activity
20242026
most citedLLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit

2 citations · 2 across the 3 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

Optimizing Stochastic Policy Geometry for Few-Step Flow Reinforcement Learning

Zhuguanyu Wu, Congjia Chen, Ruihao Gong +4

Few-step flow models generate samples through a handful of large denoising transitions. Applying GRPO to such models requires introducing stochasticity into the denoising transitio…