3 papers
cs.LG2026
Sparrow: Sparse Rollout for Stable and Efficient Long-context RL of Large Language Models
Yang Zhou, Ranajoy Sadhukhan, Zhaofeng Sun +7
Despite being powerful, reinforcement learning with verifiable rewards (RLVR) induces extremely long COT, making it computationally expensive. Since RLVR per-step cost is dominated…
cs.LG2026
Model-Preserving Adaptive Rounding
Albert Tseng, Zhaofeng Sun, Christopher De Sa
The goal of quantization is to produce a compressed model whose output distribution is as close to the original model's as possible. To do this tractably, most quantization algorit…
cs.LG2025
Beyond 2:4: exploring V:N:M sparsity for efficient transformer inference on GPUs
Kang Zhao, Tao Yuan, Han Bao +6
To date, 2:4 sparsity has stood as the only sparse pattern that can be accelerated using sparse tensor cores on GPUs. In practice, 2:4 sparsity often possesses low actual speedups…