activity
20242026
collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2026

HumanNOVA: Photorealistic, Universal and Rapid 3D Human Avatar Modeling from a Single Image

Hezhen Hu, Wangbo Zhao, Lanqing Guo +6

In this paper, we present HumanNOVA, a photorealistic, universal, and rapid model for generating 3D human avatars from a single RGB image. Achieving both photorealism and generaliz…

cs.CV2025

RAPID^3: Tri-Level Reinforced Acceleration Policies for Diffusion Transformer

Wangbo Zhao, Yizeng Han, Zhiwei Tang +7

Diffusion Transformers (DiTs) excel at visual generation yet remain hampered by slow sampling. Existing training-free accelerators - step reduction, feature caching, and sparse att…

cs.CV2025

DD-Ranking: Rethinking the Evaluation of Dataset Distillation

Zekai Li, Xinhao Zhong, Samir Khaki +49

In recent years, dataset distillation has provided a reliable solution for data compression, where models trained on the resulting smaller synthetic datasets achieve performance co…

cs.CV2025

REPA Works Until It Doesn't: Early-Stopped, Holistic Alignment Supercharges Diffusion Training

Ziqiao Wang, Wangbo Zhao, Yuhao Zhou +9

Diffusion Transformers (DiTs) deliver state-of-the-art image quality, yet their training remains notoriously slow. A recent remedy -- representation alignment (REPA) that matches D…

cs.CV2025

Enhance-A-Video: Better Generated Video for Free

Yang Luo, Xuanlei Zhao, Mengzhao Chen +5

DiT-based video generation has achieved remarkable results, but research into enhancing existing models remains relatively unexplored. In this work, we introduce a training-free ap…

cs.CV2024

A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs

Wangbo Zhao, Yizeng Han, Jiasheng Tang +5

Vision-language models (VLMs) have shown remarkable success across various multi-modal tasks, yet large VLMs encounter significant efficiency challenges due to processing numerous…