Shilin Lu

Shilin-LU's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 3 papers 2 months ago

DragFlow: Unleashing DiT Priors with Region Based Supervision for Drag Editing

Paper • 2510.02253 • Published Oct 2 • 14

Visual Document Understanding and Question Answering: A Multi-Agent Collaboration Framework with Test-Time Scaling

Paper • 2508.03404 • Published Aug 5 • 4

Does FLUX Already Know How to Perform Physically Plausible Image Composition?

Paper • 2509.21278 • Published Sep 25 • 16

authored 4 papers 8 months ago

Set You Straight: Auto-Steering Denoising Trajectories to Sidestep Unwanted Concepts

Paper • 2504.12782 • Published Apr 17 • 3

All That Glitters Is Not Gold: Key-Secured 3D Secrets within 3D Gaussian Splatting

Paper • 2503.07191 • Published Mar 10

EraseAnything: Enabling Concept Erasure in Rectified Flow Transformers

Paper • 2412.20413 • Published Dec 29, 2024

OFTSR: One-Step Flow for Image Super-Resolution with Tunable Fidelity-Realism Trade-offs

Paper • 2412.09465 • Published Dec 12, 2024

authored 3 papers about 1 year ago

Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances

Paper • 2410.18775 • Published Oct 24, 2024 • 10

MACE: Mass Concept Erasure in Diffusion Models

Paper • 2403.06135 • Published Mar 10, 2024 • 1

TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition

Paper • 2307.12493 • Published Jul 24, 2023