{"total":75,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744,"area":"wm"},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459,"area":"lr"},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288,"area":null},{"id":"2307.05973","title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","created":"2023-07-12","cited_by_count":750,"area":null},{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447,"area":"alignment"},{"id":"2311.12320","title":"A Survey on Multimodal Large Language Models for Autonomous Driving","created":"2023-11-21","cited_by_count":290,"area":"mllm"},{"id":"2204.02329","title":"Can language models learn from explanations in context?","created":"2022-04-05","cited_by_count":249,"area":null},{"id":"2202.01771","title":"Pre-Trained Language Models for Interactive Decision-Making","created":"2022-02-03","cited_by_count":221,"area":null},{"id":"2103.05247","title":"Pretrained Transformers as Universal Computation Engines","created":"2021-03-09","cited_by_count":162,"area":null},{"id":"2203.07281","title":"GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Models","created":"2022-03-14","cited_by_count":127,"area":null},{"id":"2403.12910","title":"Yell At Your Robot: Improving On-the-Fly from Language Corrections","created":"2024-03-19","cited_by_count":124,"area":"mllm"},{"id":"2309.05660","title":"Hypothesis Search: Inductive Reasoning with Language Models","created":"2023-09-11","cited_by_count":120,"area":"lr"},{"id":"2110.01517","title":"Skill Induction and Planning with Latent Language","created":"2021-10-04","cited_by_count":99,"area":null},{"id":"2310.08559","title":"Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement","created":"2023-10-12","cited_by_count":89,"area":"lr"},{"id":"2210.08773","title":"Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training","created":"2022-10-17","cited_by_count":88,"area":null},{"id":"2102.02201","title":"When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Data","created":"2021-02-03","cited_by_count":75,"area":null},{"id":"2202.08938","title":"Improving Intrinsic Exploration with Language Abstractions","created":"2022-02-17","cited_by_count":49,"area":null},{"id":"2310.19791","title":"LILO: Learning Interpretable Libraries by Compressing and Documenting Code","created":"2023-10-30","cited_by_count":49,"area":null},{"id":"2106.11053","title":"Leveraging Language to Learn Program Abstractions and Search Heuristics","created":"2021-06-18","cited_by_count":45,"area":null},{"id":"2312.04372","title":"LaMPilot: An Open Benchmark Dataset for Autonomous Driving with Language Model Programs","created":"2023-12-07","cited_by_count":45,"area":"driving"},{"id":"2205.12258","title":"History Compression via Language Models in Reinforcement Learning","created":"2022-05-24","cited_by_count":39,"area":null},{"id":"2112.03753","title":"Tell me why! Explanations support learning relational and causal structure","created":"2021-12-07","cited_by_count":36,"area":null},{"id":"2106.07824","title":"Communicating Natural Programs to Humans and Machines","created":"2021-06-15","cited_by_count":35,"area":null},{"id":"2312.07551","title":"Language Model Alignment with Elastic Reset","created":"2023-12-06","cited_by_count":34,"area":"alignment"},{"id":"2103.05823","title":"Fast and flexible: Human program induction in abstract reasoning tasks","created":"2021-03-10","cited_by_count":33,"area":null},{"id":"2208.12208","title":"Contrastive Audio-Language Learning for Music","created":"2022-08-25","cited_by_count":33,"area":null},{"id":"2211.03318","title":"Fixing Model Bugs with Natural Language Patches","created":"2022-11-07","cited_by_count":33,"area":null},{"id":"2104.08142","title":"Supervising Model Attention with Human Explanations for Robust Natural Language