2 papers
cs.LG2025
Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment
Gregor Bachmann, Sotiris Anagnostidis, Albert Pumarola +6
The performance of large language models (LLMs) is closely linked to their underlying size, leading to ever-growing networks and hence slower inference. Speculative decoding has be…
cs.CV2024
Imagine Flash: Accelerating Emu Diffusion Models with Backward Distillation
Jonas Kohler, Albert Pumarola, Edgar Schönfeld +4
Diffusion models are a powerful generative framework, but come with expensive inference. Existing acceleration methods often compromise image quality or fail under complex conditio…