collaborators

7 papers

cs.CV2026

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence

Shuailei Ma, Jiaqi Liao, Xinyang Wang +24

Despite the recent promise in robot control, video generative models suffer from a domain mismatch due to their primary focus on content creation. For example, their design inheren…

cs.LG2026

DCD-PFN: A Decoupling-Aware Foundation Model for Causal Discovery

Zhengkang Guan, Yikang Chen, Yi He +5

Causal discovery is critical for understanding complex data-generating mechanisms, yet traditional algorithms often struggle with highly non-linear and noisy systems, or suffer fro…

cs.CV2026

Asynchronous Denoising Diffusion Models for Aligning Text-to-Image Generation

Zijing Hu, Yunze Tong, Fengda Zhang +3

Diffusion models have achieved impressive results in generating high-quality images. Yet, they often struggle to faithfully align the generated images with the input prompts. This…

cs.CL2025

CDLM: Causal Concept-Guided Diffusion Large Language Models

Kairong Han, Nuanqiao Shan, Ziyu Zhao +6

Autoregressive (AR) language models and Diffusion Language Models (DLMs) constitute the two principal paradigms of large language models. However, both paradigms suffer from insuff…

cs.CV2025

Noise Projection: Closing the Prompt-Agnostic Gap Behind Text-to-Image Misalignment in Diffusion Models

Yunze Tong, Didi Zhu, Zijing Hu +2

In text-to-image generation, different initial noises induce distinct denoising paths with a pretrained Stable Diffusion (SD) model. While this pattern could output diverse images,…

cs.CV2025

D-Fusion: Direct Preference Optimization for Aligning Diffusion Models with Visually Consistent Samples

Zijing Hu, Fengda Zhang, Kun Kuang

The practical applications of diffusion models have been limited by the misalignment between generated images and corresponding text prompts. Recent studies have introduced direct…