{"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/instruction-following/papers/9","list_of":"/task/instruction-following","task":"Instruction Following","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":9,"pages_in_order":12,"rows_per_page":100,"rows":[801,900],"of":1135,"counts":{"archive_papers_tagged":1135,"with_a_code_link":609,"where_syntology_ran_a_sample":311,"not_listed_spam_title":0,"listed":1135,"listed_where_code_ran":311,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":255,"every_run_a_failure_of_syntologys_instrument":56,"listed_with_a_run_with_no_instrument_failure":255,"listed_every_run_a_failure_of_syntologys_instrument":56,"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/instruction-following","prev":"/task/instruction-following/papers/8","next":"/task/instruction-following/papers/10","papers":[{"url":null,"slug":"optimizing-latent-goal-by-learning-from","title":"Optimizing Latent Goal by Learning from Trajectory Preference","date":"2024-12-03","arxiv_id":"2412.02125","repositories_listed":0,"syntology":null},{"url":null,"slug":"t-reg-preference-optimization-with-token","title":"T-REG: Preference Optimization with Token-Level Reward Regularization","date":"2024-12-03","arxiv_id":"2412.02685","repositories_listed":0,"syntology":null},{"url":null,"slug":"alignformer-modality-matching-can-achieve","title":"AlignFormer: Modality Matching Can Achieve Better Zero-shot Instruction-Following Speech-LLM","date":"2024-12-02","arxiv_id":"2412.01145","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-function-calling-capabilities-in","title":"Enhancing Function-Calling Capabilities in LLMs: Strategies for Prompt Formats, Data Integration, and Multilingual Translation","date":"2024-12-02","arxiv_id":"2412.01130","repositories_listed":0,"syntology":null},{"url":null,"slug":"mininggpt-a-domain-specific-large-language","title":"MiningGPT -- A Domain-Specific Large Language Model for the Mining Industry","date":"2024-12-02","arxiv_id":"2412.01189","repositories_listed":0,"syntology":null},{"url":null,"slug":"vista-enhancing-long-duration-and-high","title":"VISTA: Enhancing Long-Duration and High-Resolution Video Understanding by Video Spatiotemporal Augmentation","date":"2024-12-01","arxiv_id":"2412.00927","repositories_listed":0,"syntology":null},{"url":null,"slug":"insightedit-towards-better-instruction","title":"InsightEdit: Towards Better Instruction Following for Image Editing","date":"2024-11-26","arxiv_id":"2411.17323","repositories_listed":0,"syntology":null},{"url":null,"slug":"gaussian-scenes-pose-free-sparse-view-scene","title":"Gaussian Scenes: Pose-Free Sparse-View Scene Reconstruction using Depth-Enhanced Diffusion Priors","date":"2024-11-24","arxiv_id":"2411.15966","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-instruction-following-capability-of","title":"Enhancing Instruction-Following Capability of Visual-Language Models by Reducing Image Redundancy","date":"2024-11-23","arxiv_id":"2411.15453","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-mteb-to-mtob-retrieval-augmented","title":"From MTEB to MTOB: Retrieval-Augmented Classification for Descriptive Grammars","date":"2024-11-23","arxiv_id":"2411.15577","repositories_listed":0,"syntology":null},{"url":null,"slug":"separable-mixture-of-low-rank-adaptation-for","title":"Separable Mixture of Low-Rank Adaptation for Continual Visual Instruction Tuning","date":"2024-11-21","arxiv_id":"2411.13949","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-decoding-via-latent-preference","title":"Adaptive Decoding via Latent Preference Optimization","date":"2024-11-14","arxiv_id":"2411.09661","repositories_listed":0,"syntology":null},{"url":null,"slug":"nl-slam-for-oc-vln-natural-language-grounded","title":"Zero-shot Object-Centric Instruction Following: Integrating Foundation Models with Traditional Navigation","date":"2024-11-12","arxiv_id":"2411.07848","repositories_listed":0,"syntology":null},{"url":null,"slug":"mr-steve-instruction-following-agents-in","title":"MrSteve: Instruction-Following Agents in