影响力指数

61.68/100

前 4.4%

全站排名 #2,829

发表论文6 篇

平均评分5.8

年均产出2.0 篇/年

Tianhao Wang

Assistant Professor@University of California, San Diego·美国·OpenReview

研究方向

deep learning · reinforcement learning · optimization

A Tale of Two Geometries: Adaptive Optimizers and Non-Euclidean Descent

ICLR 2026Poster

Taming Polysemanticity in LLMs: Theory-Grounded Feature Recovery via Sparse Autoencoders

ICLR 2026Poster

Can Neural Networks Achieve Optimal Computational-statistical Tradeoff? An Analysis on Single-Index Model

Structured Preconditioners in Adaptive Optimization: A Unified Analysis

ICML 2025Poster

合作者 (13)