Researcher — paper.dinq.me

2026 顶会论文

一作ICLR 2026Poster· Deep Learning / Algorithms

KBVQ-MoE: KLT-guided SVD with Bias-Corrected Vector Quantization for MoE Large Language Models

Zukang Xu · Zhixiong Zhao · Xing Hu · Zhixuan Chen · Dawei Yang

效率与系统社会与人本OpenReview

作者位次 #5/5ICLR 2026Poster· Deep Learning / Algorithms

SAES-SVD: Self-Adaptive Suppression of Accumulated and Local Errors for SVD-based LLM Compression

Xing Hu · Dawei Yang · Yuan Cheng · Zhixuan Chen · Zukang Xu

效率与系统OpenReview

作者位次 #2/3ACL 2026Poster· Natural Language Processing

BWLA : Breaking the Barrier of W 1 AX Post-Training Quantization for LLM s

Zhixiong Zhao · Zukang Xu · Dawei Yang

摘要

Large language models (LLMs) have driven major progress in NLP, yet their substantial memory and compute demands still hinder practical deployment. Binarization can compress weights to 1 bit, fundamentally lowering compute and bandwidth cost. However, existing methods cannot address activation he...

效率与系统强化学习与后训练检索与知识OpenReview 项目页

Zukang Xu

获取完整研究档案

联系方式

2026 顶会论文

KBVQ-MoE: KLT-guided SVD with Bias-Corrected Vector Quantization for MoE Large Language Models

SAES-SVD: Self-Adaptive Suppression of Accumulated and Local Errors for SVD-based LLM Compression

BWLA : Breaking the Barrier of W 1 AX Post-Training Quantization for LLM s

常见合作者