4 citations · 5 across the 6 of their papers we have counts for
7 papers
Frame Differential On-Policy Self-Distillation for Video Reasoning
Haiying He, Xin Zheng, Shaoli Hu +4
Reinforcement learning (RL) has substantially improved the reasoning ability of multimodal language models through verifiable rewards and increasingly fine-grainedvisual or tempora…
An Empirical Study of Training Pixel-Space Text-to-Image Diffusion Models
Dengyang Jiang, Ruoyi Du, Zhennan Chen +10
This paper investigates an increasingly important topic in generative modeling: pixel-space diffusion models. Although numerous studies have explored this topic, most focus on smal…
LCG: Long-Context Consistent Image Generation with Sparse Relational Attention
Zihao Wang, Yijia Xu, Haoze Zheng +3
Recent image generation models achieve impressive quality in single-image synthesis, but often fail to maintain consistency across sequential outputs, as required in comics, storyb…
D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models
Dengyang Jiang, Xin Jin, Dongyang Liu +9
The landscape of high-performance image generation models is currently shifting from the inefficient multi-step ones to the efficient few-step counterparts (e.g, Z-Image-Turbo and…
RainFusion2.0: Temporal-Spatial Awareness and Hardware-Efficient Block-wise Sparse Attention
Aiyue Chen, Yaofu Liu, Junjian Huang +6
In video and image generation tasks, Diffusion Transformer (DiT) models incur extremely high computational costs due to attention mechanisms, which limits their practical applicati…
VFX Creator: Animated Visual Effect Generation with Controllable Diffusion Transformer
Xinyu Liu, Ailing Zeng, Wei Xue +4
Crafting magic and illusions is one of the most thrilling aspects of filmmaking, with visual effects (VFX) serving as the powerhouse behind unforgettable cinematic experiences. Whi…
ConsistI2V: Enhancing Visual Consistency for Image-to-Video Generation
Weiming Ren, Huan Yang, Ge Zhang +4
Image-to-video (I2V) generation aims to use the initial frame (alongside a text prompt) to create a video sequence. A grand challenge in I2V generation is to maintain visual consis…