collaborators

13 papers

cs.CV2026

CRANE: Knowledge Editing for Reasoning MLLMs

Han Huang, Hao Wang, Mengqi Zhang +3

The emergence of reasoning multimodal large language models (MLLMs), which generate explicit chain-of-thought (CoT) reasoning before producing answers, has introduced a new challen…

cs.CL2026

On the Hidden Costs of Counterfactual Knowledge Training in LLM Unlearning

Xiaotian Ye, Xiaohan Wang, Mengqi Zhang +1

Counterfactual tuning (CFT) has emerged as a promising paradigm for Large Language Model (LLM) unlearning by training models to generate alternative fictitious knowledge in place o…

cs.CL2026

Spectral Characterization and Mitigation of Sequential Knowledge Editing Collapse

Chi Zhang, Mengqi Zhang, Xiaotian Ye +5

Sequential knowledge editing in large language models often causes catastrophic collapse of the model's general abilities, especially for parameter-modifying methods. Existing appr…

cs.CL2026

Uncovering Entity Identity Confusion in Multimodal Knowledge Editing

Shu Wu, Xiaotian Ye, Xinyu Mou +3

Multimodal knowledge editing (MKE) aims to correct the internal knowledge of large vision-language models after deployment, yet the behavioral patterns of post-edit models remain u…

cs.CL2026

Uncovering Context Reliance in Unstructured Knowledge Editing

Zisheng Zhou, Mengqi Zhang, Shiguang Wu +4

Editing Large language models (LLMs) with real-world, unstructured knowledge is essential for correcting and updating their internal parametric knowledge. In this work, we revisit…

cs.IR2026

DiffuGR: Generative Document Retrieval with Diffusion Language Models

Xinpeng Zhao, Zhaochun Ren, Yukun Zhao +9

Generative retrieval (GR) reframes document retrieval as an end-to-end task of generating sequential document identifiers (DocIDs). Existing GR methods predominantly rely on left-t…