3 papers
cs.LG2026
Beyond Uniform Token-Level Trust Region in LLM Reinforcement Learning
Renjie Mao, Xiangxin Zhou, Lvfang Tao +7
Reinforcement learning with verifiable rewards (RLVR) has become standard for improving LLM reasoning. However, existing PPO-style trust-region mechanisms remain position-agnostic…
cs.DC2026
FalconGEMM: Surpassing Hardware Peaks with Lower-Complexity Matrix Multiplication
Honglin Zhu, Jiaping Cao, Jiang Shao +10
Peak breaking Matrix Multiplication is a promising technique to improve the performance of DL, especially in LLM training and inference. We present FalconGEMM, a cross-platform fra…
cs.DC2025
NM-SpMM: Accelerating Matrix Multiplication Using N:M Sparsity with GPGPU
Cong Ma, Du Wu, Zhelang Deng +11
Deep learning demonstrates effectiveness across a wide range of tasks. However, the dense and over-parameterized nature of these models results in significant resource consumption…