Beyond Autoregression: Fast LLMs via Self-Distillation Through Time Paper • 2410.21035 • Published Oct 28, 2024
Unpacking SDXL Turbo: Interpreting Text-to-Image Models with Sparse Autoencoders Paper • 2410.22366 • Published Oct 28, 2024 • 78
Going beyond Compositions, DDPMs Can Produce Zero-Shot Interpolations Paper • 2405.19201 • Published May 29, 2024
Maximum Independent Set: Self-Training through Dynamic Programming Paper • 2310.18672 • Published Oct 28, 2023 • 1