20 citations · 23 across the 16 of their papers we have counts for
8 papers · 1 filter
DragFlow: Unleashing DiT Priors with Region Based Supervision for Drag Editing
Zihan Zhou, Shilin Lu, Shuli Leng +4
Drag-based image editing has long suffered from distortions in the target region, largely because the priors of earlier base models, Stable Diffusion, are insufficient to project o…
Revoking Amnesia: RL-based Trajectory Optimization to Resurrect Erased Concepts in Diffusion Models
Daiheng Gao, Nanxiang Jiang, Andi Zhang +5
Concept erasure techniques have been widely deployed in T2I diffusion models to prevent inappropriate content generation for safety and copyright considerations. However, as models…
Does FLUX Already Know How to Perform Physically Plausible Image Composition?
Shilin Lu, Zhuming Lian, Zihan Zhou +3
Image composition aims to seamlessly insert a user-specified object into a new scene, but existing models struggle with complex lighting (e.g., accurate shadows, water reflections)…
Visual Document Understanding and Reasoning: A Multi-Agent Collaboration Framework with Agent-Wise Adaptive Test-Time Scaling
Xinlei Yu, Chengming Xu, Zhangquan Chen +6
The dominant paradigm of monolithic scaling in Vision-Language Models (VLMs) is failing for understanding and reasoning in documents, yielding diminishing returns as it struggles w…
Set You Straight: Auto-Steering Denoising Trajectories to Sidestep Unwanted Concepts
Leyang Li, Shilin Lu, Yan Ren +1
Ensuring the ethical deployment of text-to-image models requires effective techniques to prevent the generation of harmful or inappropriate content. While concept erasure methods o…
All That Glitters Is Not Gold: Key-Secured 3D Secrets within 3D Gaussian Splatting
Yan Ren, Shilin Lu, Adams Wai-Kin Kong
Recent advances in 3D Gaussian Splatting (3DGS) have revolutionized scene reconstruction, opening new possibilities for 3D steganography by hiding 3D secrets within 3D covers. The…
Temporal-Guided Spiking Neural Networks for Event-Based Human Action Recognition
Siyuan Yang, Shilin Lu, Shizheng Wang +3
This paper explores the promising interplay between spiking neural networks (SNNs) and event-based cameras for privacy-preserving human action recognition (HAR). The unique feature…
EraseAnything: Enabling Concept Erasure in Rectified Flow Transformers
Daiheng Gao, Shilin Lu, Shaw Walters +8
Removing unwanted concepts from large-scale text-to-image (T2I) diffusion models while maintaining their overall generative quality remains an open challenge. This difficulty is es…