RepForcing: Representation-Space Initialization for Autoregressive Video Distillation Paper • 2610.20111 • Published 13 days ago • 6
More Methods, Better Agents? A Reality Check on Self-Distillation in Agentic Reinforcement Learning Paper • 2610.19789 • Published 13 days ago • 61
Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation Paper • 2610.20571 • Published 13 days ago • 370
Distilling Routed 3D Privilege for Spatial Reasoning in Vision-Language Models Paper • 2610.12355 • Published 19 days ago • 10
SpaceCast-Bench: Evaluating Predictive Spatial Reasoning in Vision-Language Models Paper • 2610.12402 • Published 19 days ago • 15
ViSkill: Reinforcing VLM Agents with Evolving Visual-Native Skills Paper • 2610.12403 • Published 19 days ago • 18
nanoMuse: An Open-Source Personal Agent for Every Device You Own Paper • 2610.08699 • Published 21 days ago • 122
CoEvoWhen: Policy-Tool Coevolution for Ultra-Long Video Temporal Grounding Paper • 2609.40048 • Published 27 days ago • 16
Scaling Properties of Same-Family On-Policy Distillation Paper • 2609.32722 • Published Sep 26 • 328
SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue Paper • 2609.26780 • Published Sep 22 • 105
RoboSPA: Can VLA Models Go Beyond Simple Scenes and Short-Horizon Tasks? Paper • 2609.05324 • Published Sep 4 • 28
ZipTok3D: High-Fidelity 3D Tokenization with Compact Token Prefixes Paper • 2609.01740 • Published Sep 1 • 29
GUI-CC: Benchmarking Contextual Consistency of GUI World Models as Agent Environments Paper • 2609.00048 • Published Aug 30 • 8
Sci-VBench: Evaluating Knowledge- and Reasoning-Intensive Video Generation in Science Domains Paper • 2608.09873 • Published Aug 10 • 29