9 papers
Timestep-Aware Block Masking for Efficient Diffusion Model Inference
Haodong He, Yuan Gao, Weizhong Zhang +1
Diffusion Probabilistic Models (DPMs) have achieved great success in image generation but suffer from high inference latency due to their iterative denoising nature. Motivated by t…
Towards Human-Level 3D Relative Pose Estimation: Generalizable, Training-Free, with Single Reference
Yuan Gao, Yajing Luo, Junhong Wang +2
Humans can easily deduce the relative pose of a previously unseen object, without labeling or training, given only a single query-reference image pair. This is arguably achieved by…
Fuse Before Transfer: Knowledge Fusion for Heterogeneous Distillation
Guopeng Li, Qiang Wang, Ke Yan +3
Most knowledge distillation (KD) methodologies predominantly focus on teacher-student pairs with similar architectures, such as both being convolutional neural networks (CNNs). How…
Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient
Yuan Gao, Zujing Liu, Weizhong Zhang +2
Recent Large-Language Models (LLMs) pruning methods typically operate at the post-training phase without the expensive weight finetuning, however, their pruning criteria often rely…
Intensity Field Decomposition for Tissue-Guided Neural Tomography
Meng-Xun Li, Jin-Gang Yu, Yuan Gao +2
Cone-beam computed tomography (CBCT) typically requires hundreds of X-ray projections, which raises concerns about radiation exposure. While sparse-view reconstruction reduces the…
DMTG: One-Shot Differentiable Multi-Task Grouping
Yuan Gao, Shuguo Jiang, Moran Li +2
We aim to address Multi-Task Learning (MTL) with a large number of tasks by Multi-Task Grouping (MTG). Given N tasks, we propose to simultaneously identify the best task groups fro…