{"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/93","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":93,"pages_in_order":142,"rows_per_page":100,"rows":[9201,9300],"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/92","next":"/task/language-modeling/papers/94","papers":[{"url":null,"slug":"right-place-right-time-towards-objectnav-for","title":"Right Place, Right Time! Dynamizing Topological Graphs for Embodied Navigation","date":"2024-03-14","arxiv_id":"2403.09905","repositories_listed":0,"syntology":null},{"url":null,"slug":"visiongpt-vision-language-understanding-agent","title":"VisionGPT: Vision-Language Understanding Agent Using Generalized Multimodal Framework","date":"2024-03-14","arxiv_id":"2403.09027","repositories_listed":0,"syntology":null},{"url":null,"slug":"autoguide-automated-generation-and-selection","title":"AutoGuide: Automated Generation and Selection of Context-Aware Guidelines for Large Language Model Agents","date":"2024-03-13","arxiv_id":"2403.08978","repositories_listed":0,"syntology":null},{"url":null,"slug":"bifurcated-attention-for-single-context-large","title":"Bifurcated Attention: Accelerating Massively Parallel Decoding with Shared Prefixes in LLMs","date":"2024-03-13","arxiv_id":"2403.08845","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-driven-visual-consensus-for-zero","title":"Language-Driven Visual Consensus for Zero-Shot Semantic Segmentation","date":"2024-03-13","arxiv_id":"2403.08426","repositories_listed":0,"syntology":null},{"url":"/paper/strengthening-multimodal-large-language-model","slug":"strengthening-multimodal-large-language-model","title":"Strengthening Multimodal Large Language Model with Bootstrapped Preference Optimization","date":"2024-03-13","arxiv_id":"2403.08730","repositories_listed":0,"syntology":null},{"url":null,"slug":"bagel-bootstrapping-agents-by-guiding","title":"BAGEL: Bootstrapping Agents by Guiding Exploration with Language","date":"2024-03-12","arxiv_id":"2403.08140","repositories_listed":0,"syntology":null},{"url":"/paper/ckerc-joint-large-language-models-with","slug":"ckerc-joint-large-language-models-with","title":"CKERC : Joint Large Language Models with Commonsense Knowledge for Emotion Recognition in Conversation","date":"2024-03-12","arxiv_id":"2403.07260","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-language-model-architectures-for","title":"Efficient Language Model Architectures for Differentially Private Federated Learning","date":"2024-03-12","arxiv_id":"2403.08100","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-depression-diagnosis-oriented-chat","title":"Enhancing Depression-Diagnosis-Oriented Chat with Psychological State Tracking","date":"2024-03-12","arxiv_id":"2403.09717","repositories_listed":0,"syntology":null},{"url":null,"slug":"generaitor-tree-in-the-loop-text-generation","title":"generAItor: Tree-in-the-Loop Text Generation for Language Model Explainability and Adaptation","date":"2024-03-12","arxiv_id":"2403.07627","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-graph-large-language-model-kg-llm","title":"Knowledge Graph Large Language Model (KG-LLM) for Link Prediction","date":"2024-03-12","arxiv_id":"2403.07311","repositories_listed":0,"syntology":null},{"url":null,"slug":"llmvssmall-model-large-language-model-based","title":"LLMvsSmall Model? Large Language Model Based Text Augmentation Enhanced Personality Detection Model","date":"2024-03-12","arxiv_id":"2403.07581","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-generative-large-language-model","title":"Rethinking Generative Large Language Model Evaluation for Semantic Comprehension","date":"2024-03-12","arxiv_id":"2403.07872","repositories_listed":0,"syntology":null},{"url":null,"slug":"taskclip-extend-large-vision-language-model","title":"TaskCLIP: Extend Large Vision-Language Model for Task Oriented Object Detection","date":"2024-03-12","arxiv_id":"2403.08108","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-future-of-document-indexing-gpt-and-donut","title":"The future