14 citations · 17 across the 12 of their papers we have counts for
13 papers
FisherDistill: Diffusion Distribution Distillation via Closed-Form Fisher Critics
Mahesh Bhosale, Yuanhao Zhai, Siwei Lyu +3
Recent advances in diffusion distillation have enabled high-quality image generation in only one or a few network function evaluations (NFEs). Despite their efficiency, aggressivel…
Scaling Muon for Diffusion Transformers
Chenghao Li, Xiao Han, Xinxin Huang +22
The matrix-aware optimizer Muon improves large model training by balancing updates across singular directions, yet its scaling behavior and end-to-end efficiency on large Diffusion…
PathDiff: Histopathology Image Synthesis with Unpaired Text and Mask Conditions
Mahesh Bhosale, Abdul Wasi, Yuanhao Zhai +7
Diffusion-based generative models have shown promise in synthesizing histopathology images to address data scarcity caused by privacy constraints. Diagnostic text reports provide h…
SlowFast-VGen: Slow-Fast Learning for Action-Driven Long Video Generation
Yining Hong, Beide Liu, Maxine Wu +9
Human beings are endowed with a complementary learning system, which bridges the slow learning of general world dynamics with fast storage of episodic memory from a new experience.…
IDOL: Unified Dual-Modal Latent Diffusion for Human-Centric Joint Video-Depth Generation
Yuanhao Zhai, Kevin Lin, Linjie Li +7
Significant advances have been made in human-centric video generation, yet the joint video-depth generation problem remains underexplored. Most existing monocular depth estimation…
Motion Consistency Model: Accelerating Video Diffusion with Disentangled Motion-Appearance Distillation
Yuanhao Zhai, Kevin Lin, Zhengyuan Yang +6
Image diffusion distillation achieves high-fidelity generation with very few sampling steps. However, applying these techniques directly to video diffusion often results in unsatis…
STAT: Towards Generalizable Temporal Action Localization
Yangcen Liu, Ziyi Liu, Yuanhao Zhai +3
Weakly-supervised temporal action localization (WTAL) aims to recognize and localize action instances with only video-level labels. Despite the significant progress, existing metho…
SOAR: Scene-debiasing Open-set Action Recognition
Yuanhao Zhai, Ziyi Liu, Zhenyu Wu +5
Deep learning models have a risk of utilizing spurious clues to make predictions, such as recognizing actions based on the background scene. This issue can severely degrade the ope…
Towards Generic Image Manipulation Detection with Weakly-Supervised Self-Consistency Learning
Yuanhao Zhai, Tianyu Luan, David Doermann +1
As advanced image manipulation techniques emerge, detecting the manipulation becomes increasingly important. Despite the success of recent learning-based approaches for image manip…
Language-guided Human Motion Synthesis with Atomic Actions
Yuanhao Zhai, Mingzhen Huang, Tianyu Luan +5
Language-guided human motion synthesis has been a challenging task due to the inherent complexity and diversity of human behaviors. Previous methods face limitations in generalizat…
High Fidelity 3D Hand Shape Reconstruction via Scalable Graph Frequency Decomposition
Tianyu Luan, Yuanhao Zhai, Jingjing Meng +4
Despite the impressive performance obtained by recent single-image hand modeling techniques, they lack the capability to capture sufficient details of the 3D hand mesh. This defici…
Two-Stream Consensus Network: Submission to HACS Challenge 2021 Weakly-Supervised Learning Track
Yuanhao Zhai, Le Wang, David Doermann +1
This technical report presents our solution to the HACS Temporal Action Localization Challenge 2021, Weakly-Supervised Learning Track. The goal of weakly-supervised temporal action…
Two-Stream Consensus Network for Weakly-Supervised Temporal Action Localization
Yuanhao Zhai, Le Wang, Wei Tang +3
Weakly-supervised Temporal Action Localization (W-TAL) aims to classify and localize all action instances in an untrimmed video under only video-level supervision. However, without…