{"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/11","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":11,"pages_in_order":12,"rows_per_page":100,"rows":[1001,1100],"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/10","next":"/task/instruction-following/papers/12","papers":[{"url":null,"slug":"vision-language-models-provide-promptable","title":"Vision-Language Models Provide Promptable Representations for Reinforcement Learning","date":"2024-02-05","arxiv_id":"2402.02651","repositories_listed":0,"syntology":null},{"url":null,"slug":"diversity-measurement-and-subset-selection","title":"Diversity Measurement and Subset Selection for Instruction Tuning Datasets","date":"2024-02-04","arxiv_id":"2402.02318","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-the-problem-of-strong-priors-in","title":"Mitigating the Influence of Distractor Tasks in LMs with Prior-Aware Decoding","date":"2024-01-31","arxiv_id":"2401.17692","repositories_listed":0,"syntology":null},{"url":null,"slug":"kaucus-knowledge-augmented-user-simulators","title":"KAUCUS: Knowledge Augmented User Simulators for Training Language Model Assistants","date":"2024-01-29","arxiv_id":"2401.16454","repositories_listed":0,"syntology":null},{"url":null,"slug":"autort-embodied-foundation-models-for-large","title":"AutoRT: Embodied Foundation Models for Large Scale Orchestration of Robotic Agents","date":"2024-01-23","arxiv_id":"2401.12963","repositories_listed":0,"syntology":null},{"url":"/paper/coco-is-all-you-need-for-visual-instruction","slug":"coco-is-all-you-need-for-visual-instruction","title":"COCO is \"ALL'' You Need for Visual Instruction Fine-tuning","date":"2024-01-17","arxiv_id":"2401.08968","repositories_listed":0,"syntology":null},{"url":null,"slug":"pub-a-pragmatics-understanding-benchmark-for","title":"PUB: A Pragmatics Understanding Benchmark for Assessing LLMs' Pragmatics Capabilities","date":"2024-01-13","arxiv_id":"2401.07078","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-instruction-free-llm-self-alignment","title":"Human-Instruction-Free LLM Self-Alignment with Limited Samples","date":"2024-01-06","arxiv_id":"2401.06785","repositories_listed":0,"syntology":null},{"url":null,"slug":"incorporating-visual-experts-to-resolve-the","title":"Incorporating Visual Experts to Resolve the Information Loss in Multimodal Large Language Models","date":"2024-01-06","arxiv_id":"2401.03105","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-instruction-tuning-with-just-a","title":"Multilingual Instruction Tuning With Just a Pinch of Multilinguality","date":"2024-01-03","arxiv_id":"2401.01854","repositories_listed":0,"syntology":null},{"url":null,"slug":"ssp-a-simple-and-safe-automatic-prompt","title":"SSP: A Simple and Safe automatic Prompt engineering method towards realistic image synthesis on LVM","date":"2024-01-02","arxiv_id":"2401.01128","repositories_listed":0,"syntology":null},{"url":null,"slug":"generate-subgoal-images-before-act-unlocking","title":"Generate Subgoal Images before Act: Unlocking the Chain-of-Thought Reasoning in Diffusion Model for Robot Manipulation with Multimodal Prompts","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unified-io-2-scaling-autoregressive-1","title":"Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision Language Audio and Action","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-instruction-tuning-towards-general","title":"Visual Instruction Tuning towards General-Purpose Multimodal Model: A Survey","date":"2023-12-27","arxiv_id":"2312.16602","repositories_listed":0,"syntology":null},{"url":null,"slug":"lidar-llm-exploring-the-potential-of-large","title":"LiDAR-LLM: Exploring the Potential of Large Language Models for 3D LiDAR Understanding","date":"2023-12-21","arxiv_id":"2312.14074","repositories_listed":0,"syntology":null},{"url":null,"slug":"mixture-of-cluster-conditional-lora-experts","title":"Mixture of Cluster-conditional LoRA Experts for Vision-language Instruction