of document indexing: GPT and Donut revolutionize table of content processing","date":"2024-03-12","arxiv_id":"2403.07553","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-zero-shot-human-object-interaction","title":"Towards Zero-shot Human-Object Interaction Detection via Vision-Language Integration","date":"2024-03-12","arxiv_id":"2403.07246","repositories_listed":0,"syntology":null},{"url":null,"slug":"development-of-a-reliable-and-accessible","title":"Development of a Reliable and Accessible Caregiving Language Model (CaLM)","date":"2024-03-11","arxiv_id":"2403.06857","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-model-driven-radiology-report","title":"Large Model driven Radiology Report Generation with Clinical Quality Reinforcement Learning","date":"2024-03-11","arxiv_id":"2403.06728","repositories_listed":0,"syntology":null},{"url":null,"slug":"mapping-high-level-semantic-regions-in-indoor","title":"Mapping High-level Semantic Regions in Indoor Environments without Object Recognition","date":"2024-03-11","arxiv_id":"2403.07076","repositories_listed":0,"syntology":null},{"url":null,"slug":"mathbf-n-k-puzzle-a-cost-efficient-testbed","title":"$\\mathbf{(N,K)}$-Puzzle: A Cost-Efficient Testbed for Benchmarking Reinforcement Learning Algorithms in Generative Language Model","date":"2024-03-11","arxiv_id":"2403.07191","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompt-selection-and-augmentation-for-few","title":"Prompt Selection and Augmentation for Few Examples Code Generation in Large Language Model and its Application in Robotics Control","date":"2024-03-11","arxiv_id":"2403.12999","repositories_listed":0,"syntology":null},{"url":null,"slug":"clear-cross-transformers-with-pre-trained","title":"CLEAR: Cross-Transformers with Pre-trained Language Model is All you need for Person Attribute Recognition and Retrieval","date":"2024-03-10","arxiv_id":"2403.06119","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-instructions-to-constraints-language","title":"From Instructions to Constraints: Language Model Alignment with Automatic Constraint Verification","date":"2024-03-10","arxiv_id":"2403.06326","repositories_listed":0,"syntology":null},{"url":null,"slug":"identifying-and-interpreting-non-aligned","title":"Identifying and interpreting non-aligned human conceptual representations using language modeling","date":"2024-03-10","arxiv_id":"2403.06204","repositories_listed":0,"syntology":null},{"url":null,"slug":"in-context-prompt-learning-for-test-time","title":"In-context Prompt Learning for Test-time Vision Recognition with Frozen Vision-language Model","date":"2024-03-10","arxiv_id":"2403.06126","repositories_listed":0,"syntology":null},{"url":null,"slug":"unpacking-tokenization-evaluating-text","title":"Unpacking Tokenization: Evaluating Text Compression and its Correlation with Model Performance","date":"2024-03-10","arxiv_id":"2403.06265","repositories_listed":0,"syntology":null},{"url":null,"slug":"aligning-speech-to-languages-to-enhance-code","title":"Aligning Speech to Languages to Enhance Code-switching Speech Recognition","date":"2024-03-09","arxiv_id":"2403.05887","repositories_listed":0,"syntology":null},{"url":null,"slug":"high-throughput-phenotyping-of-physician","title":"High Throughput Phenotyping of Physician Notes with Large Language and Hybrid NLP Models","date":"2024-03-09","arxiv_id":"2403.05920","repositories_listed":0,"syntology":null},{"url":null,"slug":"thread-detection-and-response-generation","title":"Thread Detection and Response Generation using Transformers with Prompt Optimisation","date":"2024-03-09","arxiv_id":"2403.05931","repositories_listed":0,"syntology":null},{"url":null,"slug":"are-human-conversations-special-a-large","title":"Are Human Conversations Special? A Large Language Model Perspective","date":"2024-03-08","arxiv_id":"2403.05045","repositories_listed":0,"syntology":null},{"url":null,"slug":"cfairllm-consumer-fairness-evaluation-in","title":"CFaiRLLM: Consumer Fairness Evaluation in Large-Language Model