Video2Skill: From Streaming Experience to Reusable Embodied Skills Paper • 2609.36691 • Published 11 days ago • 16
UFO: Chain-of-Evaluation for Omni-Condition Alignment in Multi-Modal Image Generation Paper • 2609.12397 • Published 23 days ago • 46
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression Paper • 2609.19969 • Published 23 days ago • 228
Confidence Comes from Experience: Experiential Confidence Estimation from Reasoning to Agents Paper • 2609.17708 • Published 25 days ago • 78
IdeaAMBIG: Benchmarking Implementation-Critical Gaps in Research-Idea Specifications Paper • 2609.10539 • Published Sep 9 • 25
RoboSPA: Can VLA Models Go Beyond Simple Scenes and Short-Horizon Tasks? Paper • 2609.05324 • Published Sep 4 • 28