Shilin Lu

Orcid: 0000-0003-2848-0619

According to our database1, Shilin Lu authored at least 18 papers between 2013 and 2026.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
MFSR: MeanFlow Distillation for One Step Real-World Image Super Resolution.
CoRR, March, 2026

LUVE : Latent-Cascaded Ultra-High-Resolution Video Generation with Dual Frequency Experts.
CoRR, February, 2026

2025
Revoking Amnesia: RL-based Trajectory Optimization to Resurrect Erased Concepts in Diffusion Models.
CoRR, October, 2025

DragFlow: Unleashing DiT Priors with Region Based Supervision for Drag Editing.
CoRR, October, 2025

Does FLUX Already Know How to Perform Physically Plausible Image Composition?
CoRR, September, 2025

Visual Document Understanding and Question Answering: A Multi-Agent Collaboration Framework with Test-Time Scaling.
CoRR, August, 2025

Temporal-Guided Spiking Neural Networks for Event-Based Human Action Recognition.
CoRR, March, 2025

All That Glitters Is Not Gold: Key-Secured 3D Secrets within 3D Gaussian Splatting.
CoRR, March, 2025

Set You Straight: Auto-Steering Denoising Trajectories to Sidestep Unwanted Concepts.
Proceedings of the 33rd ACM International Conference on Multimedia, 2025

EraseAnything: Enabling Concept Erasure in Rectified Flow Transformers.
Proceedings of the Forty-second International Conference on Machine Learning, 2025

Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024
Electrolytic capacitor surface defect detection based on deep convolution neural network.
J. King Saud Univ. Comput. Inf. Sci., February, 2024

EraseAnything: Enabling Concept Erasure in Rectified Flow Transformers.
CoRR, 2024

OFTSR: One-Step Flow for Image Super-Resolution with Tunable Fidelity-Realism Trade-offs.
CoRR, 2024

MACE: Mass Concept Erasure in Diffusion Models.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

2023
TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

2022
Copy-move image forgery detection based on evolving circular domains coverage.
Multim. Tools Appl., 2022

2013
Reporting an Experience on Design and Implementation of e-Health Systems on Azure Cloud.
Proceedings of the Internet and Distributed Computing Systems, 2013


  Loading...