Recommender System","date":"2024-03-08","arxiv_id":"2403.05668","repositories_listed":0,"syntology":null},{"url":null,"slug":"clip-gaze-towards-general-gaze-estimation-via","title":"CLIP-Gaze: Towards General Gaze Estimation via Visual-Linguistic Model","date":"2024-03-08","arxiv_id":"2403.05124","repositories_listed":0,"syntology":null},{"url":null,"slug":"vlm-pl-advanced-pseudo-labeling-approach","title":"VLM-PL: Advanced Pseudo Labeling Approach for Class Incremental Object Detection via Vision-Language Model","date":"2024-03-08","arxiv_id":"2403.05346","repositories_listed":0,"syntology":null},{"url":null,"slug":"will-gpt-4-run-doom","title":"Will GPT-4 Run DOOM?","date":"2024-03-08","arxiv_id":"2403.05468","repositories_listed":0,"syntology":null},{"url":null,"slug":"preference-optimization-of-protein-language","title":"Preference optimization of protein language models as a multi-objective binder design paradigm","date":"2024-03-07","arxiv_id":"2403.04187","repositories_listed":0,"syntology":null},{"url":null,"slug":"proxy-rlhf-decoupling-generation-and","title":"Proxy-RLHF: Decoupling Generation and Alignment in Large Language Model with Proxy","date":"2024-03-07","arxiv_id":"2403.04283","repositories_listed":0,"syntology":null},{"url":null,"slug":"sentiment-driven-prediction-of-financial","title":"Sentiment-driven prediction of financial returns: a Bayesian-enhanced FinBERT approach","date":"2024-03-07","arxiv_id":"2403.04427","repositories_listed":0,"syntology":null},{"url":null,"slug":"assessing-the-aesthetic-evaluation","title":"Assessing the Aesthetic Evaluation Capabilities of GPT-4 with Vision: Insights from Group and Individual Assessments","date":"2024-03-06","arxiv_id":"2403.03594","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffusion-on-language-model-embeddings-for","title":"Diffusion on language model encodings for protein sequence generation","date":"2024-03-06","arxiv_id":"2403.03726","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-transformer-for-comics-text-cloze","title":"Multimodal Transformer for Comics Text-Cloze","date":"2024-03-06","arxiv_id":"2403.03719","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-origins-of-linear-representations-in","title":"On the Origins of Linear Representations in Large Language Models","date":"2024-03-06","arxiv_id":"2403.03867","repositories_listed":0,"syntology":null},{"url":null,"slug":"popeye-a-unified-visual-language-model-for","title":"Popeye: A Unified Visual-Language Model for Multi-Source Ship Detection from Remote Sensing Imagery","date":"2024-03-06","arxiv_id":"2403.03790","repositories_listed":0,"syntology":null},{"url":null,"slug":"saullm-7b-a-pioneering-large-language-model","title":"SaulLM-7B: A pioneering Large Language Model for Law","date":"2024-03-06","arxiv_id":"2403.03883","repositories_listed":0,"syntology":null},{"url":"/paper/sheetagent-a-generalist-agent-for-spreadsheet","slug":"sheetagent-a-generalist-agent-for-spreadsheet","title":"SheetAgent: Towards A Generalist Agent for Spreadsheet Reasoning and Manipulation via Large Language Models","date":"2024-03-06","arxiv_id":"2403.03636","repositories_listed":0,"syntology":null},{"url":null,"slug":"breeze-7b-technical-report","title":"Breeze-7B Technical Report","date":"2024-03-05","arxiv_id":"2403.02712","repositories_listed":0,"syntology":null},{"url":null,"slug":"causal-prompting-debiasing-large-language","title":"Causal Prompting: Debiasing Large Language Model Prompting based on Front-Door Adjustment","date":"2024-03-05","arxiv_id":"2403.02738","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-guided-exploration-for-rl-agents-in","title":"Language Guided Exploration for RL Agents in Text Environments","date":"2024-03-05","arxiv_id":"2403.03141","repositories_listed":0,"syntology":null},{"url":null,"slug":"privacy-aware-semantic-cache-for-large","title":"MeanCache: User-Centric Semantic Caching for LLM Web Services","date":"2024-03-05","arxiv_id":"2403.02694","repositories_listed":0,"syntology":null},{"url":null,"slug":"sniffer-multimodal-large-language-model-for","title":"SNIFFER: