6 papers
Sparse Forcing: Native Trainable Sparse Attention for Real-time Autoregressive Diffusion Video Generation
Boxun Xu, Yuming Du, Zichang Liu +7
We introduce Sparse Forcing, a training-and-inference paradigm for autoregressive video diffusion models that improves long-horizon generation quality while reducing decoding laten…
SneakPeek: Future-Guided Instructional Streaming Video Generation
Cheeun Hong, German Barquero, Fadime Sener +6
Instructional video generation is an emerging task that aims to synthesize coherent demonstrations of procedural activities from textual descriptions. Such capability has broad imp…
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…
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…