ReCapture: Generative Video Camera Controls for User-Provided Videos using Masked Video Fine-Tuningby David Junhao Zhang,…
SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Modelsby Muyang Li, Yujun Lin, Zhekai…
Series-to-Series Diffusion Bridge Modelby Hao Yang, Zhanbo Feng, Feng Zhou, Robert C Qiu, Zenan LingFirst…
Hypercube Policy Regularization Framework for Offline Reinforcement Learningby Yi Shen, Hanyan HuangFirst submitted to arxiv…
Efficient Symmetry-Aware Materials Generation via Hierarchical Generative Flow Networksby Tri Minh Nguyen, Sherif Abdulkader Tawfik,…
Pedestrian Volume Prediction Using a Diffusion Convolutional Gated Recurrent Unit Modelby Yiwei Dong, Tingjin Chu,…
How much is a noisy image worth? Data Scaling Laws for Ambient Diffusionby Giannis Daras,…
Grouped Discrete Representation for Object-Centric Learningby Rongzhen Zhao, Vivienne Wang, Juho Kannala, Joni PajarinenFirst submitted…
Model Integrity when Unlearning with T2I Diffusion Modelsby Andrea Schioppa, Emiel Hoogeboom, Jonathan HeekFirst submitted…
Bridge-IF: Learning Inverse Protein Folding with Markov Bridgesby Yiheng Zhu, Jialu Wu, Qiuyi Li, Jiahuan…