collaborators

7 papers

cs.LG2026

FairSAM: Fair Classification on Corrupted Image Data Through Sharpness-Aware Minimization

Yucong Dai, Jie Ji, Xiaolong Ma +1

Image classification models trained on clean data often degrade sharply when exposed to corrupted test or deployment data, such as images with impulse noise, Gaussian noise, or env…

cs.CV2026

Forget-It-All: Multi-Concept Machine Unlearning via Concept-Aware Neuron Masking

Kaiyuan Deng, Bo Hui, Gen Li +4

The widespread adoption of text-to-image (T2I) diffusion models has raised concerns about their potential to generate copyrighted, inappropriate, or sensitive imagery. As a practic…

cs.LG2026

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning

Mingyu Cao, Gen Li, Jie Ji +6

Mixture-of-Experts (MoE) has garnered significant attention for its ability to scale up neural networks while utilizing the same or even fewer active parameters. However, MoE does…

cs.LG2025

The Right to be Forgotten in Pruning: Unveil Machine Unlearning on Sparse Models

Yang Xiao, Gen Li, Jie Ji +3

Machine unlearning aims to efficiently eliminate the memory about deleted data from trained models and address the right to be forgotten. Despite the success of existing unlearning…

cs.CV2025

Modality-Aware SAM: Sharpness-Aware-Minimization Driven Gradient Modulation for Harmonized Multimodal Learning

Hossein R. Nowdeh, Jie Ji, Xiaolong Ma +1

In multimodal learning, dominant modalities often overshadow others, limiting generalization. We propose Modality-Aware Sharpness-Aware Minimization (M-SAM), a model-agnostic frame…

q-bio.NC2025

Optimal Transport for Brain-Image Alignment: Unveiling Redundancy and Synergy in Neural Information Processing

Yang Xiao, Wang Lu, Jie Ji +4

The design of artificial neural networks (ANNs) is inspired by the structure of the human brain, and in turn, ANNs offer a potential means to interpret and understand brain signals…