collaborators

6 papers

cs.CV2026

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…

cs.CV2025

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…

cs.CV2025

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…

cs.LG2025

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…

cs.CV2025

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…

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…