"Kaleido Diffusion: Improving Conditional Diffusion Models with Autoregressive Latent Modeling","date":"2024-05-31","arxiv_id":"2405.21048","repositories_listed":0,"syntology":null},{"url":null,"slug":"lolameme-logic-language-memory-mechanistic","title":"LOLAMEME: Logic, Language, Memory, Mechanistic Framework","date":"2024-05-31","arxiv_id":"2406.02592","repositories_listed":0,"syntology":null},{"url":null,"slug":"masked-language-modeling-becomes-conditional","title":"Masked Language Modeling Becomes Conditional Density Estimation for Tabular Data Synthesis","date":"2024-05-31","arxiv_id":"2405.20602","repositories_listed":0,"syntology":null},{"url":null,"slug":"rag-does-not-work-for-enterprises","title":"RAG Does Not Work for Enterprises","date":"2024-05-31","arxiv_id":"2406.04369","repositories_listed":0,"syntology":null},{"url":null,"slug":"structextv3-an-efficient-vision-language","title":"StrucTexTv3: An Efficient Vision-Language Model for Text-rich Image Perception, Comprehension, and Beyond","date":"2024-05-31","arxiv_id":"2405.21013","repositories_listed":0,"syntology":null},{"url":null,"slug":"you-only-scan-once-efficient-multi-dimension","title":"You Only Scan Once: Efficient Multi-dimension Sequential Modeling with LightNet","date":"2024-05-31","arxiv_id":"2405.21022","repositories_listed":0,"syntology":null},{"url":"/paper/can-t-make-an-omelette-without-breaking-some","slug":"can-t-make-an-omelette-without-breaking-some","title":"Can't make an Omelette without Breaking some Eggs: Plausible Action Anticipation using Large Video-Language Models","date":"2024-05-30","arxiv_id":"2405.20305","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-llm-jailbreaking-by-introducing","title":"Efficient Indirect LLM Jailbreak via Multimodal-LLM Jailbreak","date":"2024-05-30","arxiv_id":"2405.20015","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-words-to-actions-unveiling-the","title":"From Words to Actions: Unveiling the Theoretical Underpinnings of LLM-Driven Autonomous Systems","date":"2024-05-30","arxiv_id":"2405.19883","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-graph-tuning-real-time-large","title":"Knowledge Graph Tuning: Real-time Large Language Model Personalization based on Human Feedback","date":"2024-05-30","arxiv_id":"2405.19686","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-grounded-adaptation-strategy-for","title":"Knowledge-grounded Adaptation Strategy for Vision-language Models: Building Unique Case-set for Screening Mammograms for Residents Training","date":"2024-05-30","arxiv_id":"2405.19675","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-watermark-stealing-with","title":"Large Language Model Watermark Stealing With Mixed Integer Programming","date":"2024-05-30","arxiv_id":"2405.19677","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-open-source-large-language-models","title":"Leveraging Open-Source Large Language Models for encoding Social Determinants of Health using an Intelligent Router","date":"2024-05-30","arxiv_id":"2405.19631","repositories_listed":0,"syntology":null},{"url":null,"slug":"seamlessexpressivelm-speech-language-model","title":"SeamlessExpressiveLM: Speech Language Model for Expressive Speech-to-Speech Translation with Chain-of-Thought","date":"2024-05-30","arxiv_id":"2405.20410","repositories_listed":0,"syntology":null},{"url":null,"slug":"specdec-boosting-speculative-decoding-via","title":"SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths","date":"2024-05-30","arxiv_id":"2405.19715","repositories_listed":0,"syntology":null},{"url":null,"slug":"who-writes-the-review-human-or-ai","title":"Who Writes the Review, Human or AI?","date":"2024-05-30","arxiv_id":"2405.20285","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-full-duplex-speech-dialogue-scheme-based-on","title":"A Full-duplex Speech Dialogue Scheme Based On Large Language Models","date":"2024-05-29","arxiv_id":"2405.19487","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-position-encoding-learning-to","title":"Contextual Position Encoding: Learning to Count What's Important","date":"2024-05-29","arxiv_id":"2405.18719","repositories_listed":0,"syntology":null},{"url":null,"slug":"gemini-physical-world-large-language-models","title":"Gemini & Physical World: Large Language Models Can Estimate the Intensity of Earthquake Shaking from Multi-Modal Social Media Posts","date":"2024-05-29","arxiv_id":"2405.18732","repositories_listed":0,"syntology":null},{"url":null,"slug":"kotlin-ml-pack-technical-report","title":"Kotlin ML Pack: Technical Report","date":"2024-05-29","arxiv_id":"2405.19250","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-from-litigation-graphs-and-llms-for","title":"Learning from Litigation: Graphs and LLMs for Retrieval and Reasoning in eDiscovery","date":"2024-05-29","arxiv_id":"2405.19164","repositories_listed":0,"syntology":null},{"url":null,"slug":"llama-reg-using-llama-2-for-unsupervised","title":"LLaMA-Reg: Using LLaMA 2 for Unsupervised Medical Image Registration","date":"2024-05-29","arxiv_id":"2405.18774","repositories_listed":0,"syntology":null},{"url":null,"slug":"lmo-dp-optimizing-the-randomization-mechanism","title":"LMO-DP: Optimizing the Randomization Mechanism for Differentially Private Fine-Tuning (Large) Language Models","date":"2024-05-29","arxiv_id":"2405.18776","repositories_listed":0,"syntology":null},{"url":null,"slug":"mindsemantix-deciphering-brain-visual","title":"MindSemantix: Deciphering Brain Visual Experiences with a Brain-Language Model","date":"2024-05-29","arxiv_id":"2405.18812","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-modal-generative-embedding-model","title":"Multi-Modal Generative Embedding Model","date":"2024-05-29","arxiv_id":"2405.19333","repositories_listed":0,"syntology":null},{"url":null,"slug":"nearest-neighbor-speculative-decoding-for-llm","title":"Nearest Neighbor Speculative Decoding for LLM Generation and Attribution","date":"2024-05-29","arxiv_id":"2405.19325","repositories_listed":0,"syntology":null},{"url":null,"slug":"posterior-sampling-via-autoregressive","title":"Posterior Sampling via Autoregressive Generation","date":"2024-05-29","arxiv_id":"2405.19466","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-preference-optimization-through-reward","title":"Robust Preference Optimization through Reward Model Distillation","date":"2024-05-29","arxiv_id":"2405.19316","repositories_listed":0,"syntology":null}],"record_sha256":"28dc25b6de40f86860678a65f46601ec200b5042a34e36cc081cf6cda030a3b3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}