{"list":"other","total":76,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2303.04137","title":"Diffusion Policy: Visuomotor Policy Learning via Action Diffusion","created":"2023-03-07","cited_by_count":2838},{"id":"2410.24164","title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","created":"2024-10-31","cited_by_count":2407},{"id":"2408.03314","title":"Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters","created":"2024-08-06","cited_by_count":1986},{"id":"2504.16054","title":"$\\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization","created":"2025-04-22","cited_by_count":1761},{"id":"2405.12213","title":"Octo: An Open-Source Generalist Robot Policy","created":"2024-05-20","cited_by_count":1484},{"id":"2306.03310","title":"LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning","created":"2023-06-05","cited_by_count":1410},{"id":"2503.14734","title":"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots","created":"2025-03-18","cited_by_count":1225},{"id":"2310.13548","title":"Towards Understanding Sycophancy in Language Models","created":"2023-10-20","cited_by_count":1040},{"id":"2502.19645","title":"Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success","created":"2025-02-27","cited_by_count":883},{"id":"2403.12945","title":"DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset","created":"2024-03-19","cited_by_count":852},{"id":"2506.09985","title":"V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning","created":"2025-06-11","cited_by_count":809},{"id":"2410.07864","title":"RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation","created":"2024-10-10","cited_by_count":691},{"id":"1909.12271","title":"RLBench: The Robot Learning Benchmark & Learning Environment","created":"2019-09-26","cited_by_count":689},{"id":"2501.09747","title":"FAST: Efficient Action Tokenization for Vision-Language-Action Models","created":"2025-01-16","cited_by_count":665},{"id":"2501.15830","title":"SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model","created":"2025-01-27","cited_by_count":519},{"id":"2503.22020","title":"CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models","created":"2025-03-27","cited_by_count":451},{"id":"2506.21539","title":"WorldVLA: Towards Autoregressive Action World Model","created":"2025-06-26","cited_by_count":367},{"id":"2407.08693","title":"Robotic Control via Embodied Chain-of-Thought Reasoning","created":"2024-07-11","cited_by_count":346},{"id":"2412.10345","title":"TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies","created":"2024-12-13","cited_by_count":304},{"id":"2209.00647","title":"Visual Prompting via Image Inpainting","created":"2022-09-01","cited_by_count":250},{"id":"2402.15852","title":"NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation","created":"2024-02-24","cited_by_count":233},{"id":"2502.19417","title":"Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models","created":"2025-02-26","cited_by_count":221},{"id":"2412.04453","title":"NaVILA: Legged Robot Vision-Language-Action Model for Navigation","created":"2024-12-05","cited_by_count":211},{"id":"2511.00062","title":"World Simulation with Video Foundation Models for Physical AI","created":"2025-10-28","cited_by_count":200},{"id":"2502.05855","title":"DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control","created":"2025-02-09","cited_by_count":195},{"id":"2306.15724","title":"REFLECT: Summarizing Robot Experiences for Failure Explanation and Correction","created":"2023-06-27","cited_by_count":175},{"id":"2507.16815","title":"ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning","created":"2025-07-22","cited_by_count":156},{"id":"2403.09227","title":"BEHAVIOR-1K: A Human-Centered, Embodied AI Benchmark with 1,000 Everyday Activities and Realistic Simulation","created":"2024-03-14","cited_by_count":148},{"id":"2303.07280","title":"Vision-Language Models as Success Detectors","created":"2023-03-13","cited_by_count":142},{"id":"2506.19850","title":"Unified Vision-Language-Action Model","created":"2025-06-24","cited_by_count":134},{"id":"2410.00371","title":"AHA: A Vision-Language-Model for Detecting and Reasoning Over Failures in Robotic Manipulation","created":"2024-10-01","cited_by_count":125},{"id":"2502.14420","title":"ChatVLA: Unified Multimodal Understanding and Robot Control with Vision-Language-Action Model","created":"2025-02-20","cited_by_count":113},{"id":"2410.20290","title":"Fast Best-of-N Decoding via Speculative Rejection","created":"2024-10-26","cited_by_count":112},{"id":"2410.13816","title":"Steering Your Generalists: Improving Robotic Foundation Models via Value Guidance","created":"2024-10-17","cited_by_count":106},{"id":"2211.12498","title":"Touch and Go: Learning from Human-Collected Vision and Touch","created":"2022-11-22","cited_by_count":87},{"id":"1903.02547","title":"Tactical Rewind: Self-Correction via Backtracking in Vision-and-Language Navigation","created":"2019-03-06","cited_by_count":81},{"id":"2508.21046","title":"CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification","created":"2025-08-28","cited_by_count":74},{"id":"2410.04640","title":"Unpacking Failure Modes of Generative Policies: Runtime Monitoring of Consistency and