Inference","created":"2021-04-16","cited_by_count":29,"area":null},{"id":"2102.07024","title":"Interactive Learning from Activity Description","created":"2021-02-13","cited_by_count":26,"area":null},{"id":"2304.13826","title":"Programmatically Grounded, Compositionally Generalizable Robotic Manipulation","created":"2023-04-26","cited_by_count":26,"area":null},{"id":"2306.11886","title":"SPRINT: Scalable Policy Pre-Training via Language Instruction Relabeling","created":"2023-06-20","cited_by_count":24,"area":null},{"id":"2209.13020","title":"Law Informs Code: A Legal Informatics Approach to Aligning Artificial Intelligence with Humans","created":"2022-09-14","cited_by_count":23,"area":null},{"id":"2206.07870","title":"How to talk so AI will learn: Instructions, descriptions, and autonomy","created":"2022-06-16","cited_by_count":22,"area":null},{"id":"2306.02797","title":"Human-like Few-Shot Learning via Bayesian Reasoning over Natural Language","created":"2023-06-05","cited_by_count":22,"area":"lr"},{"id":"2409.08466","title":"Explaining Datasets in Words: Statistical Models with Natural Language Parameters","created":"2024-09-13","cited_by_count":21,"area":null},{"id":"2205.11558","title":"Using Natural Language and Program Abstractions to Instill Human Inductive Biases in Machines","created":"2022-05-23","cited_by_count":20,"area":null},{"id":"2202.05839","title":"Abstraction for Deep Reinforcement Learning","created":"2022-02-10","cited_by_count":19,"area":null},{"id":"2210.01946","title":"Affection: Learning Affective Explanations for Real-World Visual Data","created":"2022-10-04","cited_by_count":19,"area":null},{"id":"2306.09312","title":"Semantic HELM: A Human-Readable Memory for Reinforcement Learning","created":"2023-06-15","cited_by_count":17,"area":null},{"id":"2104.12709","title":"Rich Semantics Improve Few-shot Learning","created":"2021-04-26","cited_by_count":15,"area":null},{"id":"2106.02972","title":"Zero-shot Task Adaptation using Natural Language","created":"2021-06-05","cited_by_count":15,"area":"offlinerl"},{"id":"2506.10341","title":"Formalizing Learning from Language Feedback with Provable Guarantees","created":"2025-06-12","cited_by_count":13,"area":null},{"id":"2211.15521","title":"G^3: Geolocation via Guidebook Grounding","created":"2022-11-28","cited_by_count":12,"area":null},{"id":"2306.08042","title":"FLamE: Few-shot Learning from Natural Language Explanations","created":"2023-06-13","cited_by_count":10,"area":null},{"id":"2312.04881","title":"Predictive Chemistry Augmented with Text Retrieval","created":"2023-12-08","cited_by_count":10,"area":null},{"id":"2204.07142","title":"CLUES: A Benchmark for Learning Classifiers using Natural Language Explanations","created":"2022-04-14","cited_by_count":9,"area":null},{"id":"2307.11922","title":"Selective Perception: Optimizing State Descriptions with Reinforcement Learning for Language Model Actors","created":"2023-07-21","cited_by_count":9,"area":null},{"id":"2104.07219","title":"Multitasking Inhibits Semantic Drift","created":"2021-04-15","cited_by_count":8,"area":null},{"id":"2301.10095","title":"Large Language Models as Fiduciaries: A Case Study Toward Robustly Communicating With Artificial Intelligence Through Legal Standards","created":"2023-01-24","cited_by_count":8,"area":null},{"id":"2306.12554","title":"Improving Long-Horizon Imitation Through Instruction Prediction","created":"2023-06-21","cited_by_count":8,"area":null},{"id":"2310.12344","title":"LACMA: Language-Aligning Contrastive Learning with Meta-Actions for Embodied Instruction Following","created":"2023-10-18","cited_by_count":8,"area":null},{"id":"2505.21354","title":"Leveraging Large Language Models for Bengali Math Word Problem Solving with Chain of Thought