collaborators

7 papers

cs.CV2026

StreamEdit: Training-Free Video Editing via Few-Step Streaming Video Generation

Guanlong Jiao, Chenyangguang Zhang, Jia Jun Cheng Xian +2

Although existing video editing methods are generally feasible, they often require many costly iterations and still struggle to deliver high-quality yet satisfying editing results.…

cs.CV2026

Stable Velocity: A Variance Perspective on Flow Matching

Donglin Yang, Yongxing Zhang, Xin Yu +5

While flow matching is elegant, its reliance on single-sample conditional velocities leads to high-variance training targets that destabilize optimization and slow convergence. By…

cs.CV2026

UniEdit-Flow: Unleashing Inversion and Editing in the Era of Flow Models

Guanlong Jiao, Biqing Huang, Kuan-Chieh Wang +1

Flow matching models have emerged as a strong alternative to diffusion models, but existing inversion and editing methods designed for diffusion are often ineffective or inapplicab…

cs.CV2026

TrajLoom: Dense Future Trajectory Generation from Video

Zewei Zhang, Jia Jun Cheng Xian, Kaiwen Liu +4

Predicting future motion is crucial in video understanding and controllable video generation. Dense point trajectories are a compact, expressive motion representation, but modeling…

cs.CV2025

QDM: Quadtree-Based Region-Adaptive Sparse Diffusion Models for Efficient Image Super-Resolution

Donglin Yang, Paul Vicol, Xiaojuan Qi +2

Deep learning-based super-resolution (SR) methods often perform pixel-wise computations uniformly across entire images, even in homogeneous regions where high-resolution refinement…

cs.LG2025

ControlEchoSynth: Boosting Ejection Fraction Estimation Models via Controlled Video Diffusion

Nima Kondori, Hanwen Liang, Hooman Vaseli +5

Synthetic data generation represents a significant advancement in boosting the performance of machine learning (ML) models, particularly in fields where data acquisition is challen…