Poster · Atlanta

HESTIA: A Hessian-Guided Differentiable Quantization-Aware Training Framework for Extremely Low-Bit LLMs

Name: HESTIA: A Hessian-Guided Differentiable Quantization-Aware Training Framework for Extremely Low-Bit LLMs
Start: 2026-12-10T16:30:00-05:00
End: 2026-12-10T19:30:00-05:00
Location: Hall C1, Georgia World Congress Center

When: Thu 10 Dec 2026, 16:30–19:30 EST
Where: Hall C1, Georgia World Congress Center
Session: Atlanta Poster Session 4
Authors: Guoan Wang, Feiyu Wang, Zongwei Lv, Yikun Zong, Zhewen Tan, Tong Yang
Organisations: Peking University, University of Cambridge
QRS classification: Language models, Efficient and distributed ML systems

Open in schedule Official page