activity
20242026
collaborators

18 papers

cs.CL2026

Morphing into Hybrid Attention Models

Disen Lan, Jianbin Zheng, Yuxi Ren +5

Hybrid attention models improve long-context efficiency by retaining only a subset of full-attention layers and replacing the remaining layers with linear attention. However, the e…

cs.CV2026

SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training

Jianyi Wang, Shanchuan Lin, Zhijie Lin +10

Recent advances in diffusion-based video restoration (VR) demonstrate significant improvement in visual quality, yet yield a prohibitive computational cost during inference. While…

cs.CV2025

OnlineVPO: Align Video Diffusion Model with Online Video-Centric Preference Optimization

Jiacheng Zhang, Jie Wu, Weifeng Chen +4

Video diffusion models (VDMs) have demonstrated remarkable capabilities in text-to-video (T2V) generation. Despite their success, VDMs still suffer from degraded image quality and…

cs.CV2025

Seedream 4.0: Toward Next-generation Multimodal Image Generation

Team Seedream, :, Yunpeng Chen +48

We introduce Seedream 4.0, an efficient and high-performance multimodal image generation system that unifies text-to-image (T2I) synthesis, image editing, and multi-image compositi…

cs.CV2025

Dense2MoE: Restructuring Diffusion Transformer to MoE for Efficient Text-to-Image Generation

Youwei Zheng, Yuxi Ren, Xin Xia +2

Diffusion Transformer (DiT) has demonstrated remarkable performance in text-to-image generation; however, its large parameter size results in substantial inference overhead. Existi…

cs.CV2025

Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation

Shanchuan Lin, Ceyuan Yang, Hao He +6

Existing large-scale video generation models are computationally intensive, preventing adoption in real-time and interactive applications. In this work, we propose autoregressive a…