Minecraft with What-Where-When Memory","date":"2024-11-11","arxiv_id":"2411.06736","repositories_listed":0,"syntology":null},{"url":null,"slug":"stronger-models-are-not-stronger-teachers-for","title":"Stronger Models are NOT Stronger Teachers for Instruction Tuning","date":"2024-11-11","arxiv_id":"2411.07133","repositories_listed":0,"syntology":null},{"url":null,"slug":"fox-1-technical-report","title":"Fox-1 Technical Report","date":"2024-11-08","arxiv_id":"2411.05281","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-reward-as-condition-for-instruction","title":"Multi-Reward as Condition for Instruction-based Image Editing","date":"2024-11-06","arxiv_id":"2411.04713","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-extraction-attacks-in-retrieval","title":"Data Extraction Attacks in Retrieval-Augmented Generation via Backdoors","date":"2024-11-03","arxiv_id":"2411.01705","repositories_listed":0,"syntology":null},{"url":null,"slug":"typescore-a-text-fidelity-metric-for-text-to","title":"TypeScore: A Text Fidelity Metric for Text-to-Image Generative Models","date":"2024-11-02","arxiv_id":"2411.02437","repositories_listed":0,"syntology":null},{"url":null,"slug":"uft-unifying-fine-tuning-of-sft-and-rlhf-dpo","title":"UFT: Unifying Fine-Tuning of SFT and RLHF/DPO/UNA through a Generalized Implicit Reward Function","date":"2024-10-28","arxiv_id":"2410.21438","repositories_listed":0,"syntology":null},{"url":null,"slug":"switch-studying-with-teacher-for-knowledge","title":"SWITCH: Studying with Teacher for Knowledge Distillation of Large Language Models","date":"2024-10-25","arxiv_id":"2410.19503","repositories_listed":0,"syntology":null},{"url":null,"slug":"biomistral-nlu-towards-more-generalizable","title":"BioMistral-NLU: Towards More Generalizable Medical Language Understanding through Instruction Tuning","date":"2024-10-24","arxiv_id":"2410.18955","repositories_listed":0,"syntology":null},{"url":null,"slug":"unbounded-a-generative-infinite-game-of","title":"Unbounded: A Generative Infinite Game of Character Life Simulation","date":"2024-10-24","arxiv_id":"2410.18975","repositories_listed":0,"syntology":null},{"url":null,"slug":"simrag-self-improving-retrieval-augmented","title":"SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domains","date":"2024-10-23","arxiv_id":"2410.17952","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-understanding-the-fragility-of","title":"Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks","date":"2024-10-23","arxiv_id":"2410.18210","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-models-for-autonomous-driving-1","title":"Large Language Models for Autonomous Driving (LLM4AD): Concept, Benchmark, Experiments, and Challenges","date":"2024-10-20","arxiv_id":"2410.15281","repositories_listed":0,"syntology":null},{"url":null,"slug":"llava-ultra-large-chinese-language-and-vision","title":"LLaVA-Ultra: Large Chinese Language and Vision Assistant for Ultrasound","date":"2024-10-19","arxiv_id":"2410.15074","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-llm-translation-skills-without","title":"Boosting LLM Translation Skills without General Ability Loss via Rationale Distillation","date":"2024-10-17","arxiv_id":"2410.13944","repositories_listed":0,"syntology":null},{"url":null,"slug":"porover-improving-safety-and-reducing","title":"POROver: Improving Safety and Reducing Overrefusal in Large Language Models with Overgeneration and Preference Optimization","date":"2024-10-16","arxiv_id":"2410.12999","repositories_listed":0,"syntology":null},{"url":"/paper/improving-instruction-following-in-language-1","slug":"improving-instruction-following-in-language-1","title":"Improving Instruction-Following in Language Models through Activation Steering","date":"2024-10-15","arxiv_id":"2410.12877","repositories_listed":0,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/improving-instruction-following-in-language-1#ran","syntology_url":"https://syntology.ai/paper/2410.12877","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.12877"}},"official":null}},{"url":null,"slug":"slidechat-a-large-vision-language-assistant","title":"SlideChat: A Large Vision-Language Assistant for Whole-Slide Pathology Image Understanding","date":"2024-10-15","arxiv_id":"2410.11761","repositories_listed":0,"syntology":null},{"url":null,"slug":"speculative-knowledge-distillation-bridging","title":"Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling","date":"2024-10-15","arxiv_id":"2410.11325","repositories_listed":0,"syntology":null},{"url":null,"slug":"balancing-continuous-pre-training-and","title":"Balancing Continuous Pre-Training and Instruction Fine-Tuning: Optimizing Instruction-Following in LLMs","date":"2024-10-14","arxiv_id":"2410.10739","repositories_listed":0,"syntology":null},{"url":null,"slug":"drivingdojo-dataset-advancing-interactive-and","title":"DrivingDojo Dataset: Advancing Interactive and Knowledge-Enriched Driving World Model","date":"2024-10-14","arxiv_id":"2410.10738","repositories_listed":0,"syntology":null},{"url":null,"slug":"forgerygpt-multimodal-large-language-model","title":"ForgeryGPT: Multimodal Large Language Model For Explainable Image Forgery Detection and Localization","date":"2024-10-14","arxiv_id":"2410.10238","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-instruction-synthesis-effective","title":"Optimizing Instruction Synthesis: Effective Exploration of Evolutionary Space with Tree Search","date":"2024-10-14","arxiv_id":"2410.10392","repositories_listed":0,"syntology":null},{"url":null,"slug":"thinking-llms-general-instruction-following","title":"Thinking LLMs: General Instruction Following with Thought Generation","date":"2024-10-14","arxiv_id":"2410.10630","repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-driving-simulations-via","title":"Conversational Code Generation: a Case Study of Designing a Dialogue System for Generating Driving Scenarios for Testing Autonomous Vehicles","date":"2024-10-13","arxiv_id":"2410.09829","repositories_listed":0,"syntology":null},{"url":null,"slug":"surgical-llava-toward-surgical-scenario","title":"Surgical-LLaVA: Toward Surgical Scenario Understanding via Large Language and Vision Models","date":"2024-10-13","arxiv_id":"2410.09750","repositories_listed":0,"syntology":null},{"url":null,"slug":"are-you-human-an-adversarial-benchmark-to","title":"Are You Human? An Adversarial Benchmark to Expose LLMs","date":"2024-10-12","arxiv_id":"2410.09569","repositories_listed":0,"syntology":null},{"url":null,"slug":"sera-self-reviewing-and-alignment-of-large","title":"SeRA: Self-Reviewing and Alignment of Large Language Models using Implicit Reward Margins","date":"2024-10-12","arxiv_id":"2410.09362","repositories_listed":0,"syntology":null},{"url":null,"slug":"nudging-inference-time-alignment-via-model","title":"Nudging: Inference-time Alignment of LLMs via Guided Decoding","date":"2024-10-11","arxiv_id":"2410.09300","repositories_listed":0,"syntology":null},{"url":null,"slug":"evolutionary-contrastive-distillation-for","title":"Evolutionary Contrastive Distillation for Language Model Alignment","date":"2024-10-10","arxiv_id":"2410.07513","repositories_listed":0,"syntology":null},{"url":null,"slug":"herm-benchmarking-and-enhancing-multimodal","title":"HERM: Benchmarking and Enhancing Multimodal LLMs for Human-Centric Understanding","date":"2024-10-09","arxiv_id":"2410.06777","repositories_listed":0,"syntology":null},{"url":null,"slug":"instructional-segment-embedding-improving-llm","title":"Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy","date":"2024-10-09","arxiv_id":"2410.09102","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-compression-with-neural-architecture","title":"Large Language Model Compression with Neural Architecture Search","date":"2024-10-09","arxiv_id":"2410.06479","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-self-correction-with-decrim-decompose","title":"LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints","date":"2024-10-09","arxiv_id":"2410.06458","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-boosting-large-language-models-with","title":"Self-Boosting