activity
20232026
most citedExploring Large Language Models for Multimodal Sentiment Analysis: Challenges, Benchmarks, and Future Directions

1 citations · 1 across the 8 of their papers we have counts for

collaborators

16 papers

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.CV2026

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

Shezheng Song, Shasha Li, Shan Zhao +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.NI2025

Camel: Energy-Aware LLM Inference on Resource-Constrained Devices

Hao Xu, Long Peng, Shezheng Song +5

Most Large Language Models (LLMs) are currently deployed in the cloud, with users relying on internet connectivity for access. However, this paradigm faces challenges such as netwo…

cs.CL2025

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.CL2025

How to Alleviate Catastrophic Forgetting in LLMs Finetuning? Hierarchical Layer-Wise and Element-Wise Regularization

Shezheng Song, Hao Xu, Jun Ma +5

Large Language Models (LLMs) exhibit strong general language capabilities. However, fine-tuning these models on domain-specific tasks often leads to catastrophic forgetting, where…

cs.CL2025

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…