Linyu Tang

Yunnan University

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Computer Vision (1)Multimodal Models (1)Red-Teaming & Adversarial Robustness (1)

Frequent co-authors

Yonglong Zou (1)Yong Zou (1)Haoran Li (1)Fanxiao Li (1)

Papers (1)

Mar 17, 2026

2w ago·also NVIDIA, D VAE for spatiotemporal latent encoding, Northeastern

REFORGE: Multi-modal Attacks Reveal Vulnerable Concept Unlearning in Image Generation Models

Current image generation unlearning methods are surprisingly brittle: adversarial image prompts, optimized with attention-guided masking, can effectively resurrect supposedly "forgotten" concepts.

Yonglong Zou, Yong Zou, Haoran Li +7

Computer Vision Multimodal Models Red-Teaming & Adversarial Robustness

Search

Linyu Tang

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)