collaborators

11 papers

cs.CV2026

Dual-branch Robust Unlearnable Examples

Xianlong Wang, Hangtao Zhang, Wenbo Pan +4

Unlearnable examples (UEs) aim to compromise model training by injecting imperceptible perturbations to clean samples. However, existing UE schemes exhibit limited robustness again…

cs.AI2026

Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference

Wenbo Pan, Shujie Liu, Chin-Yew Lin +5

AI agents rely on a harness of skills, tools, and workflows to solve complex problems. Continually improving this harness is essential for adapting to new tasks. However, existing…

cs.LG2026

Towards Long-Horizon Interpretability: Efficient and Faithful Multi-Token Attribution for Reasoning LLMs

Wenbo Pan, Zhichao Liu, Xianlong Wang +2

Token attribution methods provide intuitive explanations for language model outputs by identifying causally important input tokens. However, as modern LLMs increasingly rely on ext…

cs.PL2026

M: Every Task Deserves Its Own Memory Harness

Wenbo Pan, Shujie Liu, Xiangyang Zhou +4

Large language model agents rely on specialized memory systems to accumulate and reuse knowledge during extended interactions. Recent architectures typically adopt a fixed memory d…

cs.CV2026

Image-to-Video Diffusion: From Foundations to Open Frontiers

Xianlong Wang, Wenbo Pan, Shijia Zhou +6

Diffusion-based \textit{image-to-video} (I2V) generation has become a central direction in generative models by turning a reference image, with optional conditions, into a temporal…

cs.CL2026

Can LLMs Refuse Questions They Do Not Know? Measuring Knowledge-Aware Refusal in Factual Tasks

Wenbo Pan, Jie Xu, Qiguang Chen +5

Large Language Models (LLMs) should refuse to answer questions beyond their knowledge. This capability, which we term knowledge-aware refusal, is crucial for factual reliability, w…