Rollback: Experience Backtracking in World Models for Policy Improvement Paper • 2610.36068 • Published 4 days ago • 88
Spatial Audio Generation and Editing with Executable Plans and Self-Distilling Transfusion Paper • 2610.34415 • Published 5 days ago • 56
LoCA: Enabling Multi-Modality in Geospatial Location Encoders Paper • 2610.32894 • Published 7 days ago • 6
From VLM Planners to Robotic Agents: Self-Evolving Harnesses for History-Dependent Manipulation Paper • 2610.29560 • Published 9 days ago • 35
SCOPE: Semantic Bounded Credit Optimization for Prompt Engineering in Text-to-image Generation Paper • 2610.22264 • Published 15 days ago • 51
AgenticRoboRL: Bringing Coding-Agent Post-Training to Agentic Robotics Paper • 2610.28589 • Published 10 days ago • 49
InfiniDream: Open-Ended Photorealistic 3D Worlds Through Procedural Generation Paper • 2610.26853 • Published 11 days ago • 35
VerifierBench: Benchmarking the Generation of Executable Verifiers for LLM Agents Paper • 2610.28679 • Published 11 days ago • 32
Ask to Distill: Learning to Synthesize Data for On-Policy Distillation Paper • 2610.27450 • Published 10 days ago • 24
SpecKCast: Spectral Kalman Forecasting for Diffusion Acceleration Paper • 2610.26837 • Published 11 days ago • 29
OpenMobile-2: Building Versatile Mobile Agents with Scalable Environments and App-Native Tools Paper • 2610.14157 • Published 21 days ago • 62
MJev-Spatial: System One Spatial Intelligence via Native Attention Matching Paper • 2610.22276 • Published 15 days ago • 264
Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation Paper • 2610.20571 • Published 16 days ago • 239
VideoJev: System One Model for Video Understanding and Interaction Paper • 2610.18615 • Published 17 days ago • 242
Last Secure Code Benchmark: Is the Code You Vibe Secure? Paper • 2610.14766 • Published 20 days ago • 53
SWE-MISBEHAVIOR: Benchmarking and Mitigating Boundary Violations in Software Coding Agents Paper • 2610.18206 • Published 17 days ago • 19
AesCode: Aesthetic Code Generation with Decoupled Cross-Modal Rewards Paper • 2610.18860 • Published 17 days ago • 91
GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives Paper • 2609.39601 • Published about 1 month ago • 150
ARCS: Towards Precise Text-to-SQL via Structured Disambiguation Paper • 2610.09396 • Published 23 days ago • 13