Multimodal Large Language Model for Explainable Out-of-Context Misinformation Detection","date":"2024-03-05","arxiv_id":"2403.03170","repositories_listed":0,"syntology":null},{"url":null,"slug":"socratic-reasoning-improves-positive-text","title":"Socratic Reasoning Improves Positive Text Rewriting","date":"2024-03-05","arxiv_id":"2403.03029","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-training-a-chinese-large-language","title":"Towards Training A Chinese Large Language Model for Anesthesiology","date":"2024-03-05","arxiv_id":"2403.02742","repositories_listed":0,"syntology":null},{"url":null,"slug":"word-importance-explains-how-prompts-affect","title":"Word Importance Explains How Prompts Affect Language Model Outputs","date":"2024-03-05","arxiv_id":"2403.03028","repositories_listed":0,"syntology":null},{"url":null,"slug":"decider-a-rule-controllable-decoding-strategy","title":"DECIDER: A Dual-System Rule-Controllable Decoding Framework for Language Generation","date":"2024-03-04","arxiv_id":"2403.01954","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-does-architecture-influence-the-base","title":"How does Architecture Influence the Base Capabilities of Pre-trained Language Models? A Case Study Based on FFN-Wider and MoE Transformers","date":"2024-03-04","arxiv_id":"2403.02436","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-based-evolutionary","title":"Large Language Model-Based Evolutionary Optimizer: Reasoning with elitism","date":"2024-03-04","arxiv_id":"2403.02054","repositories_listed":0,"syntology":null},{"url":null,"slug":"notellm-a-retrievable-large-language-model","title":"NoteLLM: A Retrievable Large Language Model for Note Recommendation","date":"2024-03-04","arxiv_id":"2403.01744","repositories_listed":0,"syntology":null},{"url":null,"slug":"regiongpt-towards-region-understanding-vision","title":"RegionGPT: Towards Region Understanding Vision Language Model","date":"2024-03-04","arxiv_id":"2403.02330","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-intent-based-network-management-large","title":"Towards Intent-Based Network Management: Large Language Models for Intent Extraction in 5G Core Networks","date":"2024-03-04","arxiv_id":"2403.02238","repositories_listed":0,"syntology":null},{"url":null,"slug":"ovel-large-language-model-as-memory-manager","title":"OVEL: Large Language Model as Memory Manager for Online Video Entity Linking","date":"2024-03-03","arxiv_id":"2403.01411","repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-dynamic-evaluation-online","title":"Revisiting Dynamic Evaluation: Online Adaptation for Large Language Models","date":"2024-03-03","arxiv_id":"2403.01518","repositories_listed":0,"syntology":null},{"url":null,"slug":"autoattacker-a-large-language-model-guided","title":"AutoAttacker: A Large Language Model Guided System to Implement Automatic Cyber-attacks","date":"2024-03-02","arxiv_id":"2403.01038","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-free-multi-label-image-recognition-via","title":"Data-free Multi-label Image Recognition via LLM-powered Prompt Tuning","date":"2024-03-02","arxiv_id":"2403.01209","repositories_listed":0,"syntology":null},{"url":null,"slug":"scenecraft-an-llm-agent-for-synthesizing-3d","title":"SceneCraft: An LLM Agent for Synthesizing 3D Scene as Blender Code","date":"2024-03-02","arxiv_id":"2403.01248","repositories_listed":0,"syntology":null},{"url":null,"slug":"axolotl-fairness-through-assisted-self","title":"AXOLOTL: Fairness through Assisted Self-Debiasing of Large Language Model Outputs","date":"2024-03-01","arxiv_id":"2403.00198","repositories_listed":0,"syntology":null},{"url":null,"slug":"basedai-a-decentralized-p2p-network-for-zero","title":"BasedAI: A decentralized P2P network for Zero Knowledge Large Language Models (ZK-LLMs)","date":"2024-03-01","arxiv_id":"2403.01008","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-protein-structure-prediction-approach","title":"A Protein Structure Prediction