12 papers · 1 filter
Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility
Yiheng Li, Feng Liang, Dan Kondratyuk +3
The substantial training cost of diffusion models hinders their deployment. Immiscible Diffusion recently showed that reducing diffusion trajectory mixing in the noise space via li…
Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation
Shuo Yang, Haocheng Xi, Yilong Zhao +10
Diffusion Transformers (DiTs) are essential for video generation but suffer from significant latency due to the quadratic complexity of attention. By computing only critical tokens…
Video Compression Meets Video Generation: Latent Inter-Frame Pruning with Attention Recovery
Dennis Menn, Yuedong Yang, Bokun Wang +6
Current video generation models suffer from high computational latency, making real-time applications prohibitively costly. In this paper, we address this limitation by exploiting…
Rethinking Image-to-3D Generation with Sparse Queries: Efficiency, Capacity, and Input-View Bias
Zhiyuan Xu, Jiuming Liu, Yuxin Chen +3
We present SparseGen, a novel framework for efficient image-to-3D generation, which exhibits low input-view bias while being significantly faster. Unlike traditional approaches tha…
StreamDiffusionV2: A Streaming System for Dynamic and Interactive Video Generation
Tianrui Feng, Zhi Li, Shuo Yang +11
Generative models are reshaping the live-streaming industry by redefining how content is created, styled, and delivered. Previous image-based streaming diffusion models have powere…
Law of Vision Representation in MLLMs
Shijia Yang, Bohan Zhai, Quanzeng You +3
We present the "Law of Vision Representation" in multimodal large language models (MLLMs). It reveals a strong correlation between the combination of cross-modal alignment, corresp…