11 papers
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…
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…
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…
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…
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…
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…