CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation
Paper
• 2502.08639 • Published
• 43
Video
-
-
TransMLA: Multi-head Latent Attention Is All You Need
Paper • 2502.07864 • Published • 57 -
Next Block Prediction: Video Generation via Semi-Autoregressive Modeling
Paper • 2502.07737 • Published • 9 -
Enhance-A-Video: Better Generated Video for Free
Paper • 2502.07508 • Published • 21 -
Show-o Turbo: Towards Accelerated Unified Multimodal Understanding and Generation
Paper • 2502.05415 • Published • 20 -
Lumina-Video: Efficient and Flexible Video Generation with Multi-scale Next-DiT
Paper • 2502.06782 • Published • 15 -
Efficient-vDiT: Efficient Video Diffusion Transformers With Attention Tile
Paper • 2502.06155 • Published • 10 -
Goku: Flow Based Video Generative Foundation Models
Paper • 2502.04896 • Published • 106 -
SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model
Paper • 2502.02737 • Published • 256 -
Improved Training Technique for Latent Consistency Models
Paper • 2502.01441 • Published • 8 -
The Ultra-Scale Playbook
🌌3.74kThe ultimate guide to training LLM on large GPU Clusters
-
FineWeb: decanting the web for the finest text data at scale
🍷1.31kGenerate a curated web‑text dataset for LLM training
-
FlexWorld: Progressively Expanding 3D Scenes for Flexiable-View Synthesis
Paper • 2503.13265 • Published • 15 -
Reangle-A-Video: 4D Video Generation as Video-to-Video Translation
Paper • 2503.09151 • Published • 32 -
SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation
Paper • 2503.09641 • Published • 42