activity
20242026
collaborators

7 papers

cs.LG2026

Active Learning with Foundation Model Priors: Efficient Learning under Class Imbalance

Jiancheng Zhang, Meiqing Li, Qi Zhang +1

Real-world datasets across image and text domains are often characterized by skewed class distributions and noisy annotations, which jointly degrade model performance, particularly…

cs.LG2026

Online Finetuning Decision Transformers with Pure RL Gradients

Junkai Luo, Yinglun Zhu

Decision Transformers (DTs) have emerged as a powerful framework for sequential decision making by formulating offline reinforcement learning (RL) as a sequence modeling problem. H…

cs.LG2025

Interactive Machine Learning: From Theory to Scale

Yinglun Zhu

Machine learning has achieved remarkable success across a wide range of applications, yet many of its most effective methods rely on access to large amounts of labeled data or exte…

cs.AI2025

Strategic Scaling of Test-Time Compute: A Bandit Learning Approach

Bowen Zuo, Yinglun Zhu

Scaling test-time compute has emerged as an effective strategy for improving the performance of large language models. However, existing methods typically allocate compute uniforml…

cs.LG2024

Efficient Sparse PCA via Block-Diagonalization

Alberto Del Pia, Dekun Zhou, Yinglun Zhu

Sparse Principal Component Analysis (Sparse PCA) is a pivotal tool in data analysis and dimensionality reduction. However, Sparse PCA is a challenging problem in both theory and pr…

cs.LG2024

Efficient Sequential Decision Making with Large Language Models

Dingyang Chen, Qi Zhang, Yinglun Zhu

This paper focuses on extending the success of large language models (LLMs) to sequential decision making. Existing efforts either (i) re-train or finetune LLMs for decision making…