Researcher — paper.dinq.me

2026 顶会论文

作者位次 #5/5ICLR 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 #6/6ICLR 2026Poster

NLI : Non-uniform Linear Interpolation Approximation of Nonlinear Operations for Efficient LLMs Inference

Jiangyong Yu · Xiaomeng Han · Xing Hu · XUCHEN · Zhe Jiang · Dawei Yang

效率与系统OpenReview

作者位次 #2/5ICLR 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 #3/4CVPR 2026Poster· Computer Vision & Pattern Recognition

CAR-SAM: Cross-Attention Reconstruction for Post-Training Quantization of the Segment Anything Model

Houji Wen · Jiangyong Yu · Dawei Yang · Jun Li

多模态强化学习与后训练效率与系统OpenReview 项目页

作者位次 #3/3ACL 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

作者位次 #4/4AAAI 2026Poster· Artificial Intelligence

VAEVQ: Enhancing Discrete Visual Tokenization Through Variational Modeling

Sicheng Yang · Xing Hu · Qiang Wu · Dawei Yang

多模态数据与预训练OpenReview

作者位次 #6/6AAAI 2026Poster· Artificial Intelligence

FQ-PETR: Fully Quantized Position Embedding Transformation for Multi-View 3D Object Detection

Jiangyong Yu · Changyong Shu · Sifan Zhou · Zichen Yu · Xing Hu · Dawei Yang

效率与系统OpenReview

作者位次 #3/5AAAI 2026Poster· Artificial Intelligence

OTARo: Once Tuning for All Precisions Toward Robust On-Device LLMs

Shaoyuan Chen · Zhixuan Chen · Dawei Yang · Zhihang Yuan · Qiang Wu

OpenReview

Dawei Yang

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

NLI : Non-uniform Linear Interpolation Approximation of Nonlinear Operations for Efficient LLMs Inference

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

CAR-SAM: Cross-Attention Reconstruction for Post-Training Quantization of the Segment Anything Model

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

VAEVQ: Enhancing Discrete Visual Tokenization Through Variational Modeling

FQ-PETR: Fully Quantized Position Embedding Transformation for Multi-View 3D Object Detection

OTARo: Once Tuning for All Precisions Toward Robust On-Device LLMs

常见合作者