Hidenori Tanaka
21 papers · 2019–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
π Conference Polyglot (3) π Academic Marathon (6) π§ Keyword Pioneer π Interdisciplinary Bridge π Cross-Pollinator (14)
π
Renaissance Researcher
(5)
πΊοΈ
Taxonomy Completionist
(28)
π
Interdisciplinary Bridge
π
Triple Crown
π€
Dynamic Duo
(12)
β
The Questioner
β‘
Prolific Year
(5)
π
Trend Setter
π
Century Club
(21)
Conferences
ICLR (9)
NIPS (7)
ICML (5)
Top co-authors
Research topics
Keywords
generative model
(2)
emergent capability
(2)
neural network
(2)
learning dynamics
(2)
deep neural network
(2)
convex optimization
(1)
neural dynamics
(1)
neural network pruning
(1)
neural network interpretability
(1)
conditional generation
(1)
loss landscape
(1)
compositional generalization
(1)
sensory processing
(1)
gradient descent
(1)
lottery ticket hypothesis
(1)
recurrent neural network
(1)
diffusion model
(1)
batch normalization
(1)
concept learning
(1)
computational neuroscience
(1)
Papers
Competition Dynamics Shape Algorithmic Phases of In-Context Learning
ICLR 2025
ICLR: In-Context Learning of Representations
ICLR 2025
Dynamical phases of short-term memory mechanisms in RNNs
ICML 2025
A Percolation Model of Emergence: Analyzing Transformers Trained on a Formal Language
ICLR 2025
Swing-by Dynamics in Concept Learning and Compositional Generalization
ICLR 2025
Forking Paths in Neural Text Generation
ICLR 2025
Representation Shattering in Transformers: A Synthetic Study with Knowledge Editing
ICML 2025
In-Context Learning Dynamics with Random Binary Sequences
ICLR 2024
Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Space
NIPS 2024
Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks
ICLR 2024
Towards an Understanding of Stepwise Inference in Transformers: A Synthetic Graph Navigation Model
ICML 2024
Compositional Capabilities of Autoregressive Transformers: A Study on Synthetic, Interpretable Tasks
ICML 2024
What shapes the loss landscape of self supervised learning?
ICLR 2023
CORNN: Convex optimization of recurrent neural networks for rapid inference of neural dynamics
NIPS 2023
Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Task
NIPS 2023
Mechanistic Mode Connectivity
ICML 2023
Neural Mechanics: Symmetry and Broken Conservation Laws in Deep Learning Dynamics
ICLR 2021
Beyond BatchNorm: Towards a Unified Understanding of Normalization in Deep Learning
NIPS 2021
Noetherβs Learning Dynamics: Role of Symmetry Breaking in Neural Networks
NIPS 2021
Pruning neural networks without any data by iteratively conserving synaptic flow
NIPS 2020
From deep learning to mechanistic understanding in neuroscience: the structure of retinal prediction
NIPS 2019