6 papers
Probabilistic and Alarm-Based Evaluation of a b-Value-Driven Deep Learning Earthquake Forecast
Jonas Köhler, Wei Li, Johannes Faber +2
We evaluate the forecasting performance of a deep learning model, originally introduced as a pattern-extraction framework, that operates on the spatiotemporal evolution of seismic…
Autoregressive Distillation of Diffusion Transformers
Yeongmin Kim, Sotiris Anagnostidis, Yuming Du +6
Diffusion models with transformer architectures have demonstrated promising capabilities in generating high-fidelity images and scalability for high resolution. However, iterative…
Storybooth: Training-free Multi-Subject Consistency for Improved Visual Storytelling
Jaskirat Singh, Junshen Kevin Chen, Jonas Kohler +1
Training-free consistent text-to-image generation depicting the same subjects across different images is a topic of widespread recent interest. Existing works in this direction pre…
FlexiDiT: Your Diffusion Transformer Can Easily Generate High-Quality Samples with Less Compute
Sotiris Anagnostidis, Gregor Bachmann, Yeongmin Kim +7
Despite their remarkable performance, modern Diffusion Transformers are hindered by substantial resource requirements during inference, stemming from the fixed and large amount of…
Movie Gen: A Cast of Media Foundation Models
Adam Polyak, Amit Zohar, Andrew Brown +85
We present Movie Gen, a cast of foundation models that generates high-quality, 1080p HD videos with different aspect ratios and synchronized audio. We also show additional capabili…
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…