Compression Forcing: Hierarchical History Tokenization Enables Flexible World Models Paper • 2611.04028 • Published 15 days ago
Democratizing Robot-Use Agents: A Unified Harness with Open Models Paper • 2611.01560 • Published 16 days ago • 51
Qwen-Image-PE: Learning Visual Design for Text-to-Image Prompt Enhancement Paper • 2610.33472 • Published 24 days ago • 24
Vision-Language Models Are Joint Denoisers in Robotic Action Generation Paper • 2611.01215 • Published 16 days ago • 2
MemSteer: Turning User Histories into Supervision for Agent Memory Optimization Paper • 2610.39276 • Published 19 days ago • 11
MemSteer: Turning User Histories into Supervision for Agent Memory Optimization Paper • 2610.39276 • Published 19 days ago • 11
Rethinking Video Storage for AI Training: Breaking Cross-Frame Dependencies for Efficient Random Access Paper • 2610.33079 • Published 27 days ago • 12
Rethinking Video Storage for AI Training: Breaking Cross-Frame Dependencies for Efficient Random Access Paper • 2610.33079 • Published 27 days ago • 12
AffordanceWAM: Affordance-Aware Joint World-Action Modeling for Robot Manipulation Paper • 2609.22332 • Published 30 days ago • 18
Execution Before Memory: Diagnosing Memory Failures in Video World Models Paper • 2610.23542 • Published Oct 16 • 28
Towards Trustworthy Embodied Intelligence: A Systems Framework and Graded Trustworthiness Levels Paper • 2607.26121 • Published Jul 28 • 1
LongR: Unleashing Long-Context Reasoning via Reinforcement Learning with Dense Utility Rewards Paper • 2602.05758 • Published Oct 12 • 11
RoboAware: Learning to Coordinate Embodied Skills from Counterfactual Outcomes Paper • 2610.11480 • Published Oct 8 • 4
AUGUstus: Autonomous Driving VLA Model with Unified Generation and Understanding Paper • 2610.16985 • Published Oct 12 • 12