Tuning","date":"2023-12-19","arxiv_id":"2312.12379","repositories_listed":0,"syntology":null},{"url":null,"slug":"thinkbot-embodied-instruction-following-with","title":"ThinkBot: Embodied Instruction Following with Thought Chain Reasoning","date":"2023-12-12","arxiv_id":"2312.07062","repositories_listed":0,"syntology":null},{"url":null,"slug":"variety-and-quality-over-quantity-towards","title":"Rethinking the Instruction Quality: LIFT is What You Need","date":"2023-12-12","arxiv_id":"2312.11508","repositories_listed":0,"syntology":null},{"url":null,"slug":"aligner-one-global-token-is-worth-millions-of","title":"Aligner: One Global Token is Worth Millions of Parameters When Aligning Large Language Models","date":"2023-12-09","arxiv_id":"2312.05503","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-as-image-learning-transferable-adapter","title":"Text as Image: Learning Transferable Adapter for Multi-Label Classification","date":"2023-12-07","arxiv_id":"2312.04160","repositories_listed":0,"syntology":null},{"url":null,"slug":"muffin-curating-multi-faceted-instructions","title":"MUFFIN: Curating Multi-Faceted Instructions for Improving Instruction-Following","date":"2023-12-05","arxiv_id":"2312.02436","repositories_listed":0,"syntology":null},{"url":null,"slug":"instructbooth-instruction-following","title":"InstructBooth: Instruction-following Personalized Text-to-Image Generation","date":"2023-12-04","arxiv_id":"2312.03011","repositories_listed":0,"syntology":null},{"url":null,"slug":"medxchat-bridging-cxr-modalities-with-a","title":"MedXChat: A Unified Multimodal Large Language Model Framework towards CXRs Understanding and Generation","date":"2023-12-04","arxiv_id":"2312.02233","repositories_listed":0,"syntology":null},{"url":null,"slug":"releasing-the-craqan-coreference-resolution","title":"Releasing the CRaQAn (Coreference Resolution in Question-Answering): An open-source dataset and dataset creation methodology using instruction-following models","date":"2023-11-27","arxiv_id":"2311.16338","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-vision-enhancing-llms-empowering","title":"Towards Vision Enhancing LLMs: Empowering Multimodal Knowledge Storage and Sharing in LLMs","date":"2023-11-27","arxiv_id":"2311.15759","repositories_listed":0,"syntology":null},{"url":null,"slug":"gpt4video-a-unified-multimodal-large-language","title":"GPT4Video: A Unified Multimodal Large Language Model for lnstruction-Followed Understanding and Safety-Aware Generation","date":"2023-11-25","arxiv_id":"2311.16511","repositories_listed":0,"syntology":null},{"url":null,"slug":"limit-less-is-more-for-instruction-tuning","title":"LIMIT: Less Is More for Instruction Tuning Across Evaluation Paradigms","date":"2023-11-22","arxiv_id":"2311.13133","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-diversity-matters-for-robust-instruction","title":"Data Diversity Matters for Robust Instruction Tuning","date":"2023-11-21","arxiv_id":"2311.14736","repositories_listed":0,"syntology":null},{"url":null,"slug":"traffic-sign-interpretation-in-real-road","title":"Traffic Sign Interpretation in Real Road Scene","date":"2023-11-17","arxiv_id":"2311.10793","repositories_listed":0,"syntology":null},{"url":null,"slug":"crispr-eliminating-bias-neurons-from-an","title":"Mitigating Biases for Instruction-following Language Models via Bias Neurons Elimination","date":"2023-11-16","arxiv_id":"2311.09627","repositories_listed":0,"syntology":null},{"url":null,"slug":"followeval-a-multi-dimensional-benchmark-for","title":"FollowEval: A Multi-Dimensional Benchmark for Assessing the Instruction-Following Capability of Large Language Models","date":"2023-11-16","arxiv_id":"2311.09829","repositories_listed":0,"syntology":null},{"url":null,"slug":"x-mark-towards-lossless-watermarking-through","title":"WatME: Towards Lossless Watermarking Through Lexical Redundancy","date":"2023-11-16","arxiv_id":"2311.09832","repositories_listed":0,"syntology":null},{"url":null,"slug":"generate-filter-and-fuse-query-expansion-via","title":"Can Query Expansion