Researcher — paper.dinq.me

2026 顶会论文

作者位次 #3/5ICML 2026Poster· Social Aspects / Security

The Latent Guardian: Defending Collaborative Perception via Feature-Level Consistency Verification

Zhuangzhuang Zhang · MingXin Li · Libing Wu · Wei-Bin Lee · Jianping Wang

安全社会与人本OpenReview

作者位次 #2/6CVPR 2026Poster· Computer Vision & Pattern Recognition

All Vehicles Can Lie: Efficient Adversarial Defense in Fully Untrusted-Vehicle Collaborative Perception via Pseudo-Random Bayesian Inference

Yi Yu · Libing Wu · Zhuangzhuang Zhang · Jing Qiu · Lijuan Huo · Jiaqi Feng

效率与系统安全多模态OpenReview 项目页

作者位次 #7/7ACL 2026Poster· Natural Language Processing

Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents

Yi Yu · Liuyi Yao · Yuexiang Xie · Qingquan Tan · Jiaqi Feng · Yaliang Li · Libing Wu

摘要

Large language model (LLM) agents face fundamental limitations in long-horizon reasoning due to finite context windows, making effective memory management critical. Existing methods typically handle long-term memory (LTM) and short-term memory (STM) as separate components, relying on heuristics o...

强化学习与后训练检索与知识推理OpenReview 项目页

Libing Wu

获取完整研究档案

联系方式

2026 顶会论文

The Latent Guardian: Defending Collaborative Perception via Feature-Level Consistency Verification

All Vehicles Can Lie: Efficient Adversarial Defense in Fully Untrusted-Vehicle Collaborative Perception via Pseudo-Random Bayesian Inference

Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents

常见合作者