1 citations · 1 across the 7 of their papers we have counts for
Showing 2026Show all
3 papers · 1 filter
cs.LG2026
Asynchronous LLM Post-Training: Group-Mass Capping and Convergence Analysis
Qijia He, Ruinan Jin, Jun Luo +2
Asynchronous reinforcement learning (RL) improves the efficiency of large language model post-training but introduces stale rollouts generated by earlier policies. Theoretical unde…
cs.AI2026
Adam under Generalized Smoothness with Second-Moment-Type Stochastic Gradients
Ruinan Jin, Difei Cheng, Ling Chen +3
Adam is widely observed to remain stable even when the objective deviates significantly from global smoothness. Under the generalized smoothness framework, however, existing analys…
cs.LG2026
Why Adam Can Beat SGD: Second-Moment Normalization Yields Sharper Tails
Ruinan Jin, Yingbin Liang, Shaofeng Zou
Despite Adam demonstrating faster empirical convergence than SGD in many applications, much of the existing theory yields guarantees essentially comparable to those of SGD, leaving…