{"list":"other","total":62,"rows":[{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"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":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"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":"2403.12945","title":"DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset","created":"2024-03-19","cited_by_count":852},{"id":"2407.07726","title":"PaliGemma: A versatile 3B VLM for transfer","created":"2024-07-10","cited_by_count":696},{"id":"2501.09747","title":"FAST: Efficient Action Tokenization for Vision-Language-Action Models","created":"2025-01-16","cited_by_count":665},{"id":"2308.12952","title":"BridgeData V2: A Dataset for Robot Learning at Scale","created":"2023-08-24","cited_by_count":657},{"id":"2501.15830","title":"SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model","created":"2025-01-27","cited_by_count":519},{"id":"2506.18088","title":"RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation","created":"2025-06-22","cited_by_count":518},{"id":"2409.12514","title":"TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation","created":"2024-09-19","cited_by_count":339},{"id":"2403.09631","title":"3D-VLA: A 3D Vision-Language-Action Generative World Model","created":"2024-03-14","cited_by_count":328},{"id":"2504.05299","title":"SmolVLM: Redefining small and efficient multimodal models","created":"2025-04-07","cited_by_count":237},{"id":"2412.13877","title":"RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation","created":"2024-12-18","cited_by_count":175},{"id":"2505.17685","title":"FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving","created":"2025-05-23","cited_by_count":166},{"id":"2507.11539","title":"Streaming 4D Visual Geometry Transformer","created":"2025-07-15","cited_by_count":161},{"id":"2506.19850","title":"Unified Vision-Language-Action Model","created":"2025-06-24","cited_by_count":134},{"id":"2401.01686","title":"ODTrack: Online Dense Temporal Token Learning for Visual Tracking","created":"2024-01-03","cited_by_count":129},{"id":"2410.13571","title":"DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation","created":"2024-10-17","cited_by_count":123},{"id":"2508.20072","title":"Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies","created":"2025-08-27","cited_by_count":90},{"id":"2411.19548","title":"ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restoration","created":"2024-11-29","cited_by_count":89},{"id":"2501.10105","title":"Universal Actions for Enhanced Embodied Foundation Models","created":"2025-01-17","cited_by_count":82},{"id":"2508.09071","title":"GeoVLA: Empowering 3D Representations in Vision-Language-Action Models","created":"2025-08-12","cited_by_count":70},{"id":"2308.14103","title":"Towards Unified Token Learning for Vision-Language Tracking","created":"2023-08-27","cited_by_count":62},{"id":"2108.06455","title":"PTT: Point-Track-Transformer Module for 3D Single Object Tracking in Point Clouds","created":"2021-08-14","cited_by_count":59},{"id":"2503.03663","title":"LION-FS: Fast & Slow Video-Language Thinker as Online Video Assistant","created":"2025-03-05","cited_by_count":58},{"id":"2507.00416","title":"Evo-0: Vision-Language-Action Model with Implicit Spatial Understanding","created":"2025-07-01","cited_by_count":58},{"id":"2506.22242","title":"4D-VLA: Spatiotemporal Vision-Language-Action Pretraining with Cross-Scene Calibration","created":"2025-06-27","cited_by_count":56},{"id":"2110.14921","title":"3D Object Tracking with Transformer","created":"2021-10-28","cited_by_count":49},{"id":"2411.18623","title":"Lift3D Foundation Policy: Lifting 2D Large-Scale Pretrained Models for Robust 3D Robotic Manipulation","created":"2024-11-27","cited_by_count":46},{"id":"2510.19430","title":"GigaBrain-0: A World Model-Powered Vision-Language-Action Model","created":"2025-10-22","cited_by_count":44},{"id":"2503.07523","title":"VisRL: Intention-Driven Visual Perception via Reinforced Reasoning","created":"2025-03-10","cited_by_count":39},{"id":"2510.01623","title":"VLA-R1: Enhancing Reasoning in Vision-Language-Action Models","created":"2025-10-02","cited_by_count":38},{"id":"2303.12384","title":"RegFormer: An Efficient Projection-Aware Transformer Network for Large-Scale Point Cloud Registration","created":"2023-03-22","cited_by_count":37},{"id":"2503.18438","title":"ReconDreamer++: Harmonizing Generative and Reconstructive Models for Driving Scene Representation","created":"2025-03-24","cited_by_count":36},{"id":"2506.17561","title":"VLA-OS: Structuring and Dissecting Planning Representations and Paradigms in Vision-Language-Action Models","created":"2025-06-21","cited_by_count":36},{"id":"2307.06505","title":"WaterScenes: A Multi-Task 4D Radar-Camera Fusion Dataset and Benchmarks for Autonomous Driving on Water Surfaces","created":"2023-07-13","cited_by_count":35},{"id":"2505.05800","title":"3D CAVLA: Leveraging Depth and 3D Context to Generalize Vision Language Action Models for Unseen Tasks","created":"2025-05-09","cited_by_count":31},{"id":"2412.09043","title":"DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Driving","created":"2024-12-12","cited_by_count":29},{"id":"2507.05198","title":"EmbodieDreamer: Advancing Real2Sim2Real Transfer for Policy Training via Embodied World Modeling","created":"2025-07-07","cited_by_count":29},{"id":"2508.08170","title":"ReconDreamer-RL: Enhancing Reinforcement Learning via Diffusion-based Scene Reconstruction","created":"2025-08-11","cited_by_count":27},{"id":"2509.22199","title":"MimicDreamer: Aligning Human and Robot Demonstrations for Scalable VLA Training","created":"2025-09-26","cited_by_count":25},{"id":"2510.14836","title":"QDepth-VLA: Quantized Depth Prediction as Auxiliary Supervision for Vision-Language-Action Models","created":"2025-10-16","cited_by_count":21},{"id":"2507.23782","title":"MonoFusion: Sparse-View 4D Reconstruction via Monocular Fusion","created":"2025-07-31","cited_by_count":19},{"id":"2508.10523","title":"Reasoning in Computer Vision: Taxonomy, Models, Tasks, and Methodologies","created":"2025-08-14","cited_by_count":17},{"id":"2510.15264","title":"DriveGen3D: Boosting Feed-Forward Driving Scene Generation with Efficient Video Diffusion","created":"2025-10-17","cited_by_count":15},{"id":"2504.03536","title":"HumanDreamer-X: Photorealistic Single-image Human Avatars Reconstruction via Gaussian Restoration","created":"2025-04-04","cited_by_count":13},{"id":"2506.16201","title":"FlowRAM: Grounding Flow Matching Policy with Region-Aware Mamba Framework for Robotic Manipulation","created":"2025-06-19","cited_by_count":13},{"id":"2508.19257","title":"TTF-VLA: Temporal Token Fusion via Pixel-Attention Integration for Vision-Language-Action Models","created":"2025-08-15","cited_by_count":12},{"id":"2509.22407","title":"EMMA: Generalizing Real-World Robot Manipulation via Generative Visual Transfer","created":"2025-09-26","cited_by_count":12},{"id":"2504.00950","title":"Neural Pruning for 3D Scene Reconstruction: Efficient NeRF Acceleration","created":"2025-04-01","cited_by_count":10},{"id":"2509.10140","title":"Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization","created":"2025-09-12","cited_by_count":10},{"id":"2504.00270","title":"NeRF-Based defect detection","created":"2025-03-31","cited_by_count":7},{"id":"2506.20590","title":"WonderFree: Enhancing Novel View Quality and Cross-View Consistency for 3D Scene Exploration","created":"2025-06-25","cited_by_count":7},{"id":"2410.01529","title":"Robo-MUTUAL: Robotic Multimodal Task Specification via Unimodal Learning","created":"2024-10-02","cited_by_count":6},{"id":"2410.15885","title":"VLASCD: A Visual Language Action Model for Simultaneous Chatting and Decision Making","created":"2024-10-21","cited_by_count":5},{"id":"2509.24524","title":"PhysiAgent: An Embodied Agent Framework in Physical World","created":"2025-09-29","cited_by_count":5},{"id":"2509.05746","title":"Depth-Aware Super-Resolution via Distance-Adaptive Variational Formulation","created":"2025-09-06","cited_by_count":4}],"next_cursor":null}