Reasoning","created":"2025-05-27","cited_by_count":8,"area":"lr"},{"id":"2104.08793","title":"SalKG: Learning From Knowledge Graph Explanations for Commonsense Reasoning","created":"2021-04-18","cited_by_count":7,"area":null},{"id":"2203.04806","title":"One-Shot Learning from a Demonstration with Hierarchical Latent Language","created":"2022-03-09","cited_by_count":6,"area":null},{"id":"2204.01437","title":"Disentangling Abstraction from Statistical Pattern Matching in Human and Machine Learning","created":"2022-04-04","cited_by_count":6,"area":null},{"id":"2207.03133","title":"Improving Few-Shot Image Classification Using Machine- and User-Generated Natural Language Descriptions","created":"2022-07-07","cited_by_count":6,"area":null},{"id":"2406.08572","title":"LLM-assisted Concept Discovery: Automatically Identifying and Explaining Neuron Functions","created":"2024-06-12","cited_by_count":6,"area":null},{"id":"2210.02615","title":"Learning to Reason With Relational Abstractions","created":"2022-10-06","cited_by_count":5,"area":"lr"},{"id":"2409.04512","title":"Chain-of-Translation Prompting (CoTR): A Novel Prompting Technique for Low Resource Languages","created":"2024-09-06","cited_by_count":5,"area":null},{"id":"2105.12804","title":"TexRel: a Green Family of Datasets for Emergent Communications on Relations","created":"2021-05-26","cited_by_count":3,"area":null},{"id":"2111.01785","title":"PatchGame: Learning to Signal Mid-level Patches in Referential Games","created":"2021-11-02","cited_by_count":3,"area":null},{"id":"2201.10222","title":"Explanatory Learning: Beyond Empiricism in Neural Networks","created":"2022-01-25","cited_by_count":3,"area":null},{"id":"2210.11000","title":"Visual-Semantic Contrastive Alignment for Few-Shot Image Classification","created":"2022-10-20","cited_by_count":3,"area":null},{"id":"2306.08400","title":"Simple Embodied Language Learning as a Byproduct of Meta-Reinforcement Learning","created":"2023-06-14","cited_by_count":3,"area":null},{"id":"2202.13100","title":"SemSup: Semantic Supervision for Simple and Scalable Zero-shot Generalization","created":"2022-02-26","cited_by_count":2,"area":null},{"id":"2203.11197","title":"Teachable Reinforcement Learning via Advice Distillation","created":"2022-03-19","cited_by_count":2,"area":"offlinerl"},{"id":"2212.09104","title":"LaSQuE: Improved Zero-Shot Classification from Explanations Through Quantifier Modeling and Curriculum Learning","created":"2022-12-18","cited_by_count":2,"area":null},{"id":"2301.09770","title":"Language-guided Task Adaptation for Imitation Learning","created":"2023-01-24","cited_by_count":2,"area":"offlinerl"},{"id":"2311.07538","title":"Leveraging Multiple Teachers for Test-Time Adaptation of Language-Guided Classifiers","created":"2023-11-13","cited_by_count":2,"area":null},{"id":"2506.11475","title":"AutoGen Driven Multi Agent Framework for Iterative Crime Data Analysis and Prediction","created":"2025-06-13","cited_by_count":2,"area":"agents"},{"id":"2602.20517","title":"Inner Speech as Behavior Guides: Steerable Imitation of Diverse Behaviors for Human-AI coordination","created":"2026-02-24","cited_by_count":2,"area":null},{"id":"2608.18008","title":"Policy-Invariant Reward Shaping from LLM Feedback: A Framework for Hybrid RL Agents","created":"2026-08-18","cited_by_count":1,"area":"agents"},{"id":"2406.15816","title":"Reading Is Believing: Revisiting Language Bottleneck Models for Image Classification","created":"2024-06-22","cited_by_count":0,"area":null},{"id":"2510.07058","title":"Concept Retrieval -- What and How?","created":"2025-10-08","cited_by_count":0,"area":null},{"id":"2609.36867","title":"State Trace Rationale As Auxiliary Task in Reinforcement Learning","created":"2026-09-29","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}