RoboValue: A Fine-Grained Sim-and-Real Benchmark for Unified Evaluation of Robotic Value Models Paper • 2610.26663 • Published 21 days ago • 25
VolleyBots: A Testbed for Multi-Drone Volleyball Game Combining Motion Control and Strategic Play Paper • 2502.01932 • Published Feb 4, 2025
MARS: Reinforcing Multi-Agent Reasoning of LLMs through Self-Play in Strategic Games Paper • 2510.15414 • Published Oct 17, 2025 • 1
TaH2 Collection Improving Test-Time Scaling with Adaptive Looped Transformers • 6 items • Updated 18 days ago • 1
TokenRouter Collection TokenRouter: Efficient Serving System for Token-Level LLM Routing • 4 items • Updated 19 days ago