10 citations · 10 across the 9 of their papers we have counts for
4 papers · 1 filter
The Curse and Blessing of Mean Bias in FP4-Quantized LLM Training
Hengjie Cao, Zhendong Huang, Mengyi Chen +15
FP4 training promises substantial memory and compute savings for large language models, but remains fragile because blockwise quantization is dictated by extreme activation magnitu…
Spectra: Rethinking Optimizers for LLMs Under Spectral Anisotropy
Zhendong Huang, Hengjie Cao, Fang Dong +14
Gradient signals in LLM training are highly anisotropic: recurrent linguistic structure concentrates energy into a small set of dominant spectral directions, while context specific…
Metis: Training LLMs with FP4 Quantization
Hengjie Cao, Mengyi Chen, Yifeng Yang +13
This work identifies anisotropy in the singular value spectra of parameters, activations, and gradients as the fundamental barrier to low-bit training of large language models (LLM…
Train Faster, Perform Better: Modular Adaptive Training in Over-Parameterized Models
Yubin Shi, Yixuan Chen, Mingzhi Dong +10
Despite their prevalence in deep-learning communities, over-parameterized models convey high demands of computational costs for proper training. This work studies the fine-grained,…