Improve Generalization of Strong Cross-Encoder Rankers?","date":"2023-11-15","arxiv_id":"2311.09175","repositories_listed":0,"syntology":null},{"url":null,"slug":"map-s-not-dead-yet-uncovering-true-language","title":"MAP's not dead yet: Uncovering true language model modes by conditioning away degeneracy","date":"2023-11-15","arxiv_id":"2311.08817","repositories_listed":0,"syntology":null},{"url":null,"slug":"mart-improving-llm-safety-with-multi-round","title":"MART: Improving LLM Safety with Multi-round Automatic Red-Teaming","date":"2023-11-13","arxiv_id":"2311.07689","repositories_listed":0,"syntology":null},{"url":null,"slug":"active-reasoning-in-an-open-world-environment","title":"Active Reasoning in an Open-World Environment","date":"2023-11-03","arxiv_id":"2311.02018","repositories_listed":0,"syntology":null},{"url":null,"slug":"cosmic-data-efficient-instruction-tuning-for","title":"COSMIC: Data Efficient Instruction-tuning For Speech In-Context Learning","date":"2023-11-03","arxiv_id":"2311.02248","repositories_listed":0,"syntology":null},{"url":null,"slug":"tensor-trust-interpretable-prompt-injection","title":"Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game","date":"2023-11-02","arxiv_id":"2311.01011","repositories_listed":0,"syntology":null},{"url":null,"slug":"cyclealign-iterative-distillation-from-black","title":"CycleAlign: Iterative Distillation from Black-box LLM to White-box Models for Better Human Alignment","date":"2023-10-25","arxiv_id":"2310.16271","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-coarse-political-stance","title":"Multilingual Coarse Political Stance Classification of Media. The Editorial Line of a ChatGPT and Bard Newspaper","date":"2023-10-25","arxiv_id":"2310.16269","repositories_listed":0,"syntology":null},{"url":null,"slug":"privately-aligning-language-models-with","title":"Privately Aligning Language Models with Reinforcement Learning","date":"2023-10-25","arxiv_id":"2310.16960","repositories_listed":0,"syntology":null},{"url":null,"slug":"analyzing-multilingual-competency-of-llms-in","title":"Analyzing Multilingual Competency of LLMs in Multi-Turn Instruction Following: A Case Study of Arabic","date":"2023-10-23","arxiv_id":"2310.14819","repositories_listed":0,"syntology":null},{"url":null,"slug":"lohoravens-a-long-horizon-language","title":"LoHoRavens: A Long-Horizon Language-Conditioned Benchmark for Robotic Tabletop Manipulation","date":"2023-10-18","arxiv_id":"2310.12020","repositories_listed":0,"syntology":null},{"url":null,"slug":"vera-vector-based-random-matrix-adaptation","title":"VeRA: Vector-based Random Matrix Adaptation","date":"2023-10-17","arxiv_id":"2310.11454","repositories_listed":0,"syntology":null},{"url":null,"slug":"gaining-wisdom-from-setbacks-aligning-large","title":"Gaining Wisdom from Setbacks: Aligning Large Language Models via Mistake Analysis","date":"2023-10-16","arxiv_id":"2310.10477","repositories_listed":0,"syntology":null},{"url":null,"slug":"mastering-robot-manipulation-with-multimodal","title":"Mastering Robot Manipulation with Multimodal Prompts through Pretraining and Multi-task Fine-tuning","date":"2023-10-14","arxiv_id":"2310.09676","repositories_listed":0,"syntology":null},{"url":null,"slug":"groot-learning-to-follow-instructions-by","title":"GROOT: Learning to Follow Instructions by Watching Gameplay Videos","date":"2023-10-12","arxiv_id":"2310.08235","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-better-evaluation-of-instruction","title":"Towards Better Evaluation of Instruction-Following: A Case-Study in Summarization","date":"2023-10-12","arxiv_id":"2310.08394","repositories_listed":0,"syntology":null},{"url":null,"slug":"parrot-enhancing-multi-turn-chat-models-by","title":"Parrot: Enhancing Multi-Turn Instruction Following for Large Language Models","date":"2023-10-11","arxiv_id":"2310.07301","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-foundation-models-for-learning-on","title":"From Supervised to Generative: A Novel Paradigm for Tabular