activity
20242026
collaborators

7 papers

cs.AI2026

CoTZero: Annotation-Free Human-Like Vision Reasoning via Hierarchical Synthetic CoT

Chengyi Du, Yazhe Niu, Dazhong Shen +1

Recent advances in vision-language models (VLMs) have markedly improved image-text alignment, yet they still fall short of human-like visual reasoning. A key limitation is that man…

cs.CV2025

Pretrained Reversible Generation as Unsupervised Visual Representation Learning

Rongkun Xue, Jinouwen Zhang, Yazhe Niu +4

Recent generative models based on score matching and flow matching have significantly advanced generation tasks, but their potential in discriminative tasks remains underexplored.…

cs.CV2025

ADT: Tuning Diffusion Models with Adversarial Supervision

Dazhong Shen, Guanglu Song, Yi Zhang +5

Diffusion models have achieved outstanding image generation by reversing a forward noising process to approximate true data distributions. During training, these models predict dif…

cs.CV2024

EasyRef: Omni-Generalized Group Image Reference for Diffusion Models via Multimodal LLM

Zhuofan Zong, Dongzhi Jiang, Bingqi Ma +5

Significant achievements in personalization of diffusion models have been witnessed. Conventional tuning-free methods mostly encode multiple reference images by averaging their ima…

cs.LG2024

Phased Consistency Models

Fu-Yun Wang, Zhaoyang Huang, Alexander William Bergman +9

Consistency Models (CMs) have made significant progress in accelerating the generation of diffusion models. However, their application to high-resolution, text-conditioned image ge…

cs.CV2024

CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching

Dongzhi Jiang, Guanglu Song, Xiaoshi Wu +5

Diffusion models have demonstrated great success in the field of text-to-image generation. However, alleviating the misalignment between the text prompts and images is still challe…