Progress","created":"2024-10-06","cited_by_count":69},{"id":"2407.08735","title":"Real-Time Anomaly Detection and Reactive Planning with Large Language Models","created":"2024-07-11","cited_by_count":68},{"id":"2108.04718","title":"Sampling-Based Approximations to Minimum Bayes Risk Decoding for Neural Machine Translation","created":"2021-08-10","cited_by_count":65},{"id":"2307.00329","title":"DoReMi: Grounding Language Model by Detecting and Recovering from Plan-Execution Misalignment","created":"2023-07-01","cited_by_count":61},{"id":"2506.17811","title":"RoboMonkey: Scaling Test-Time Sampling and Verification for Vision-Language-Action Models","created":"2025-06-21","cited_by_count":61},{"id":"2112.05251","title":"Error-Aware Imitation Learning from Teleoperation Data for Mobile Manipulation","created":"2021-12-09","cited_by_count":59},{"id":"2505.08243","title":"Training Strategies for Efficient Embodied Reasoning","created":"2025-05-13","cited_by_count":55},{"id":"2403.13438","title":"SpatialPIN: Enhancing Spatial Reasoning Capabilities of Vision-Language Models through Prompting and Interacting 3D Priors","created":"2024-03-18","cited_by_count":54},{"id":"2503.08558","title":"Can We Detect Failures Without Failure Data? Uncertainty-Aware Runtime Failure Detection for Imitation Learning Policies","created":"2025-03-11","cited_by_count":52},{"id":"2505.21906","title":"ChatVLA-2: Vision-Language-Action Model with Open-World Embodied Reasoning from Pretrained Knowledge","created":"2025-05-28","cited_by_count":49},{"id":"2508.19958","title":"Long-VLA: Unleashing Long-Horizon Capability of Vision Language Action Model for Robot Manipulation","created":"2025-08-27","cited_by_count":48},{"id":"2502.16707","title":"Reflective Planning: Vision-Language Models for Multi-Stage Long-Horizon Robotic Manipulation","created":"2025-02-23","cited_by_count":42},{"id":"2310.17552","title":"Model-Based Runtime Monitoring with Interactive Imitation Learning","created":"2023-10-26","cited_by_count":38},{"id":"2410.22689","title":"Multi-Task Interactive Robot Fleet Learning with Visual World Models","created":"2024-10-30","cited_by_count":36},{"id":"2410.01971","title":"Run-time Observation Interventions Make Vision-Language-Action Models More Visually Robust","created":"2024-10-02","cited_by_count":33},{"id":"2503.10069","title":"SmartWay: Enhanced Waypoint Prediction and Backtracking for Zero-Shot Vision-and-Language Navigation","created":"2025-03-13","cited_by_count":29},{"id":"2311.08380","title":"Direct Preference Optimization for Neural Machine Translation with Minimum Bayes Risk Decoding","created":"2023-11-14","cited_by_count":28},{"id":"2202.05894","title":"Failure Prediction with Statistical Guarantees for Vision-Based Robot Control","created":"2022-02-11","cited_by_count":21},{"id":"2210.10765","title":"When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learning","created":"2022-10-19","cited_by_count":21},{"id":"2405.17418","title":"A Self-Correcting Vision-Language-Action Model for Fast and Slow System Manipulation","created":"2024-05-27","cited_by_count":21},{"id":"2504.00907","title":"Grounding Multimodal LLMs to Embodied Agents that Ask for Help with Reinforcement Learning","created":"2025-04-01","cited_by_count":21},{"id":"2408.16228","title":"Policy Adaptation via Language Optimization: Decomposing Tasks for Few-Shot Imitation","created":"2024-08-29","cited_by_count":18},{"id":"2302.04334","title":"Asking for Help: Failure Prediction in Behavioral Cloning through Value Approximation","created":"2023-02-08","cited_by_count":16},{"id":"2407.15343","title":"Improving Minimum Bayes Risk Decoding with Multi-Prompt","created":"2024-07-22","cited_by_count":13},{"id":"2304.07537","title":"Gradient-less Federated Gradient Boosting Trees with Learnable Learning Rates","created":"2023-04-15","cited_by_count":12},{"id":"2509.14138","title":"SeqVLA: Sequential Task Execution for Long-Horizon Manipulation with Completion-Aware Vision-Language-Action Model","created":"2025-09-17","cited_by_count":10},{"id":"2409.17431","title":"On Extending Direct Preference Optimization to Accommodate Ties","created":"2024-09-25","cited_by_count":8},{"id":"2406.15917","title":"To Err is Robotic: Rapid Value-Based Trial-and-Error during Deployment","created":"2024-06-22","cited_by_count":7},{"id":"2510.23495","title":"COOPERA: Continual Open-Ended Human-Robot Assistance","created":"2025-10-27","cited_by_count":7},{"id":"2509.14889","title":"CollabVLA: Self-Reflective Vision-Language-Action Model Dreaming Together with Human","created":"2025-09-18","cited_by_count":6},{"id":"2509.24768","title":"IA-VLA: Input Augmentation for Vision-Language-Action models in settings with semantically complex tasks","created":"2025-09-29","cited_by_count":4},{"id":"2305.11236","title":"Efficient Vertical Federated Learning with Secure Aggregation","created":"2023-05-18","cited_by_count":3},{"id":"2510.14968","title":"RDD: Retrieval-Based Demonstration Decomposer for Planner Alignment in Long-Horizon Tasks","created":"2025-10-16","cited_by_count":3},{"id":"2503.06060","title":"STAR: A Foundation Model-driven Framework for Robust Task Planning and Failure Recovery in Robotic Systems","created":"2025-03-08","cited_by_count":2}],"next_cursor":null}