D2Quant: Low-Bit Weight Quantization for Large Language Models

Aug 25, 2026·
肖洋
· 0 min read
The D2Quant framework
Abstract
Review of paper writing approach, summarizing research themes and innovations, sharing paper submission experiences.
Date
Aug 25, 2026 8:30 AM — 9:15 AM
Event
D2Quant: Low-Bit Weight Quantization for Large Language Models
Location

Room 101, Xinda Building B

events
Group Meeting Research Sharing Model Compression Quantization
Sina Weibo