activity
20242026
collaborators

14 papers

cs.LG2026

Outlier Smoothing with Closed-Form Rotations for W4A4 Large Language Model Quantization

Jinying Xiao, Bin Ji, Shasha Li +8

Large Language Models (LLMs) quantization facilitates deploying LLMs in resource-limited settings, but existing methods that combine incompatible gradient optimization and quantiza…

cs.CL2026

EMSEdit: Efficient Multi-Step Meta-Learning-based Model Editing

Xiaopeng Li, Shasha Li, Xi Wang +7

Large Language Models (LLMs) power numerous AI applications, yet updating their knowledge remains costly. Model editing provides a lightweight alternative through targeted paramete…

cs.CL2026

Rethinking Residual Distribution in Locate-then-Edit Model Editing

Xiaopeng Li, Shanwen Wang, Shasha Li +4

Model editing enables targeted updates to the knowledge of large language models (LLMs) with minimal retraining. Among existing approaches, locate-then-edit methods constitute a pr…

cs.CV2026

Where Does Vision Meet Language? Understanding and Refining Visual Fusion in MLLMs via Contrastive Attention

Shezheng Song, Shasha Li, Jie Yu +6

Multimodal Large Language Models (MLLMs) have achieved remarkable progress in vision-language understanding, yet how they internally integrate visual and textual information remain…

cs.CV2026

Seeing Right but Saying Wrong: Inter- and Intra-Layer Refinement in MLLMs without Training

Shezheng Song, Shasha Li, Jie Yu

Multimodal Large Language Models (MLLMs) have demonstrated strong capabilities across a variety of vision-language tasks. However, their internal reasoning often exhibits a critica…

cs.CR2026

JPU: Bridging Jailbreak Defense and Unlearning via On-Policy Path Rectification

Xi Wang, Songlei Jian, Shasha Li +5

Despite extensive safety alignment, Large Language Models (LLMs) often fail against jailbreak attacks. While machine unlearning has emerged as a promising defense by erasing specif…