{"total":23,"rows":[{"id":"2503.14734","title":"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots","created":"2025-03-18","cited_by_count":1225,"area":null},{"id":"2505.21457","title":"ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning","created":"2025-05-27","cited_by_count":43,"area":null},{"id":"2607.08639","title":"Native Video-Action Pretraining for Generalizable Robot Control","created":"2026-07-09","cited_by_count":36,"area":null},{"id":"2503.18943","title":"SlowFast-LLaVA-1.5: A Family of Token-Efficient Video Large Language Models for Long-Form Video Understanding","created":"2025-03-24","cited_by_count":30,"area":null},{"id":"2503.13502","title":"Foundation Models for Spatio-Temporal Data Science: A Tutorial and Survey","created":"2025-03-12","cited_by_count":24,"area":null},{"id":"2607.15275","title":"RoboTTT: Context Scaling for Robot Policies","created":"2026-07-16","cited_by_count":19,"area":null},{"id":"2511.21025","title":"CaptionQA: Is Your Caption as Useful as the Image Itself?","created":"2025-11-26","cited_by_count":15,"area":null},{"id":"2510.09507","title":"PhysToolBench: Benchmarking Physical Tool Understanding for MLLMs","created":"2025-10-10","cited_by_count":9,"area":null},{"id":"2509.22652","title":"Pixel Motion Diffusion is What We Need for Robot Control","created":"2025-09-26","cited_by_count":7,"area":null},{"id":"2601.10781","title":"Future Optical Flow Prediction Improves Robot Control & Video Generation","created":"2026-01-15","cited_by_count":7,"area":null},{"id":"2509.13615","title":"See, Think, Act: Teaching Multimodal Agents to Effectively Interact with GUI by Identifying Toggles","created":"2025-09-17","cited_by_count":4,"area":null},{"id":"2509.14537","title":"ClearFairy: Capturing Creative Workflows through Decision Structuring, In-Situ Questioning, and Rationale Inference","created":"2025-09-18","cited_by_count":4,"area":null},{"id":"2509.23541","title":"OVSeg3R: Learn Open-vocabulary Instance Segmentation from 2D via 3D Reconstruction","created":"2025-09-28","cited_by_count":4,"area":null},{"id":"2507.06233","title":"AnthroTAP: Learning Point Tracking with Real-World Motion","created":"2025-07-08","cited_by_count":3,"area":null},{"id":"2601.06031","title":"Beyond Clicking:A Step Towards Generalist GUI Grounding via Text Dragging","created":"2025-11-07","cited_by_count":3,"area":null},{"id":"2603.02050","title":"\"When to Hand Off, When to Work Together\": Understanding Concurrent Human-Agent Interaction in Shared Co-Creative Workspaces","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2605.06088","title":"OpenGaFF: Open-Vocabulary Gaussian Feature Field with Codebook Attention","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.20085","title":"Spatially Prompted Visual Trajectory Prediction for Egocentric Manipulation","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2607.21125","title":"Causal-AgentIR: Self-Evolving Causal Memory for Adaptive Image Restoration Agents","created":"2026-07-23","cited_by_count":1,"area":null},{"id":"2608.01851","title":"Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2507.21589","title":"Exploring the Link Between Bayesian Inference and Embodied Intelligence: Toward Open Physical-World Embodied AI Systems","created":"2025-07-29","cited_by_count":0,"area":null},{"id":"2603.28306","title":"Self++: Co-Determined Agency for Human--AI Symbiosis in Extended Reality","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2609.09119","title":"DeCAL: Towards Physically-Grounded Dexterous Vision-Language-Action Models via Contact-Aware Latent Co-Imagination","created":"2026-09-08","cited_by_count":0,"area":null}],"next_cursor":null}