ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Hadi Daneshmand

Hadi Daneshmand

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 15, 2026, 9:14 AM AMS

8

papers

333

total citations

papers (8)

Transformers learn to implement preconditioned gradient descent for in-context learning

NEURIPS 2023arXiv

Batch Normalization Orthogonalizes Representations in Deep Random Networks

NEURIPS 2021arXiv

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

On the impact of activation and normalization in obtaining isometric embeddings at initialization

NEURIPS 2023arXiv

Towards Training Without Depth Limits: Batch Normalization Without Gradient Explosion

Batch normalization provably avoids ranks collapse for randomly initialised deep networks

NEURIPS 2020arXiv

Linear Transformers Implicitly Discover Unified Numerical Algorithms

NEURIPS 2025arXiv

Rethinking the Variational Interpretation of Accelerated Optimization Methods