VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time Paper โข 2404.10667 โข Published Apr 16, 2024 โข 24 โข 2
Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length Paper โข 2404.08801 โข Published Apr 12, 2024 โข 66 โข 2