← Search

Minxuan Duan

2 accepted papers

2026

Efficient Estimation of Kernel Surrogate Models for Task Attribution

ICLR 2026poster

Modern AI agents such as large language models are trained on diverse tasks---translation, code generation, mathematical reasoning, and text prediction---simultaneously. A key question is to quantify how each individual training task influences performance on a target task, a problem we refer to as…

Cited by 0SourcecodeScholar
2026

Scalable Multi-Objective and Meta Reinforcement Learning via Gradient Estimation

AAAI 2026technical

We study the problem of efficiently estimating policies that simultaneously optimize multiple objectives in reinforcement learning (RL). Given n objectives (or tasks), we seek the optimal partition of these objectives into k groups, which is much smaller than n, where each group comprises related ob

Cited by 0SourcePDFScholar