Large Language Models with Synthetic Preference Data","date":"2024-10-09","arxiv_id":"2410.06961","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-situational-safety","title":"Multimodal Situational Safety","date":"2024-10-08","arxiv_id":"2410.06172","repositories_listed":0,"syntology":null},{"url":null,"slug":"rlrf4rec-reinforcement-learning-from-recsys","title":"Direct Preference Optimization for LLM-Enhanced Recommendation Systems","date":"2024-10-08","arxiv_id":"2410.05939","repositories_listed":0,"syntology":null},{"url":null,"slug":"tower-tree-organized-weighting-for-evaluating","title":"TOWER: Tree Organized Weighting for Evaluating Complex Instructions","date":"2024-10-08","arxiv_id":"2410.06089","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-instruction-finetuning-neural-machine","title":"On Instruction-Finetuning Neural Machine Translation Models","date":"2024-10-07","arxiv_id":"2410.05553","repositories_listed":0,"syntology":null},{"url":null,"slug":"reviseval-improving-llm-as-a-judge-via","title":"RevisEval: Improving LLM-as-a-Judge via Response-Adapted References","date":"2024-10-07","arxiv_id":"2410.05193","repositories_listed":0,"syntology":null},{"url":null,"slug":"sftmix-elevating-language-model-instruction","title":"SFTMix: Elevating Language Model Instruction Tuning with Mixup Recipe","date":"2024-10-07","arxiv_id":"2410.05248","repositories_listed":0,"syntology":null},{"url":null,"slug":"superficial-safety-alignment-hypothesis","title":"Superficial Safety Alignment Hypothesis","date":"2024-10-07","arxiv_id":"2410.10862","repositories_listed":0,"syntology":null},{"url":null,"slug":"textbf-only-if-revealing-the-decisive-effect","title":"$\\textbf{Only-IF}$:Revealing the Decisive Effect of Instruction Diversity on Generalization","date":"2024-10-07","arxiv_id":"2410.04717","repositories_listed":0,"syntology":null},{"url":null,"slug":"sag-style-aligned-article-generation-via","title":"SAG: Style-Aligned Article Generation via Model Collaboration","date":"2024-10-04","arxiv_id":"2410.03137","repositories_listed":0,"syntology":null},{"url":null,"slug":"ticking-all-the-boxes-generated-checklists","title":"TICKing All the Boxes: Generated Checklists Improve LLM Evaluation and Generation","date":"2024-10-04","arxiv_id":"2410.03608","repositories_listed":0,"syntology":null},{"url":null,"slug":"better-instruction-following-through-minimum","title":"Better Instruction-Following Through Minimum Bayes Risk","date":"2024-10-03","arxiv_id":"2410.02902","repositories_listed":0,"syntology":null},{"url":null,"slug":"llava-critic-learning-to-evaluate-multimodal","title":"LLaVA-Critic: Learning to Evaluate Multimodal Models","date":"2024-10-03","arxiv_id":"2410.02712","repositories_listed":0,"syntology":null},{"url":null,"slug":"logra-med-long-context-multi-graph-alignment","title":"LoGra-Med: Long Context Multi-Graph Alignment for Medical Vision-Language Model","date":"2024-10-03","arxiv_id":"2410.02615","repositories_listed":0,"syntology":null},{"url":"/paper/video-instruction-tuning-with-synthetic-data","slug":"video-instruction-tuning-with-synthetic-data","title":"Video Instruction Tuning With Synthetic Data","date":"2024-10-03","arxiv_id":"2410.02713","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-perfect-blend-redefining-rlhf-with","title":"The Perfect Blend: Redefining RLHF with Mixture of Judges","date":"2024-09-30","arxiv_id":"2409.20370","repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-the-superficial-alignment","title":"Revisiting the Superficial Alignment Hypothesis","date":"2024-09-27","arxiv_id":"2410.03717","repositories_listed":0,"syntology":null},{"url":null,"slug":"inference-time-language-model-alignment-via","title":"Inference-Time Language Model Alignment via Integrated Value Guidance","date":"2024-09-26","arxiv_id":"2409.17819","repositories_listed":0,"syntology":null},{"url":null,"slug":"mmmt-if-a-challenging-multimodal-multi-turn","title":"MMMT-IF: A Challenging Multimodal Multi-Turn Instruction Following