AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents Paper • 2607.02255 • Published 2 days ago • 41
SkillCoach: Self-Evolving Rubrics for Evaluating and Enhancing Agentic Skill-Use Paper • 2607.01874 • Published 2 days ago • 14
Representation Distribution Matching for One-Step Visual Generation Paper • 2607.02375 • Published 2 days ago • 4
Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity Paper • 2607.00248 • Published 4 days ago • 23
Learning to Move Before Learning to Do: Task-Agnostic pretraining for VLAs Paper • 2607.02466 • Published 2 days ago • 4
WorldDirector: Building Controllable World Simulators with Persistent Dynamic Memory Paper • 2607.02517 • Published 2 days ago • 18
TurboServe: Serving Streaming Video Generation Efficiently and Economically Paper • 2606.19271 • Published 17 days ago • 27
Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity Paper • 2607.00248 • Published 4 days ago • 23
ABot-M0.5: Unified Mobility-and-Manipulation World Action Model Paper • 2607.00678 • Published 3 days ago • 13 • 2
ABot-M0.5: Unified Mobility-and-Manipulation World Action Model Paper • 2607.00678 • Published 3 days ago • 13