8 papers
ViTok-v2: Scaling Native Resolution Auto-Encoders to 5 Billion Parameters
Philippe Hansen-Estruch, Jiahui Chen, Vivek Ramanujan +9
Vision Transformer (ViT) autoencoders have emerged as compelling tokenizers for images, offering improved reconstruction over convolutional tokenizers. However, existing ViT tokeni…
Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning
Lei Zhang, Junjiao Tian, Zhipeng Fan +9
Humans paint images incrementally: they plan a global layout, sketch a coarse draft, inspect, and refine details, and most importantly, each step is grounded in the evolving visual…
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…
Improving Chain-of-Thought Efficiency for Autoregressive Image Generation
Zeqi Gu, Markos Georgopoulos, Xiaoliang Dai +10
Autoregressive multimodal large language models have recently gained popularity for image generation, driven by advances in foundation models. To enhance alignment and detail, newe…
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…