Robert P. Dick
9 papers · 2021–2025 · 2 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(13)
🐣
Hot Topic Early Bird
🔥
Unstoppable · Bronze
Top co-authors
Research topics
Keywords
formal language
(2)
network pruning
(2)
variational inference
(1)
feature space
(1)
transformer
(1)
neural network optimization
(1)
compositional generalization
(1)
mechanistic interpretability
(1)
compositional structure
(1)
model pruning
(1)
condition number
(1)
phase transition
(1)
disentangled representation
(1)
gradient flow
(1)
learning dynamics
(1)
loss landscape
(1)
in-context learning
(1)
mode connectivity
(1)
autoregressive transformer
(1)
representation learning
(1)
Papers
A Percolation Model of Emergence: Analyzing Transformers Trained on a Formal Language
ICLR 2025
Compositional Capabilities of Autoregressive Transformers: A Study on Synthetic, Interpretable Tasks
ICML 2024
In-Context Learning Dynamics with Random Binary Sequences
ICLR 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
Mechanistic Mode Connectivity
ICML 2023
Over-parameterized Model Optimization with Polyak-{\L}ojasiewicz Condition
ICLR 2023
Recursive Disentanglement Network
ICLR 2022
A Gradient Flow Framework For Analyzing Network Pruning
ICLR 2021