Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length Paper • 2512.04677 • Published 4 days ago • 148
XC-Cache: Cross-Attending to Cached Context for Efficient LLM Inference Paper • 2404.15420 • Published Apr 23, 2024 • 11
BASS: Batched Attention-optimized Speculative Sampling Paper • 2404.15778 • Published Apr 24, 2024 • 11
MaGGIe: Masked Guided Gradual Human Instance Matting Paper • 2404.16035 • Published Apr 24, 2024 • 12
ID-Aligner: Enhancing Identity-Preserving Text-to-Image Generation with Reward Feedback Learning Paper • 2404.15449 • Published Apr 23, 2024 • 14
MotionMaster: Training-free Camera Motion Transfer For Video Generation Paper • 2404.15789 • Published Apr 24, 2024 • 13
CatLIP: CLIP-level Visual Recognition Accuracy with 2.7x Faster Pre-training on Web-scale Image-Text Data Paper • 2404.15653 • Published Apr 24, 2024 • 29
PuLID: Pure and Lightning ID Customization via Contrastive Alignment Paper • 2404.16022 • Published Apr 24, 2024 • 25
MagicProp: Diffusion-based Video Editing via Motion-aware Appearance Propagation Paper • 2309.00908 • Published Sep 2, 2023 • 6
Sequential Dexterity: Chaining Dexterous Policies for Long-Horizon Manipulation Paper • 2309.00987 • Published Sep 2, 2023 • 4
Compositional Diffusion-Based Continuous Constraint Solvers Paper • 2309.00966 • Published Sep 2, 2023 • 6