-
LNS-Madam: Low-Precision Training in Logarithmic Number System using Multiplicative Weight Update
Paper • 2106.13914 • Published • 1 -
HeurAgenix: Leveraging LLMs for Solving Complex Combinatorial Optimization Challenges
Paper • 2506.15196 • Published • 3 -
Ascend HiFloat8 Format for Deep Learning
Paper • 2409.16626 • Published • 1 -
Recipes for Pre-training LLMs with MXFP8
Paper • 2506.08027 • Published • 1
zhangwenbin
ExceedZhang
AI & ML interests
None yet
Recent Activity
liked a model about 6 hours ago
Inferact/Qwen3.8-Flash-Next-NVFP4 upvoted an article about 6 hours ago
Transformers now runs llama.cpp quants upvoted an article about 6 hours ago
Pruning LLMs Like a Physicist: Block Removal as an Ising Optimization ProblemOrganizations
None yet