Summary of Snapgen-v: Generating a Five-second Video Within Five Seconds on a Mobile Device, by Yushu Wu et al.
SnapGen-V: Generating a Five-Second Video within Five Seconds on a Mobile Deviceby Yushu Wu, Zhixing…
SnapGen-V: Generating a Five-Second Video within Five Seconds on a Mobile Deviceby Yushu Wu, Zhixing…
SVGFusion: Scalable Text-to-SVG Generation via Vector Space Diffusionby Ximing Xing, Juncheng Hu, Jing Zhang, Dong…
Simple Guidance Mechanisms for Discrete Diffusion Modelsby Yair Schiff, Subham Sekhar Sahoo, Hao Phung, Guanghan…
Efficient Generative Modeling with Residual Vector Quantization-Based Tokensby Jaehyeon Kim, Taehong Moon, Keon Lee, Jaewoong…
EP-CFG: Energy-Preserving Classifier-Free Guidanceby Kai Zhang, Fujun Luan, Sai Bi, Jianming ZhangFirst submitted to arxiv…
The Unreasonable Effectiveness of Gaussian Score Approximation for Diffusion Models and its Applicationsby Binxu Wang,…
Learning Structural Causal Models from Ordering: Identifiable Flow Modelsby Minh Khoa Le, Kien Do, Truyen…
LinGen: Towards High-Resolution Minute-Length Text-to-Video Generation with Linear Computational Complexityby Hongjie Wang, Chih-Yao Ma, Yen-Cheng…
SimAvatar: Simulation-Ready Avatars with Layered Hair and Clothingby Xueting Li, Ye Yuan, Shalini De Mello,…
Auto-Regressive Moving Diffusion Models for Time Series Forecastingby Jiaxin Gao, Qinglong Cao, Yuntian ChenFirst submitted…