BLAST RADIUS

Open-weight & owned stack · Quantization efficiency

BCJR-QAT proposes differentiable trellis-coded weight quantization

Sep 12, 2026

BCJR-QAT proposed a differentiable method for training models with trellis-coded weight quantization below post-training quantization limits.

Read the original at awesomepapers.ioOpens the publisher's site in a new tab

More in Open-weight & owned stack

Z.ai publishes GLM-5.3 open weightsSep 8MiniMax H3 highlighted as open-weight multimodal modelSep 7InternLM releases 397B multimodal Intern-S2 modelSep 13DeepSeek Model Nearly Matches GPT-6 Astra DesignSep 10DeepSeek presents V4 FlashSep 8