One-Minute Video Generation with Test-Time Training
Paper • 2504.05298 • Published • 110
read
-
-
MoCha: Towards Movie-Grade Talking Character Synthesis
Paper • 2503.23307 • Published • 141 -
Towards Understanding Camera Motions in Any Video
Paper • 2504.15376 • Published • 157 -
Antidistillation Sampling
Paper • 2504.13146 • Published • 59 -
TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization
Paper • 2503.19901 • Published • 41 -
DreamActor-M1: Holistic, Expressive and Robust Human Image Animation with Hybrid Guidance
Paper • 2504.01724 • Published • 68 -
Long Video Diffusion Generation with Segmented Cross-Attention and Content-Rich Video Data Curation
Paper • 2412.01316 • Published • 10 -
STIV: Scalable Text and Image Conditioned Video Generation
Paper • 2412.07730 • Published • 74 -
VidGen-1M: A Large-Scale Dataset for Text-to-video Generation
Paper • 2408.02629 • Published • 15 -
VideoUFO: A Million-Scale User-Focused Dataset for Text-to-Video Generation
Paper • 2503.01739 • Published • 9 -
Video-T1: Test-Time Scaling for Video Generation
Paper • 2503.18942 • Published • 90 -
VideoGuide: Improving Video Diffusion Models without Training Through a Teacher's Guide
Paper • 2410.04364 • Published • 29 -
Improving Video Generation with Human Feedback
Paper • 2501.13918 • Published • 53 -
Training-free Long Video Generation with Chain of Diffusion Model Experts
Paper • 2408.13423 • Published • 23 -
VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models
Paper • 2502.02492 • Published • 66 -
OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models
Paper • 2502.01061 • Published • 225 -
Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps
Paper • 2501.09732 • Published • 72 -
LTX-Video: Realtime Video Latent Diffusion
Paper • 2501.00103 • Published • 50 -
Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
Paper • 2412.05271 • Published • 160 -
VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM
Paper • 2501.00599 • Published • 46 -
Shifting AI Efficiency From Model-Centric to Data-Centric Compression
Paper • 2505.19147 • Published • 145 -
AttentionInfluence: Adopting Attention Head Influence for Weak-to-Strong Pretraining Data Selection
Paper • 2505.07293 • Published • 28 -
Alchemist: Turning Public Text-to-Image Data into Generative Gold
Paper • 2505.19297 • Published • 84 -
Predictive Data Selection: The Data That Predicts Is the Data That Teaches
Paper • 2503.00808 • Published • 57 -
R&B: Domain Regrouping and Data Mixture Balancing for Efficient Foundation Model Training
Paper • 2505.00358 • Published • 26 -
ICon: In-Context Contribution for Automatic Data Selection
Paper • 2505.05327 • Published • 12 -
SWE-smith: Scaling Data for Software Engineering Agents
Paper • 2504.21798 • Published • 15 -
MoDoMoDo: Multi-Domain Data Mixtures for Multimodal LLM Reinforcement Learning
Paper • 2505.24871 • Published • 23 -
Programming Every Example: Lifting Pre-training Data Quality like Experts at Scale
Paper • 2409.17115 • Published • 64