Approach Leveraging Transformer and CNN Integration","date":"2024-02-29","arxiv_id":"2402.19095","repositories_listed":0,"syntology":null},{"url":null,"slug":"fac-2-e-better-understanding-large-language","title":"FAC$^2$E: Better Understanding Large Language Model Capabilities by Dissociating Language and Cognition","date":"2024-02-29","arxiv_id":"2403.00126","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-ensemble-optimal-large-language-model","title":"LLM-Ensemble: Optimal Large Language Model Ensemble Method for E-commerce Product Attribute Value Extraction","date":"2024-02-29","arxiv_id":"2403.00863","repositories_listed":0,"syntology":null},{"url":null,"slug":"paecter-patent-level-representation-learning","title":"PaECTER: Patent-level Representation Learning using Citation-informed Transformers","date":"2024-02-29","arxiv_id":"2402.19411","repositories_listed":0,"syntology":null},{"url":null,"slug":"plangpt-enhancing-urban-planning-with","title":"PlanGPT: Enhancing Urban Planning with Tailored Language Model and Efficient Retrieval","date":"2024-02-29","arxiv_id":"2402.19273","repositories_listed":0,"syntology":null},{"url":null,"slug":"typographic-attacks-in-large-multimodal","title":"Unveiling Typographic Deceptions: Insights of the Typographic Vulnerability in Large Vision-Language Model","date":"2024-02-29","arxiv_id":"2402.19150","repositories_listed":0,"syntology":null},{"url":null,"slug":"vixen-visual-text-comparison-network-for","title":"VIXEN: Visual Text Comparison Network for Image Difference Captioning","date":"2024-02-29","arxiv_id":"2402.19119","repositories_listed":0,"syntology":null},{"url":null,"slug":"chaining-text-to-image-and-large-language","title":"Chaining text-to-image and large language model: A novel approach for generating personalized e-commerce banners","date":"2024-02-28","arxiv_id":"2403.05578","repositories_listed":0,"syntology":null},{"url":null,"slug":"ice-search-a-language-model-driven-feature","title":"ICE-SEARCH: A Language Model-Driven Feature Selection Approach","date":"2024-02-28","arxiv_id":"2402.18609","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-crowdsourcing-breaking-your-bank-cost","title":"Is Crowdsourcing Breaking Your Bank? Cost-Effective Fine-Tuning of Pre-trained Language Models with Proximal Policy Optimization","date":"2024-02-28","arxiv_id":"2402.18284","repositories_listed":0,"syntology":null},{"url":null,"slug":"merino-entropy-driven-design-for-generative","title":"Merino: Entropy-driven Design for Generative Language Models on IoT Devices","date":"2024-02-28","arxiv_id":"2403.07921","repositories_listed":0,"syntology":null},{"url":null,"slug":"miko-multimodal-intention-knowledge","title":"MIKO: Multimodal Intention Knowledge Distillation from Large Language Models for Social-Media Commonsense Discovery","date":"2024-02-28","arxiv_id":"2402.18169","repositories_listed":0,"syntology":null},{"url":null,"slug":"orchid-flexible-and-data-dependent","title":"Orchid: Flexible and Data-Dependent Convolution for Sequence Modeling","date":"2024-02-28","arxiv_id":"2402.18508","repositories_listed":0,"syntology":null},{"url":null,"slug":"random-silicon-sampling-simulating-human-sub","title":"Random Silicon Sampling: Simulating Human Sub-Population Opinion Using a Large Language Model Based on Group-Level Demographic Information","date":"2024-02-28","arxiv_id":"2402.18144","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-language-model-based-caption","title":"Vision Language Model-based Caption Evaluation Method Leveraging Visual Context Extraction","date":"2024-02-28","arxiv_id":"2402.17969","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-neural-rewriting-system-to-solve","title":"A Neural Rewriting System to Solve Algorithmic Problems","date":"2024-02-27","arxiv_id":"2402.17407","repositories_listed":0,"syntology":null},{"url":null,"slug":"bases-large-scale-web-search-user-simulation","title":"BASES: Large-scale Web Search User Simulation with Large Language Model based