Benchmark","date":"2024-09-26","arxiv_id":"2409.18216","repositories_listed":0,"syntology":null},{"url":null,"slug":"eagle-towards-efficient-arbitrary-referring","title":"EAGLE: Towards Efficient Arbitrary Referring Visual Prompts Comprehension for Multimodal Large Language Models","date":"2024-09-25","arxiv_id":"2409.16723","repositories_listed":0,"syntology":null},{"url":null,"slug":"eliciting-instruction-tuned-code-language","title":"Eliciting Instruction-tuned Code Language Models' Capabilities to Utilize Auxiliary Function for Code Generation","date":"2024-09-20","arxiv_id":"2409.13928","repositories_listed":0,"syntology":null},{"url":null,"slug":"cameleval-advancing-culturally-aligned-arabic","title":"CamelEval: Advancing Culturally Aligned Arabic Language Models and Benchmarks","date":"2024-09-19","arxiv_id":"2409.12623","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-low-resource-language-and","title":"Enhancing Low-Resource Language and Instruction Following Capabilities of Audio Language Models","date":"2024-09-17","arxiv_id":"2409.10999","repositories_listed":0,"syntology":null},{"url":null,"slug":"siftom-robust-spoken-instruction-following","title":"SIFToM: Robust Spoken Instruction Following through Theory of Mind","date":"2024-09-17","arxiv_id":"2409.10849","repositories_listed":0,"syntology":null},{"url":null,"slug":"emo-dpo-controllable-emotional-speech","title":"Emo-DPO: Controllable Emotional Speech Synthesis through Direct Preference Optimization","date":"2024-09-16","arxiv_id":"2409.10157","repositories_listed":0,"syntology":null},{"url":null,"slug":"sfr-rag-towards-contextually-faithful-llms","title":"SFR-RAG: Towards Contextually Faithful LLMs","date":"2024-09-16","arxiv_id":"2409.09916","repositories_listed":0,"syntology":null},{"url":null,"slug":"keypoints-integrated-instruction-following","title":"Keypoints-Integrated Instruction-Following Data Generation for Enhanced Human Pose Understanding in Multimodal Models","date":"2024-09-14","arxiv_id":"2409.09306","repositories_listed":0,"syntology":null},{"url":null,"slug":"stressprompt-does-stress-impact-large","title":"StressPrompt: Does Stress Impact Large Language Models and Human Performance Similarly?","date":"2024-09-14","arxiv_id":"2409.17167","repositories_listed":0,"syntology":null},{"url":null,"slug":"rnr-teaching-large-language-models-to-follow","title":"RNR: Teaching Large Language Models to Follow Roles and Rules","date":"2024-09-10","arxiv_id":"2409.13733","repositories_listed":0,"syntology":null},{"url":null,"slug":"incorporate-llms-with-influential-recommender","title":"Leveraging LLMs for Influence Path Planning in Proactive Recommendation","date":"2024-09-07","arxiv_id":"2409.04827","repositories_listed":0,"syntology":null},{"url":null,"slug":"continual-skill-and-task-learning-via","title":"Continual Skill and Task Learning via Dialogue","date":"2024-09-05","arxiv_id":"2409.03166","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompt-baking","title":"Prompt Baking","date":"2024-09-04","arxiv_id":"2409.13697","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-models-benefit-from-preparation-with","title":"Language Models Benefit from Preparation with Elicited Knowledge","date":"2024-09-02","arxiv_id":"2409.01345","repositories_listed":0,"syntology":null},{"url":null,"slug":"entropic-distribution-matching-in-supervised","title":"Entropic Distribution Matching in Supervised Fine-tuning of LLMs: Less Overfitting and Better Diversity","date":"2024-08-29","arxiv_id":"2408.16673","repositories_listed":0,"syntology":null},{"url":null,"slug":"m4cxr-exploring-multi-task-potentials-of","title":"M4CXR: Exploring Multi-task Potentials of Multi-modal Large Language Models for Chest X-ray Interpretation","date":"2024-08-29","arxiv_id":"2408.16213","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-modal-instruction-tuning-small-scale","title":"Multi-Modal Instruction-Tuning Small-Scale Language-and-Vision Assistant for Semiconductor Electron Micrograph Analysis","date":"2024-08-27","arxiv_id":"2409.07463","repositories_listed":0,"syntology":null},{"url":null,"slug":"parameter-efficient-quantized-mixture-of","title":"Parameter-Efficient