activity
20212026
most citedLearning Prediction Intervals for Regression: Generalization and Calibration

8 citations · 12 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CL2026

Utility-Oriented Visual Evidence Selection for Multimodal Retrieval-Augmented Generation

Weiqing Luo, Zongye Hu, Xiao Wang +3

Visual evidence selection is a critical component of multimodal retrieval-augmented generation (RAG), yet existing methods typically rely on semantic relevance or surface-level sim…

cs.CV2026

Learning to Align Generative Appearance Priors for Fine-grained Image Retrieval

Shijie Wang, Yadan Luo, Zijian Wang +2

Fine-grained image retrieval (FGIR) typically relies on supervision from seen categories to learn discriminative embeddings for retrieving unseen categories. However, such supervis…

stat.ML2024★ 1 cited

Bayesian Bandit Algorithms with Approximate Inference in Stochastic Linear Bandits

Ziyi Huang, Henry Lam, Haofeng Zhang

Bayesian bandit algorithms with approximate Bayesian inference have been widely used in real-world applications. Despite the superior practical performance, their theoretical justi…

stat.ML2023★ 2 cited

Efficient Uncertainty Quantification and Reduction for Over-Parameterized Neural Networks

Ziyi Huang, Henry Lam, Haofeng Zhang

Uncertainty quantification (UQ) is important for reliability assessment and enhancement of machine learning models. In deep learning, uncertainties arise not only from data, but al…

stat.ML2021★ 8 cited

Learning Prediction Intervals for Regression: Generalization and Calibration

Haoxian Chen, Ziyi Huang, Henry Lam +2

We study the generation of prediction intervals in regression for uncertainty quantification. This task can be formalized as an empirical constrained optimization problem that mini…

cs.LG2021★ 1 cited

Co-Seg: An Image Segmentation Framework Against Label Corruption

Ziyi Huang, Haofeng Zhang, Andrew Laine +3

Supervised deep learning performance is heavily tied to the availability of high-quality labels for training. Neural networks can gradually overfit corrupted labels if directly tra…