1 citations · 2 across the 11 of their papers we have counts for
11 papers
From Local Mismatch to Global Impact: Optimizing Cache Reuse Policy for Efficient Diffusion
Xichen Ye, Yifan Wu, Zhikang Xie +3
Diffusion models have achieved dominant performance in visual generation but suffer from substantial inference overhead. While cache-based acceleration has emerged as a promising s…
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…
When Human Preferences Flip: An Instance-Dependent Robust Loss for RLHF
Yifan Xu, Xichen Ye, Yifan Chen +1
Quality of datasets plays an important role in large language model (LLM) alignment. In collecting human feedback, however, preference flipping is ubiquitous and causes corruption…
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…
Revisiting Energy-Based Model for Out-of-Distribution Detection
Yifan Wu, Xichen Ye, Songmin Dai +4
Out-of-distribution (OOD) detection is an essential approach to robustifying deep learning models, enabling them to identify inputs that fall outside of their trained distribution.…
Active Negative Loss: A Robust Framework for Learning with Noisy Labels
Xichen Ye, Yifan Wu, Yiqi Wang +3
Deep supervised learning has achieved remarkable success across a wide range of tasks, yet it remains susceptible to overfitting when confronted with noisy labels. To address this…
DuPL: Dual Student with Trustworthy Progressive Learning for Robust Weakly Supervised Semantic Segmentation
Yuanchen Wu, Xichen Ye, Kequan Yang +2
Recently, One-stage Weakly Supervised Semantic Segmentation (WSSS) with image-level labels has gained increasing interest due to simplification over its cumbersome multi-stage coun…