Deep Learning with Large Language Models","date":"2023-10-11","arxiv_id":"2310.07338","repositories_listed":0,"syntology":null},{"url":null,"slug":"heap-hierarchical-policies-for-web-actions","title":"SteP: Stacked LLM Policies for Web Actions","date":"2023-10-05","arxiv_id":"2310.03720","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-and-improving-generator","title":"Benchmarking and Improving Generator-Validator Consistency of Language Models","date":"2023-10-03","arxiv_id":"2310.01846","repositories_listed":0,"syntology":null},{"url":null,"slug":"slm-bridge-the-thin-gap-between-speech-and","title":"SLM: Bridge the thin gap between speech and text foundation models","date":"2023-09-30","arxiv_id":"2310.00230","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-specialization-uncovering-latent","title":"Self-Specialization: Uncovering Latent Expertise within Large Language Models","date":"2023-09-29","arxiv_id":"2310.00160","repositories_listed":0,"syntology":null},{"url":null,"slug":"llms-as-counterfactual-explanation-modules","title":"Towards LLM-guided Causal Explainability for Black-box Text Classifiers","date":"2023-09-23","arxiv_id":"2309.13340","repositories_listed":0,"syntology":null},{"url":null,"slug":"frustrated-with-code-quality-issues-llms-can","title":"Frustrated with Code Quality Issues? LLMs can Help!","date":"2023-09-22","arxiv_id":"2309.12938","repositories_listed":0,"syntology":null},{"url":null,"slug":"instruction-following-speech-recognition","title":"Instruction-Following Speech Recognition","date":"2023-09-18","arxiv_id":"2309.09843","repositories_listed":0,"syntology":null},{"url":null,"slug":"sorted-llama-unlocking-the-potential-of","title":"Sorted LLaMA: Unlocking the Potential of Intermediate Layers of Large Language Models for Dynamic Inference","date":"2023-09-16","arxiv_id":"2309.08968","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantifying-and-attributing-the-hallucination","title":"Quantifying and Attributing the Hallucination of Large Language Models via Association Analysis","date":"2023-09-11","arxiv_id":"2309.05217","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-finetuning-large-language-models","title":"Efficient Finetuning Large Language Models For Vietnamese Chatbot","date":"2023-09-09","arxiv_id":"2309.04646","repositories_listed":0,"syntology":null},{"url":"/paper/improving-open-information-extraction-with","slug":"improving-open-information-extraction-with","title":"Improving Open Information Extraction with Large Language Models: A Study on Demonstration Uncertainty","date":"2023-09-07","arxiv_id":"2309.03433","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-driven-grounding-large-language-model","title":"Self-driven Grounding: Large Language Model Agents with Automatical Language-aligned Skill Learning","date":"2023-09-04","arxiv_id":"2309.01352","repositories_listed":0,"syntology":null},{"url":null,"slug":"factllama-optimizing-instruction-following","title":"FactLLaMA: Optimizing Instruction-Following Language Models with External Knowledge for Automated Fact-Checking","date":"2023-09-01","arxiv_id":"2309.00240","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-the-robustness-to-instructions-of","title":"Evaluating the Robustness to Instructions of Large Language Models","date":"2023-08-28","arxiv_id":"2308.14306","repositories_listed":0,"syntology":null},{"url":null,"slug":"medalign-a-clinician-generated-dataset-for","title":"MedAlign: A Clinician-Generated Dataset for Instruction Following with Electronic Medical Records","date":"2023-08-27","arxiv_id":"2308.14089","repositories_listed":0,"syntology":null},{"url":null,"slug":"unidoc-a-universal-large-multimodal-model-for","title":"UniDoc: A Universal Large Multimodal Model for Simultaneous Text Detection, Recognition, Spotting and Understanding","date":"2023-08-19","arxiv_id":"2308.11592","repositories_listed":0,"syntology":null},{"url":null,"slug":"pumgpt-a-large-vision-language-model-for","title":"PUMGPT: A Large Vision-Language