Researcher — paper.dinq.me

2026 顶会论文

作者位次 #6/7ICML 2026Poster· Deep Learning / Robustness

On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression

Xinwei Zhang · Hangcheng Liu · Li Bai · Hao Wang · Qingqing Ye · Tianwei Zhang · Haibo Hu

多模态安全效率与系统OpenReview

作者位次 #4/4ICML 2026Poster· Deep Learning / Large Language Models

DSB: Dynamic Sliding Block Scheduling for Diffusion LLMs

Lizhuo Luo · Shenggui Li · Yonggang Wen · Tianwei Zhang

OpenReview

作者位次 #10/10ICML 2026Poster

CONCUR: High-Throughput Agentic Batch Inference of LLM via Congestion-Based Concurrency Control

Qiaoling Chen · Zhisheng Ye · Tian Tang · Peng Sun · Boyu Tian · Guoteng Wang · Shenggui Li · Yonggang Wen · Zhenhua Han · Tianwei Zhang

效率与系统智能体与工具OpenReview

作者位次 #4/5ICML 2026Poster· Social Aspects / Security

Turning Bias into Bugs: Bandit-Guided Style Manipulation Attacks on LLM Judges

XIANGLIN YANG · Bryan Hooi · Gelei Deng · Tianwei Zhang · Jin Song Dong

安全社会与人本评测与基准OpenReview

作者位次 #16/16ICML 2026Poster

SpecForge: A Flexible and Efficient Open-Source Training Framework for Speculative Decoding

Shenggui Li · Chao Wang · YIKAI ZHU · Yubo Wang · Fan Yin · Shuai Shi · YefeiChen · Xiaomin Dong · Qiaoling Chen · Jin Pan · Ji Li · Yineng Zhang · Lei Yu · Yonggang Wen · Ivor Tsang · Tianwei Zhang

效率与系统代码OpenReview

作者位次 #3/8ICML 2026Poster· Social Aspects / Safety

State-Dependent Safety Failures in Multi-Turn Language Model Interaction

pengcheng li · Jie Zhang · Tianwei Zhang · Han Qiu · Zhang kejun · Weiming Zhang · Nenghai Yu · Wenbo Zhou

安全社会与人本OpenReview

作者位次 #7/8ICML 2026Poster· Deep Learning / Large Language Models

When Search Goes Wrong: Red-Teaming Web-Augmented Large Language Models

Haoran Ou · Kangjie Chen · Xingshuo Han · Gelei Deng · Jie Zhang · Han Qiu · Tianwei Zhang · Kwok Yan Lam

安全检索与知识OpenReview

作者位次 #6/7ICML 2026Poster· Social Aspects / Security

Dissecting the Safety Circuit: Neuronal Intervention for Transferable Adversarial Attacks on VLMs

Chunlong Xie · Kangjie Chen · Shangwei Guo · Shudong Zhang · Jiamou Liu · Tianwei Zhang · Tao Xiang

安全可解释性多模态OpenReview

作者位次 #6/9ICML 2026Poster· Social Aspects / Safety

SafeSearch: Automated Red-Teaming of LLM-Based Search Agents

Jianshuo Dong · Sheng Guo · Hao Wang · Xun Chen · Zhuotao Liu · Tianwei Zhang · Ke Xu · Minlie Huang · Han Qiu

安全智能体与工具检索与知识OpenReview

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

UniTG: A Unified System for Efficient and Seamless Textual Graph Learning

Meng Zhang · Zhisheng Ye · Qiyu Liu · Jingshu Peng · Tianwei Zhang

效率与系统OpenReview

作者位次 #5/5ICRA 2026Oral· Robotics & Automation

PolygMap: A Perceptive Locomotion Framework for Humanoid Robot Stair Climbing

Bingquan Li · Ning Wang · Zhicheng He · Yucong Wu · Tianwei Zhang

社会与人本OpenReview

Tianwei Zhang

获取完整研究档案

联系方式