Researcher — paper.dinq.me

2026 顶会论文

作者位次 #5/5NeurIPS 2026Poster

Scalable Minimal-Change Learning for Controllable Image Editing

Shuo Chen · Fengming Huang · Yu Yao · Mingming Gong · Tongliang Liu

多模态OpenReview

作者位次 #9/9NeurIPS 2026Poster

Ultra-DPO: Reimagining LLM Alignment as a Semi-Supervised Task

Li He · Jiaxian Guo · Yaqing Wang · Yue Yang · He Zhao · Stephen Wan · Dadong Wang · Lina Yao · Tongliang Liu

对齐与偏好OpenReview

作者位次 #4/5NeurIPS 2026Poster· Applications / Language, Speech and Dialog

Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory

Jingwei Sun · Jianing Zhu · Jiangchao Yao · Tongliang Liu · Bo Han

检索与知识智能体与工具多模态OpenReview

作者位次 #2/2NeurIPS 2026Poster· General Machine Learning / Causality

Causal Effect Identification with a Single Agnostic Proxy

Xiu-Chuan Li · Tongliang Liu

OpenReview

作者位次 #5/5NeurIPS 2026Poster

Chain-of-Thought Oversight Should Not Treat Faithfulness as Monitorability

Sichao Li · Sai Ma · Xiyang Hu · Chudi Zhong · Tongliang Liu

推理OpenReview

作者位次 #6/6NeurIPS 2026Poster· Applications / Chemistry and Drug Discovery

Adaptive Multi-Frame Learning for Expressive and Stable Atomic Representations

Jun Wang · Yifan Zeng · Bo Han · Fengwang Li · Aoni Xu · Tongliang Liu

可解释性理论与学习动力学OpenReview

作者位次 #6/6NeurIPS 2026Poster

Rethinking Parallel Multi-Agent Systems: A Cost-Aware Framework for Efficient Coordination

Yexiong Lin · Shanshan Ye · Yu Yao · Zhen Fang · Bo Han · Tongliang Liu

智能体与工具效率与系统OpenReview

作者位次 #4/7NeurIPS 2026Poster· Social Aspects / Accountability, Transparency and Interpretability

Taming CoT Obfuscation in VLMs: From Mechanistic Evidence to Activation-Level Enforcement

Xutao Mao · Jianing Zhu · Jinman Zhao · Tongliang Liu · Xiaowen Chu · Cong Wang (Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences) · Bo Han

可解释性推理多模态OpenReview

作者位次 #5/5NeurIPS 2026Poster

My Video Stays Mine: Temporally Consistent Universal Adversarial Perturbations against Video Customization

Yuxin Huang · Mingming Gong · Wanyu Wang · Jing Zhang · Tongliang Liu

安全多模态OpenReview

Tongliang Liu

获取完整研究档案

联系方式

2026 顶会论文

Scalable Minimal-Change Learning for Controllable Image Editing

Ultra-DPO: Reimagining LLM Alignment as a Semi-Supervised Task

Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory

Causal Effect Identification with a Single Agnostic Proxy

Chain-of-Thought Oversight Should Not Treat Faithfulness as Monitorability

Adaptive Multi-Frame Learning for Expressive and Stable Atomic Representations

Rethinking Parallel Multi-Agent Systems: A Cost-Aware Framework for Efficient Coordination

Taming CoT Obfuscation in VLMs: From Mechanistic Evidence to Activation-Level Enforcement

My Video Stays Mine: Temporally Consistent Universal Adversarial Perturbations against Video Customization

常见合作者