Dan Busbridge
11 papers · 2022–2025 · 4 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 · Bronze
🗺️
Taxonomy Completionist
(18)
💎
Century Club · Bronze
Venues
Top co-authors
Research topics
Machine Learning
(10)
Deep Learning
(7)
Learning Types · Machine Learning
(6)
Artificial Intelligence
(4)
Core Methods
(4)
Application Areas
(3)
Architectures
(3)
Core AI
(3)
Learning Types · Deep Learning
(3)
Natural Language Processing
(2)
Optimization & Theory
(2)
Resources & Methods
(2)
Techniques
(2)
Learning Paradigms
(1)
Models
(1)
Keywords
self-supervised learning
(6)
representation learning
(3)
contrastive learning
(3)
scaling law
(3)
multi-view learning
(2)
multi-view self-supervised learning
(2)
sparsity
(1)
optimization
(1)
attention mechanism
(1)
theoretical analysis
(1)
neural network optimization
(1)
mutual information
(1)
entropy minimization
(1)
image reconstruction
(1)
forgetting
(1)
distribution shift
(1)
information maximization
(1)
learning rate
(1)
test-time adaptation
(1)
transfer learning
(1)
Papers
Distillation Scaling Laws
ICML 2025
Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Models
ICML 2025
Scaling Laws for Forgetting during Finetuning with Pretraining Data Injection
ICML 2025
Theory, Analysis, and Best Practices for Sigmoid Self-Attention
ICLR 2025
Poly-View Contrastive Learning
ICLR 2024
REALM: Robust Entropy Adaptive Loss Minimization for Improved Single-Sample Test-Time Adaptation
WACV 2024
DUET: 2D Structured and Approximately Equivariant Representations
ICML 2023
How to Scale Your EMA
NeurIPS 2023
Stabilizing Transformer Training by Preventing Attention Entropy Collapse
ICML 2023
The Role of Entropy and Reconstruction in Multi-View Self-Supervised Learning
ICML 2023
Position Prediction as an Effective Pretraining Strategy
ICML 2022