Quantized Mixture-of-Experts Meets Vision-Language Instruction Tuning for Semiconductor Electron Micrograph Analysis","date":"2024-08-27","arxiv_id":"2408.15305","repositories_listed":0,"syntology":null},{"url":null,"slug":"foundational-model-for-electron-micrograph","title":"Foundational Model for Electron Micrograph Analysis: Instruction-Tuning Small-Scale Language-and-Vision Assistant for Enterprise Adoption","date":"2024-08-23","arxiv_id":"2408.13248","repositories_listed":0,"syntology":null},{"url":null,"slug":"less-for-more-enhancing-preference-learning","title":"Preference Consistency Matters: Enhancing Preference Learning in Language Models with Automated Self-Curation of Training Corpora","date":"2024-08-23","arxiv_id":"2408.12799","repositories_listed":0,"syntology":null},{"url":null,"slug":"kubrick-multimodal-agent-collaborations-for","title":"Kubrick: Multimodal Agent Collaborations for Synthetic Video Generation","date":"2024-08-19","arxiv_id":"2408.10453","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-large-language-models-understand-symbolic","title":"Can Large Language Models Understand Symbolic Graphics Programs?","date":"2024-08-15","arxiv_id":"2408.08313","repositories_listed":0,"syntology":null},{"url":"/paper/crome-cross-modal-adapters-for-efficient","slug":"crome-cross-modal-adapters-for-efficient","title":"CROME: Cross-Modal Adapters for Efficient Multimodal LLM","date":"2024-08-13","arxiv_id":"2408.06610","repositories_listed":0,"syntology":null},{"url":null,"slug":"adapting-a-foundation-model-for-space-based","title":"Space-LLaVA: a Vision-Language Model Adapted to Extraterrestrial Applications","date":"2024-08-12","arxiv_id":"2408.05924","repositories_listed":0,"syntology":null},{"url":null,"slug":"creating-arabic-llm-prompts-at-scale","title":"Creating Arabic LLM Prompts at Scale","date":"2024-08-12","arxiv_id":"2408.05882","repositories_listed":0,"syntology":null},{"url":null,"slug":"empirical-analysis-of-large-vision-language","title":"Empirical Analysis of Large Vision-Language Models against Goal Hijacking via Visual Prompt Injection","date":"2024-08-07","arxiv_id":"2408.03554","repositories_listed":0,"syntology":null},{"url":null,"slug":"exaone-3-0-7-8b-instruction-tuned-language","title":"EXAONE 3.0 7.8B Instruction Tuned Language Model","date":"2024-08-07","arxiv_id":"2408.03541","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-02861","title":"A Framework for Fine-Tuning LLMs using Heterogeneous Feedback","date":"2024-08-05","arxiv_id":"2408.02861","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-01024","title":"Semantic Skill Grounding for Embodied Instruction-Following in Cross-Domain Environments","date":"2024-08-02","arxiv_id":"2408.01024","repositories_listed":0,"syntology":null},{"url":null,"slug":"saullm-54b-saullm-141b-scaling-up-domain","title":"SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domain","date":"2024-07-28","arxiv_id":"2407.19584","repositories_listed":0,"syntology":null},{"url":null,"slug":"hapfi-history-aware-planning-based-on-fused","title":"HAPFI: History-Aware Planning based on Fused Information","date":"2024-07-23","arxiv_id":"2407.16533","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-do-universal-image-jailbreaks-transfer","title":"Failures to Find Transferable Image Jailbreaks Between Vision-Language Models","date":"2024-07-21","arxiv_id":"2407.15211","repositories_listed":0,"syntology":null},{"url":null,"slug":"chatqa-2-bridging-the-gap-to-proprietary-llms","title":"ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities","date":"2024-07-19","arxiv_id":"2407.14482","repositories_listed":0,"syntology":null},{"url":null,"slug":"situated-instruction-following","title":"Situated Instruction Following","date":"2024-07-15","arxiv_id":"2407.12061","repositories_listed":0,"syntology":null}],"record_sha256":"1001c8f03415b6ee4375ea6715cb6fdaf54454f46eb5851f0cb135cb6e95adc9","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}