Showing 2026Show all
3 papers · 1 filter
cs.LG2026
Allspark: Weak to Strong Transfer via Alternating Chain of Thought
Kaizhao Liang, Junxiong Wang, Chen Liang +2
Recent progress in frontier models has renewed interest in large-scale reinforcement learning (RL), but the cost of generating large-model rollouts makes even testing RL recipes ex…
cs.LG2026
Training-Free Looped Transformers
Lizhang Chen, Jonathan Li, Chen Liang +2
We introduce training-free looped transformers, in which a lightweight inference-time wrapper loops a contiguous mid-stack block of layers of a frozen checkpoint without additional…
cs.LG2026
-Balancing for Mixture-of-Experts Training
Lizhang Chen, Jonathan Li, Qi Wang +5
Mixture-of-Experts (MoE) models rely on balanced expert utilization to fully realize their scalability. However, existing load-balancing methods are largely heuristic and operate o…