Model for Product Understanding","date":"2023-08-18","arxiv_id":"2308.09568","repositories_listed":0,"syntology":null},{"url":null,"slug":"llama-e-empowering-e-commerce-authoring-with","title":"LLaMA-E: Empowering E-commerce Authoring with Object-Interleaved Instruction Following","date":"2023-08-09","arxiv_id":"2308.04913","repositories_listed":0,"syntology":null},{"url":null,"slug":"ether-aligning-emergent-communication-for","title":"ETHER: Aligning Emergent Communication for Hindsight Experience Replay","date":"2023-07-28","arxiv_id":"2307.15494","repositories_listed":0,"syntology":null},{"url":null,"slug":"instruction-following-evaluation-through","title":"Instruction-following Evaluation through Verbalizer Manipulation","date":"2023-07-20","arxiv_id":"2307.10558","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-censorship-a-machine-learning-challenge","title":"LLM Censorship: A Machine Learning Challenge or a Computer Security Problem?","date":"2023-07-20","arxiv_id":"2307.10719","repositories_listed":0,"syntology":null},{"url":null,"slug":"chatspot-bootstrapping-multimodal-llms-via","title":"ChatSpot: Bootstrapping Multimodal LLMs via Precise Referring Instruction Tuning","date":"2023-07-18","arxiv_id":"2307.09474","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-the-integration-of-large-language","title":"Exploring the Integration of Large Language Models into Automatic Speech Recognition Systems: An Empirical Study","date":"2023-07-13","arxiv_id":"2307.06530","repositories_listed":0,"syntology":null},{"url":null,"slug":"instruction-mining-high-quality-instruction","title":"Instruction Mining: Instruction Data Selection for Tuning Large Language Models","date":"2023-07-12","arxiv_id":"2307.06290","repositories_listed":0,"syntology":null},{"url":null,"slug":"becoming-self-instruct-introducing-early","title":"Becoming self-instruct: introducing early stopping criteria for minimal instruct tuning","date":"2023-07-05","arxiv_id":"2307.03692","repositories_listed":0,"syntology":null},{"url":null,"slug":"goal-representations-for-instruction","title":"Goal Representations for Instruction Following: A Semi-Supervised Language Interface to Control","date":"2023-06-30","arxiv_id":"2307.00117","repositories_listed":0,"syntology":null},{"url":null,"slug":"kite-keypoint-conditioned-policies-for","title":"KITE: Keypoint-Conditioned Policies for Semantic Manipulation","date":"2023-06-29","arxiv_id":"2306.16605","repositories_listed":0,"syntology":null},{"url":null,"slug":"mo-vln-a-multi-task-benchmark-for-open-set","title":"CorNav: Autonomous Agent with Self-Corrected Planning for Zero-Shot Vision-and-Language Navigation","date":"2023-06-17","arxiv_id":"2306.10322","repositories_listed":0,"syntology":null},{"url":null,"slug":"are-you-telling-me-to-put-glasses-on-the-dog","title":"\"Are you telling me to put glasses on the dog?'' Content-Grounded Annotation of Instruction Clarification Requests in the CoDraw Dataset","date":"2023-06-04","arxiv_id":"2306.02377","repositories_listed":0,"syntology":null},{"url":null,"slug":"controllable-text-to-image-generation-with","title":"Controllable Text-to-Image Generation with GPT-4","date":"2023-05-29","arxiv_id":"2305.18583","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-monte-carlo-language-model-pipeline-for","title":"A Monte Carlo Language Model Pipeline for Zero-Shot Sociopolitical Event Extraction","date":"2023-05-24","arxiv_id":"2305.15051","repositories_listed":0,"syntology":null},{"url":null,"slug":"sail-search-augmented-instruction-learning","title":"SAIL: Search-Augmented Instruction Learning","date":"2023-05-24","arxiv_id":"2305.15225","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-task-instruction-tuning-of-llama-for","title":"Multi-Task Instruction Tuning of LLaMa for Specific Scenarios: A Preliminary Study on Writing Assistance","date":"2023-05-22","arxiv_id":"2305.13225","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-web-navigation-with-instruction","title":"Multimodal Web