ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Hidenori Tanaka

Hidenori Tanaka

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 14, 2026, 8:46 PM AMS

15

papers

1,207

total citations

papers (15)

Pruning neural networks without any data by iteratively conserving synaptic flow

NEURIPS 2020arXiv

Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks

Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Task

NEURIPS 2023arXiv

Beyond BatchNorm: Towards a Unified Understanding of Normalization in Deep Learning

NEURIPS 2021arXiv

Competition Dynamics Shape Algorithmic Phases of In-Context Learning

Noether’s Learning Dynamics: Role of Symmetry Breaking in Neural Networks

NEURIPS 2021arXiv

ICLR: In-Context Learning of Representations

A Percolation Model of Emergence: Analyzing Transformers Trained on a Formal Language

Forking Paths in Neural Text Generation

Compositional Capabilities of Autoregressive Transformers: A Study on Synthetic, Interpretable Tasks

Towards an Understanding of Stepwise Inference in Transformers: A Synthetic Graph Navigation Model

CORNN: Convex optimization of recurrent neural networks for rapid inference of neural dynamics

NEURIPS 2023arXiv

In-Context Learning Strategies Emerge Rationally

NEURIPS 2025arXiv

Dynamical phases of short-term memory mechanisms in RNNs

Swing-by Dynamics in Concept Learning and Compositional Generalization