Submitted by akhaliq 34 Schrodinger Bridges Beat Diffusion Models on Text-to-Speech Synthesis · 5 authors
Submitted by akhaliq 23 Gaussian Head Avatar: Ultra High-fidelity Head Avatar via Dynamic Gaussians · 7 authors 3
Submitted by akhaliq 20 MotionCtrl: A Unified and Flexible Motion Controller for Video Generation · 7 authors 2
Submitted by akhaliq 17 Cache Me if You Can: Accelerating Diffusion Models through Block Caching · 14 authors
Submitted by akhaliq 15 HiFi4G: High-Fidelity Human Performance Rendering via Compact Gaussian Splatting · 8 authors
Submitted by akhaliq 12 LooseControl: Lifting ControlNet for Generalized Depth Conditioning · 3 authors 2
Submitted by akhaliq 9 MagicStick: Controllable Video Editing via Control Handle Transformations · 8 authors 2
Submitted by akhaliq 8 Generative agent-based modeling with actions grounded in physical, social, or digital space using Concordia · 10 authors
Submitted by akhaliq 7 DreamComposer: Controllable 3D Object Generation via Multi-View Conditions · 8 authors
Submitted by akhaliq 5 HybridNeRF: Efficient Neural Rendering via Adaptive Volumetric Surfaces · 8 authors
Submitted by akhaliq 4 Multimodal Data and Resource Efficient Device-Directed Speech Detection with Large Foundation Models · 7 authors