{"list":"other","total":69,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"2405.12213","title":"Octo: An Open-Source Generalist Robot Policy","created":"2024-05-20","cited_by_count":1484},{"id":"2209.14687","title":"Diffusion Posterior Sampling for General Noisy Inverse Problems","created":"2022-09-29","cited_by_count":1416},{"id":"2503.14734","title":"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots","created":"2025-03-18","cited_by_count":1225},{"id":"2310.08864","title":"Open X-Embodiment: Robotic Learning Datasets and RT-X Models","created":"2023-10-13","cited_by_count":862},{"id":"2308.12952","title":"BridgeData V2: A Dataset for Robot Learning at Scale","created":"2023-08-24","cited_by_count":657},{"id":"2206.01714","title":"Compositional Visual Generation with Composable Diffusion Models","created":"2022-06-03","cited_by_count":624},{"id":"2112.01071","title":"Extract Free Dense Labels from CLIP","created":"2021-12-02","cited_by_count":583},{"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":"2312.08344","title":"FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects","created":"2023-12-13","cited_by_count":429},{"id":"2406.02523","title":"RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots","created":"2024-06-04","cited_by_count":407},{"id":"2402.10329","title":"Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots","created":"2024-02-15","cited_by_count":394},{"id":"2409.01652","title":"ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation","created":"2024-09-03","cited_by_count":315},{"id":"2312.05251","title":"Reconstructing Hands in 3D with Transformers","created":"2023-12-08","cited_by_count":306},{"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":"2511.14759","title":"$\\pi^{*}_{0.6}$: a VLA That Learns From Experience","created":"2025-11-18","cited_by_count":303},{"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":"2302.11552","title":"Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMC","created":"2023-02-22","cited_by_count":220},{"id":"2509.20328","title":"Video models are zero-shot learners and reasoners","created":"2025-09-24","cited_by_count":220},{"id":"2506.07339","title":"Real-Time Execution of Action Chunking Flow Policies","created":"2025-06-09","cited_by_count":216},{"id":"2508.07917","title":"MolmoAct: Action Reasoning Models that can Reason in Space","created":"2025-08-11","cited_by_count":197},{"id":"2508.19236","title":"MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation","created":"2025-08-26","cited_by_count":192},{"id":"2412.18194","title":"VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Tasks","created":"2024-12-24","cited_by_count":175},{"id":"2506.15799","title":"Steering Your Diffusion Policy with Latent Space Reinforcement Learning","created":"2025-06-18","cited_by_count":169},{"id":"2505.17016","title":"Interactive Post-Training for Vision-Language-Action Models","created":"2025-05-22","cited_by_count":135},{"id":"2510.12276","title":"Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model","created":"2025-10-14","cited_by_count":134},{"id":"2308.07931","title":"Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation","created":"2023-07-27","cited_by_count":130},{"id":"2405.01527","title":"Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation","created":"2024-05-02","cited_by_count":124},{"id":"2410.13816","title":"Steering Your Generalists: Improving Robotic Foundation Models via Value Guidance","created":"2024-10-17","cited_by_count":106},{"id":"2410.13882","title":"Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation Model","created":"2024-10-03","cited_by_count":96},{"id":"2510.03342","title":"Gemini Robotics 1.5: Pushing the Frontier of Generalist Robots with Advanced Embodied Reasoning, Thinking, and Motion Transfer","created":"2025-10-02","cited_by_count":87},{"id":"2510.21890","title":"The Principles of Diffusion Models","created":"2025-10-24","cited_by_count":76},{"id":"2406.08474","title":"Real2Code: Reconstruct Articulated Objects via Code Generation","created":"2024-06-12","cited_by_count":69},{"id":"2410.16499","title":"SINGAPO: Single Image Controlled Generation of Articulated Parts in Objects","created":"2024-10-21","cited_by_count":69},{"id":"2503.08136","title":"FlowDPS: Flow-Driven Posterior Sampling for Inverse Problems","created":"2025-03-11","cited_by_count":68},{"id":"2510.00406","title":"VLA-RFT: Vision-Language-Action Reinforcement Fine-tuning with Verified Rewards in World Simulators","created":"2025-10-01","cited_by_count":67},{"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":"2506.08440","title":"TGRPO :Fine-tuning Vision-Language-Action Model via Trajectory-wise Group Relative Policy Optimization","created":"2025-06-10","cited_by_count":49},{"id":"2404.01223","title":"Feature Splatting: Language-Driven Physics-Based Scene Synthesis and Editing","created":"2024-04-01","cited_by_count":45},{"id":"2506.13922","title":"DynaGuide: Steering Diffusion Polices with Active Dynamic Guidance","created":"2025-06-16","cited_by_count":44},{"id":"2412.00100","title":"Steering Rectified Flow Models in the Vector Field for Controlled Image Generation","created":"2024-11-27","cited_by_count":39},{"id":"2411.16627","title":"Inference-Time Policy Steering through Human Interactions","created":"2024-11-25","cited_by_count":38},{"id":"2512.11891","title":"VLSA: Vision-Language-Action Models with Plug-and-Play Safety Constraint Layer","created":"2025-12-09","cited_by_count":34},{"id":"2412.19948","title":"Motion Planning Diffusion: Learning and Adapting Robot Motion Planning with Diffusion Models","created":"2024-12-27","cited_by_count":33},{"id":"2503.23877","title":"ZeroMimic: Distilling Robotic Manipulation Skills from Web Videos","created":"2025-03-31","cited_by_count":32},{"id":"2512.22539","title":"VLA-Arena: An Open-Source Framework for Benchmarking Vision-Language-Action Models","created":"2025-12-27","cited_by_count":31},{"id":"2503.16365","title":"JARVIS-VLA: Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mouse","created":"2025-03-20","cited_by_count":28},{"id":"2506.07564","title":"SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems","created":"2025-06-09","cited_by_count":25},{"id":"2508.05941","title":"Latent Policy Barrier: Learning Robust Visuomotor Policies by Staying In-Distribution","created":"2025-08-08","cited_by_count":25},{"id":"1902.03138","title":"A Purely Algebraic Justification of the Kabsch-Umeyama Algorithm","created":"2019-02-07","cited_by_count":24},{"id":"2507.01099","title":"Geometry-aware 4D Video Generation for Robot Manipulation","created":"2025-07-01","cited_by_count":24},{"id":"2508.17437","title":"Pixie: Fast and Generalizable Supervised Learning of 3D Physics from Pixels","created":"2025-08-20","cited_by_count":24},{"id":"2410.22332","title":"Local Policies Enable Zero-shot Long-horizon Manipulation","created":"2024-10-29","cited_by_count":22},{"id":"2501.08329","title":"Predicting 4D Hand Trajectory from Monocular Videos","created":"2025-01-14","cited_by_count":21},{"id":"2512.02834","title":"Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach","created":"2025-12-02","cited_by_count":21},{"id":"2506.20668","title":"DemoDiffusion: One-Shot Human Imitation using pre-trained Diffusion Policy","created":"2025-06-25","cited_by_count":19},{"id":"2506.01320","title":"Psi-Sampler: Initial Particle Sampling for SMC-Based Inference-Time Reward Alignment in Score Models","created":"2025-06-02","cited_by_count":15},{"id":"2403.17931","title":"Track Everything Everywhere Fast and Robustly","created":"2024-03-26","cited_by_count":14},{"id":"2511.01163","title":"ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generation","created":"2025-11-03","cited_by_count":13},{"id":"2509.24243","title":"SafeFlowMatcher: Safe and Fast Planning using Flow Matching with Control Barrier Functions","created":"2025-09-29","cited_by_count":12},{"id":"2510.02614","title":"UMI-on-Air: Embodiment-Aware Guidance for Embodiment-Agnostic Visuomotor Policies","created":"2025-10-02","cited_by_count":11},{"id":"2509.06953","title":"Deep Reactive Policy: Learning Reactive Manipulator Motion Planning for Dynamic Environments","created":"2025-09-08","cited_by_count":9},{"id":"2504.02828","title":"Concept Lancet: Image Editing with Compositional Representation Transplant","created":"2025-04-03","cited_by_count":4},{"id":"2510.21746","title":"Avi: Action from Volumetric Inference","created":"2025-10-07","cited_by_count":2}],"next_cursor":null}