45 citations · 134 across the 47 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.LG2026
EchoRL: Reinforcement Learning via Rollout Echoing
Jinhe Bi, Aniri, Minglai Yang +9
Reinforcement Learning with Verifiable Rewards is an effective route for post-training to strengthen the reasoning capability of large language models. However, as training proceed…
cs.LG2026
Routing-Free Mixture-of-Experts
Yilun Liu, Jinru Han, Sikuan Yan +2
Standard Mixture-of-Experts (MoE) models rely on centralized routing mechanisms that introduce rigid inductive biases. We propose Routing-Free MoE which eliminates any hard-coded c…