An Image is Worth 32 Tokens for Reconstruction and Generation Paper • 2406.07550 • Published Jun 11 • 55
Layer Skip: Enabling Early Exit Inference and Self-Speculative Decoding Paper • 2404.16710 • Published Apr 25 • 57
Better & Faster Large Language Models via Multi-token Prediction Paper • 2404.19737 • Published Apr 30 • 73
Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting Paper • 2404.18911 • Published Apr 29 • 29
Mixture-of-Depths: Dynamically allocating compute in transformer-based language models Paper • 2404.02258 • Published Apr 2 • 103
Multitrack Music Transcription with a Time-Frequency Perceiver Paper • 2306.10785 • Published Jun 19, 2023 • 5