activity
20242026
collaborators

7 papers

cs.CV2026

GrOCE:Graph-Guided Online Concept Erasure for Text-to-Image Diffusion Models

Ning Han, Zhenyu Ge, Feng Han +3

Concept erasure aims to remove harmful, inappropriate, or copyrighted content from text-to-image diffusion models while preserving non-target semantics. However, existing methods e…

cs.CV2025

ControlThinker: Unveiling Latent Semantics for Controllable Image Generation through Visual Reasoning

Feng Han, Yang Jiao, Shaoxiang Chen +3

The field of controllable image generation has seen significant advancements, with various architectures improving generation layout consistency with control signals. However, cont…

cs.CV2025

UniREditBench: A Unified Reasoning-based Image Editing Benchmark

Feng Han, Yibin Wang, Chenglin Li +8

Recent advances in multi-modal generative models have driven substantial improvements in image editing. However, current generative models still struggle with handling diverse and…

cs.CV2025

VCE: Safe Autoregressive Image Generation via Visual Contrast Exploitation

Feng Han, Chao Gong, Zhipeng Wei +2

Recently, autoregressive image generation models have wowed audiences with their remarkable capability in creating surprisingly realistic images. Models such as GPT-4o and LlamaGen…

cs.LG2025

Dual-LoRA and Quality-Enhanced Pseudo Replay for Multimodal Continual Food Learning

Xinlan Wu, Bin Zhu, Feng Han +2

Food analysis has become increasingly critical for health-related tasks such as personalized nutrition and chronic disease prevention. However, existing large multimodal models (LM…

cs.CV2025

DuMo: Dual Encoder Modulation Network for Precise Concept Erasure

Feng Han, Kai Chen, Chao Gong +3

The exceptional generative capability of text-to-image models has raised substantial safety concerns regarding the generation of Not-Safe-For-Work (NSFW) content and potential copy…