Navigation with Instruction-Finetuned Foundation Models","date":"2023-05-19","arxiv_id":"2305.11854","repositories_listed":0,"syntology":null},{"url":null,"slug":"recommendation-as-instruction-following-a","title":"Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approach","date":"2023-05-11","arxiv_id":"2305.07001","repositories_listed":0,"syntology":null},{"url":null,"slug":"accessible-instruction-following-agent","title":"Accessible Instruction-Following Agent","date":"2023-05-08","arxiv_id":"2305.06358","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-enhanced-agents-for-interactive","title":"Knowledge-enhanced Agents for Interactive Text Games","date":"2023-05-08","arxiv_id":"2305.05091","repositories_listed":0,"syntology":null},{"url":null,"slug":"retrieval-augmented-chest-x-ray-report","title":"Retrieval Augmented Chest X-Ray Report Generation using OpenAI GPT models","date":"2023-05-05","arxiv_id":"2305.03660","repositories_listed":0,"syntology":null},{"url":null,"slug":"plan-eliminate-and-track-language-models-are","title":"Plan, Eliminate, and Track -- Language Models are Good Teachers for Embodied Agents","date":"2023-05-03","arxiv_id":"2305.02412","repositories_listed":0,"syntology":null},{"url":null,"slug":"embodied-concept-learner-self-supervised","title":"Embodied Concept Learner: Self-supervised Learning of Concepts and Mapping through Instruction Following","date":"2023-04-07","arxiv_id":"2304.03767","repositories_listed":0,"syntology":null},{"url":null,"slug":"chatgpt-is-a-knowledgeable-but-inexperienced","title":"ChatGPT is a Knowledgeable but Inexperienced Solver: An Investigation of Commonsense Problem in Large Language Models","date":"2023-03-29","arxiv_id":"2303.16421","repositories_listed":0,"syntology":null},{"url":null,"slug":"natural-language-conditioned-reinforcement","title":"Natural Language-conditioned Reinforcement Learning with Inside-out Task Language Development and Translation","date":"2023-02-18","arxiv_id":"2302.09368","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-programmatic-behavior-of-llms-dual","title":"Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks","date":"2023-02-11","arxiv_id":"2302.05733","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-internet-scale-vision-language","title":"Distilling Internet-Scale Vision-Language Models into Embodied Agents","date":"2023-01-29","arxiv_id":"2301.12507","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-sequential-generative-models-for","title":"Multimodal Sequential Generative Models for Semi-Supervised Language Instruction Following","date":"2022-12-29","arxiv_id":"2301.00676","repositories_listed":0,"syntology":null},{"url":null,"slug":"clip-nav-using-clip-for-zero-shot-vision-and","title":"CLIP-Nav: Using CLIP for Zero-Shot Vision-and-Language Navigation","date":"2022-11-30","arxiv_id":"2211.16649","repositories_listed":0,"syntology":null},{"url":"/paper/ugif-ui-grounded-instruction-following","slug":"ugif-ui-grounded-instruction-following","title":"UGIF: UI Grounded Instruction Following","date":"2022-11-14","arxiv_id":"2211.07615","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompter-utilizing-large-language-model","title":"Prompter: Utilizing Large Language Model Prompting for a Data Efficient Embodied Instruction Following","date":"2022-11-07","arxiv_id":"2211.03267","repositories_listed":0,"syntology":null},{"url":"/paper/a-new-path-scaling-vision-and-language","slug":"a-new-path-scaling-vision-and-language","title":"A New Path: Scaling Vision-and-Language Navigation with Synthetic Instructions and Imitation Learning","date":"2022-10-06","arxiv_id":"2210.03112","repositories_listed":0,"syntology":null},{"url":null,"slug":"iterative-vision-and-language-navigation","title":"Iterative Vision-and-Language Navigation","date":"2022-10-06","arxiv_id":"2210.03087","repositories_listed":0,"syntology":null}],"record_sha256":"46e490b69f3f42d7214c4b79b4d277f3539fcd037b7f0b51389fbc946bd6e8a0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}