Hadi Daneshmand

Assistant Professor@University of Virginia, Charlottesville·美国·OpenReview

研究方向

In-context learning · Foundations of generative AI · Optimization for language models · Stochastic Integration · Non-asymptotic statistics · Markov Chains · Deep Learning Theory · Optimization for ML · Non-convex Optimization

3.5

How Does Layer Normalization Improve Deep $\boldsymbol{Q}$-learning?

ICLR 2026Rejected

二作

7.6

Linear Transformers Implicitly Discover Unified Numerical Algorithms

NeurIPS 2025Poster

三作

6.7

Transformers Can Learn Temporal Difference Methods for In-Context Reinforcement Learning

ICLR 2025Poster

三作

5.3

Provable optimal transport with transformers: The essence of depth and prompt engineering

合作者 (13)