167 citations · 189 across the 13 of their papers we have counts for
8 papers · 1 filter
HLA-WM: Hybrid Linear Attention for Long-Horizon Video World Models
Zhuokun Chen, Feng Chen, Xi Lin +4
Long-horizon video world models require persistent memory to preserve scene consistency over extended rollouts. Softmax attention retains the full generation history through a grow…
FlashBlock: Attention Caching for Efficient Long-Context Block Diffusion
Zhuokun Chen, Jianfei Cai, Bohan Zhuang
Generating long-form content, such as minute-long videos and extended texts, is increasingly important for modern generative models. Block diffusion improves inference efficiency v…
An Empirical Study on How Video-LLMs Answer Video Questions
Chenhui Gou, Ziyu Ma, Zicheng Duan +6
Taking advantage of large-scale data and pretrained language models, Video Large Language Models (Video-LLMs) have shown strong capabilities in answering video questions. However,…
MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views
Yuedong Chen, Chuanxia Zheng, Haofei Xu +4
We introduce MVSplat360, a feed-forward approach for 360° novel view synthesis (NVS) of diverse real-world scenes, using only sparse observations. This setting is inherently ill-po…
McCaD: Multi-Contrast MRI Conditioned, Adaptive Adversarial Diffusion Model for High-Fidelity MRI Synthesis
Sanuwani Dayarathna, Kh Tohidul Islam, Bohan Zhuang +4
Magnetic Resonance Imaging (MRI) is instrumental in clinical diagnosis, offering diverse contrasts that provide comprehensive diagnostic information. However, acquiring multiple MR…
SAM-Med3D-MoE: Towards a Non-Forgetting Segment Anything Model via Mixture of Experts for 3D Medical Image Segmentation
Guoan Wang, Jin Ye, Junlong Cheng +5
Volumetric medical image segmentation is pivotal in enhancing disease diagnosis, treatment planning, and advancing medical research. While existing volumetric foundation models for…
MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images
Yuedong Chen, Haofei Xu, Chuanxia Zheng +5
We introduce MVSplat, an efficient model that, given sparse multi-view images as input, predicts clean feed-forward 3D Gaussians. To accurately localize the Gaussian centers, we bu…
T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching
Zizheng Pan, Bohan Zhuang, De-An Huang +5
Sampling from diffusion probabilistic models (DPMs) is often expensive for high-quality image generation and typically requires many steps with a large model. In this paper, we int…