Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
State-Aware Activation Recomputation with Replay Contracts and Selective Preservation
Annan Zhang, Shengjie Song, Wenshuai Yao +2
Activation recomputation saves accelerator memory by replaying forward segments during the backward pass, but replay is only correct if it sees the state the original forward pass…
cs.AI2026
SetCommit: Coordinated Token Commitments for Few-Step Diffusion Language Model Decoding
Yuannuo Feng, Yubing Ye, Wenshuai Yao +4
Diffusion language models generate multiple token positions in parallel, but few-step decoding makes parallel commitment difficult: tokens that appear reliable individually may be…