Researcher — paper.dinq.me

2026 顶会论文

作者位次 #3/3ICLR 2026Poster· Applications / Language, Speech and Dialog

GradPruner: Gradient-guided Layer Pruning Enabling Efficient Fine-Tuning and Inference for LLMs

Wei Huang · Anda Cheng · Yinggui Wang

效率与系统多模态强化学习与后训练OpenReview

作者位次 #5/8ACL 2026Findings· Findings of ACL

C o T rust: Privacy-Preserving Collaboration Between Large and Small Language Models in Trusted Execution Environments

Zhenya Ma · Tingyi Wang · Yongheng Deng · Ziqing Qiao · Yinggui Wang · Tao Wei · Lei Wang · Ju Ren

摘要

Services powered by large language models (LLMs) provide powerful text generation capabilities, but accessing sensitive user inputs raises serious privacy concerns. Trusted Execution Environments (TEEs) provide a secure computation environment, enabling sensitive inputs to be safely processed. Ho...

效率与系统检索与知识推理OpenReview 项目页

作者位次 #3/5VLDB 2026Oral· Data Management (REG)

LLM-AutoDP: Automatic Data Processing via LLM Agents for Model Fine-tuning

Wei Huang · Anda Cheng · Yinggui Wang · Lei Wang · Tao Wei

智能体与工具强化学习与后训练OpenReview

Yinggui Wang

获取完整研究档案

联系方式

2026 顶会论文

GradPruner: Gradient-guided Layer Pruning Enabling Efficient Fine-Tuning and Inference for LLMs

C o T rust: Privacy-Preserving Collaboration Between Large and Small Language Models in Trusted Execution Environments

LLM-AutoDP: Automatic Data Processing via LLM Agents for Model Fine-tuning

常见合作者