Agents","date":"2024-02-27","arxiv_id":"2402.17505","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-for-participatory-urban","title":"Large Language Model for Participatory Urban Planning","date":"2024-02-27","arxiv_id":"2402.17161","repositories_listed":0,"syntology":null},{"url":null,"slug":"omniact-a-dataset-and-benchmark-for-enabling","title":"OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web","date":"2024-02-27","arxiv_id":"2402.17553","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-optimal-learning-of-language-models","title":"Towards Optimal Learning of Language Models","date":"2024-02-27","arxiv_id":"2402.17759","repositories_listed":0,"syntology":null},{"url":null,"slug":"cfret-dvqa-coarse-to-fine-retrieval-and","title":"Read and Think: An Efficient Step-wise Multimodal Language Model for Document Understanding and Reasoning","date":"2024-02-26","arxiv_id":"2403.00816","repositories_listed":0,"syntology":null},{"url":null,"slug":"esg-sentiment-analysis-comparing-human-and","title":"ESG Sentiment Analysis: comparing human and language model performance including GPT","date":"2024-02-26","arxiv_id":"2402.16650","repositories_listed":0,"syntology":null},{"url":"/paper/groundhog-grounding-large-language-models-to","slug":"groundhog-grounding-large-language-models-to","title":"GROUNDHOG: Grounding Large Language Models to Holistic Segmentation","date":"2024-02-26","arxiv_id":"2402.16846","repositories_listed":0,"syntology":null},{"url":null,"slug":"nemotron-4-15b-technical-report","title":"Nemotron-4 15B Technical Report","date":"2024-02-26","arxiv_id":"2402.16819","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-languaging-a-simulation-engine","title":"On Languaging a Simulation Engine","date":"2024-02-26","arxiv_id":"2402.16482","repositories_listed":0,"syntology":null},{"url":null,"slug":"oncogpt-a-medical-conversational-model","title":"OncoGPT: A Medical Conversational Model Tailored with Oncology Domain Expertise on a Large Language Model Meta-AI (LLaMA)","date":"2024-02-26","arxiv_id":"2402.16810","repositories_listed":0,"syntology":null},{"url":null,"slug":"think-big-generate-quick-llm-to-slm-for-fast","title":"Think Big, Generate Quick: LLM-to-SLM for Fast Autoregressive Decoding","date":"2024-02-26","arxiv_id":"2402.16844","repositories_listed":0,"syntology":null},{"url":null,"slug":"topic-to-essay-generation-with-knowledge","title":"Topic-to-essay generation with knowledge-based content selection","date":"2024-02-26","arxiv_id":"2402.16248","repositories_listed":0,"syntology":null},{"url":null,"slug":"bootstrapping-cognitive-agents-with-a-large","title":"Bootstrapping Cognitive Agents with a Large Language Model","date":"2024-02-25","arxiv_id":"2403.00810","repositories_listed":0,"syntology":null},{"url":null,"slug":"building-flexible-machine-learning-models-for","title":"Building Flexible Machine Learning Models for Scientific Computing at Scale","date":"2024-02-25","arxiv_id":"2402.16014","repositories_listed":0,"syntology":null},{"url":null,"slug":"don-t-forget-your-reward-values-language","title":"Don't Forget Your Reward Values: Language Model Alignment via Value-based Calibration","date":"2024-02-25","arxiv_id":"2402.16030","repositories_listed":0,"syntology":null},{"url":null,"slug":"pidformer-transformer-meets-control-theory","title":"PIDformer: Transformer Meets Control Theory","date":"2024-02-25","arxiv_id":"2402.15989","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-a-bilingual-language-model-by","title":"Training a Bilingual Language Model by Mapping Tokens onto a Shared Character Space","date":"2024-02-25","arxiv_id":"2402.16065","repositories_listed":0,"syntology":null},{"url":null,"slug":"bytecomposer-a-human-like-melody-composition","title":"ByteComposer: a Human-like Melody Composition Method based on Language Model Agent","date":"2024-02-24","arxiv_id":"2402.17785","repositories_listed":0,"syntology":null}],"record_sha256":"5285464a07dfb6a215450bb43d89f6f5e323e33eed92d1dba966f51808d67954","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}