{"total":37,"rows":[{"id":"2606.28128","title":"PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation","created":"2026-06-26","cited_by_count":10,"area":null},{"id":"2606.30534","title":"Orca: The World is in Your Mind","created":"2026-06-29","cited_by_count":6,"area":null},{"id":"2607.24744","title":"Data Pyramid for Embodied Manipulation: A Survey","created":"2026-07-27","cited_by_count":6,"area":null},{"id":"2608.19613","title":"What Matters for Latent Actions in Robot Learning","created":"2026-08-20","cited_by_count":4,"area":null},{"id":"2606.31946","title":"World Narrative Model for Highly Controllable Video Generation: A Paradigm Shift from Pixel Sampling to Physical World Orchestration","created":"2026-06-30","cited_by_count":3,"area":null},{"id":"2607.21072","title":"Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text","created":"2026-07-23","cited_by_count":2,"area":null},{"id":"2607.29679","title":"Scaling Properties of Text Conditioning in Visual Generation","created":"2026-07-31","cited_by_count":2,"area":null},{"id":"2608.15659","title":"WorldRover: A Scalable Synthetic Video Data Engine for World Exploration with Rich Annotations","created":"2026-08-16","cited_by_count":2,"area":null},{"id":"2607.25537","title":"Visual prompt engineering for video models","created":"2026-07-28","cited_by_count":1,"area":null},{"id":"2608.07693","title":"CosmosAlign: Adapting a World Foundation Model for Generative Traffic Video Forecasting","created":"2026-08-07","cited_by_count":1,"area":null},{"id":"2608.27529","title":"Revisiting Local Context for Long-Horizon Streaming 3D Reconstruction","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2609.08368","title":"Miles v0.1: Production-Level Post-Training","created":"2026-09-08","cited_by_count":1,"area":null},{"id":"2609.25627","title":"MachEmbodied-U0: Unified Understanding and Generation Model for Embodied Intelligence","created":"2026-09-22","cited_by_count":1,"area":null},{"id":"2606.29013","title":"Mural: Transferring LLM knowledge to image generation via Mixture-of-Transformers","created":"2026-06-27","cited_by_count":0,"area":null},{"id":"2607.29545","title":"MoRoute: Dynamic Routing for In-Context Multimodal Video Generation","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.25757","title":"LM-X: Explainable Vision--Language--Action Modeling via Progress, Event, and Uncertainty Prediction","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.04196","title":"Puffin-World: Scaling a Unified Multimodal Model with Native 3D World States","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.06629","title":"Physico-Geospatial Grounded Scene Interpretation for Mobile Robotics","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2609.18077","title":"vidax: A Unified JAX Framework for Video Generative Models on Accelerator Meshes","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.21461","title":"AtomEgo: Exploring Ego-Robot Integration for Embodied Foundation Model Pretraining","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.21942","title":"When Should a Failing Robot Ask? Initiating Corrective Human-Robot Dialogue from Audited Sensor Evidence","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.34271","title":"Scaling Versatile 3D Assets Editing with a Million-Scale Dataset","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.38059","title":"WorldLine: Action-Driven Visual Simulation for Robotic Manipulation","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38079","title":"OmniTaskonomy: When Does Visual Generation Improve Visual Understanding?","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39375","title":"Beyond the Current Scene: Event-Referential Grasping with Active View Selection","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.39601","title":"GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.01092","title":"Ego2Act: Evaluating Goal-Directed Manipulation in Egocentric Video Generation","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.02089","title":"HumanoidToolBench: Benchmarking Humanoid Tool Use from Selection to Mobile Execution","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.05135","title":"How Does Geometry Enter Generated Motion?","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.09455","title":"RLHND: Video Foundation Models as Physically Grounded Hand Trackers for Robot Learning","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.11039","title":"Rendering-Free Lookahead for Question-Guided Active Vision","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.12374","title":"AgentGarten: Code Worlds for Evolving Agents","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.12386","title":"ARC: A Reasoning Recipe for Robot Foundation Models","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.13412","title":"TextVBench: Evaluating Text Rendering and Preservation in Video Generation","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.15782","title":"Data-Centric Recursive Self-Improvement for Navigation via Policy-Synchronized Language-Action Dual Bootstrapping","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.18053","title":"LADDER: A Long-Horizon Robot Manipulation Benchmark","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.19495","title":"Robota-Embed: Unified VLA Embeddings for Robot In-Context Learning and Evolution","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}