6 papers
AnyStep-WAM: Budget-Aligned Distillation and Adaptive Inference for World Action Models
Rui Wang, Xiangyu Wang, Donglin Yang +4
World-action models (WAMs) couple predictive visual modeling with action generation, typically relying on iterative denoising with a fixed denoising steps. However, manipulation ta…
Stable Velocity: A Variance Perspective on Flow Matching
Donglin Yang, Yongxing Zhang, Xin Yu +5
While flow matching is elegant, its reliance on single-sample conditional velocities leads to high-variance training targets that destabilize optimization and slow convergence. By…
Advancing Generalizable Tumor Segmentation with Anomaly-Aware Open-Vocabulary Attention Maps and Frozen Foundation Diffusion Models
Yankai Jiang, Peng Zhang, Donglin Yang +3
We explore Generalizable Tumor Segmentation, aiming to train a single model for zero-shot tumor segmentation across diverse anatomical regions. Existing methods face limitations re…
QDM: Quadtree-Based Region-Adaptive Sparse Diffusion Models for Efficient Image Super-Resolution
Donglin Yang, Paul Vicol, Xiaojuan Qi +2
Deep learning-based super-resolution (SR) methods often perform pixel-wise computations uniformly across entire images, even in homogeneous regions where high-resolution refinement…
SymmetricDiffusers: Learning Discrete Diffusion on Finite Symmetric Groups
Yongxing Zhang, Donglin Yang, Renjie Liao
Finite symmetric groups are essential in fields such as combinatorics, physics, and chemistry. However, learning a probability distribution over poses significant chall…
On Sparse Modern Hopfield Model
Jerry Yao-Chieh Hu, Donglin Yang, Dennis Wu +3
We introduce the sparse modern Hopfield model as a sparse extension of the modern Hopfield model. Like its dense counterpart, the sparse modern Hopfield model equips a memory-retri…