6 papers · 1 filter
OnlineCache: Learning Dynamic Caching Policies with Error Correction for Efficient Diffusion Inference
Zhikang Xie, Xichen Ye, Yifan Wu +5
Diffusion models have revolutionized generative tasks but incur high latency due to iterative denoising. While cache-based strategies accelerate inference by reusing intermediate f…
Distill on a Diet: Efficient Knowledge Distillation via Learnable Data Pruning
Yifan Wu, Yiqi Wang, Xichen Ye +5
Knowledge Distillation (KD) is widely used to obtain compact models for efficient inference in resource-constrained environments. Yet the computational overhead of the distillation…
Investigating Data Pruning for Pretraining Biological Foundation Models at Scale
Yifan Wu, Jiyue Jiang, Xichen Ye +9
Biological foundation models (BioFMs), pretrained on large-scale biological sequences, have recently shown strong potential in providing meaningful representations for diverse down…
Towards Robust Influence Functions with Flat Validation Minima
Xichen Ye, Yifan Wu, Weizhong Zhang +2
The Influence Function (IF) is a widely used technique for assessing the impact of individual training samples on model predictions. However, existing IF methods often fail to prov…
Embedding Empirical Distributions for Computing Optimal Transport Maps
Mingchen Jiang, Peng Xu, Xichen Ye +3
Distributional data have become increasingly prominent in modern signal processing, highlighting the necessity of computing optimal transport (OT) maps across multiple probability…
Optimized Gradient Clipping for Noisy Label Learning
Xichen Ye, Yifan Wu, Weizhong Zhang +3
Previous research has shown that constraining the gradient of loss function with respect to model-predicted probabilities can enhance the model robustness against noisy labels. The…