2 citations · 3 across the 5 of their papers we have counts for
8 papers
SGF+: Decoupling Gradient Flows for Autoregressive Video Generation
Zihan Su, Junhao Zhuang, Yaowei Li +10
Autoregressive video generation requires denoising the current frames while writing their key-value representations as context for future predictions. However, these two roles typi…
Where and When to Force: Routed Forcing for Streaming Avatars
Zihan Su, Siwen Lu, Junhao Zhuang +6
Audio-driven streaming avatar generation requires real-time synthesis of speech-synchronized videos with dynamic and diverse motion. Self Forcing uses Distribution Matching Distill…
NarraScore: Bridging Visual Narrative and Musical Dynamics via Hierarchical Affective Control
Yufan Wen, Zhaocheng Liu, YeGuo Hua +4
Synthesizing coherent soundtracks for long-form videos remains a formidable challenge, currently stalled by three critical impediments: computational scalability, temporal coherenc…
A Mamba-Based Model for Automatic Chord Recognition
Chunyu Yuan, Johanna Devaney
In this work, we propose a new efficient solution, which is a Mamba-based model named BMACE (Bidirectional Mamba-based network, for Automatic Chord Estimation), which utilizes sele…
FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolution
Junhao Zhuang, Shi Guo, Xin Cai +4
Diffusion models have recently advanced video restoration, but applying them to real-world video super-resolution (VSR) remains challenging due to high latency, prohibitive computa…
Safe-Sora: Safe Text-to-Video Generation via Graphical Watermarking
Zihan Su, Xuerui Qiu, Hongbin Xu +6
The explosive growth of generative video models has amplified the demand for reliable copyright preservation of AI-generated content. Despite its popularity in image synthesis, inv…
TextureDiffusion: Target Prompt Disentangled Editing for Various Texture Transfer
Zihan Su, Junhao Zhuang, Chun Yuan
Recently, text-guided image editing has achieved significant success. However, existing methods can only apply simple textures like wood or gold when changing the texture of an obj…
A Task is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpainting
Junhao Zhuang, Yanhong Zeng, Wenran Liu +2
Advancing image inpainting is challenging as it requires filling user-specified regions for various intents, such as background filling and object synthesis. Existing approaches fo…