4 papers
Divide-and-Remember: Recursive Action-Relevant Memory for Long-Horizon VLA Policies
Xuehui Yu, Eason Yu, Meiyi Wang +3
Vision-language-action (VLA) models struggle on history-dependent manipulation tasks, where the current observation alone does not determine the action, and the policy needs a memo…
Mahjax: A GPU-Accelerated Mahjong Simulator for Reinforcement Learning in JAX
Soichiro Nishimori, Shinri Okano, Keigo Habara +3
Riichi Mahjong is a multi-player, imperfect-information game characterized by stochasticity and high-dimensional state spaces. These attributes present a unique combination of chal…
GoodSpeed: Optimizing Fair Goodput with Adaptive Speculative Decoding in Distributed Edge Inference
Phuong Tran, Tzu-Hao Liu, Long Tan Le +6
Large language models (LLMs) have revolutionized natural language processing, yet their high computational demands pose significant challenges for real-time inference, especially i…
NashPG: A Policy Gradient Method with Iteratively Refined Regularization for Finding Nash Equilibria
Eason Yu, Tzu Hao Liu, Clément L. Canonne +4
Finding Nash equilibria in two-player zero-sum imperfect-information games remains a central challenge in multi-agent reinforcement learning. Recent multi-round regularization meth…