Thomas Jiralerspong
5 papers · 2023–2025 · 5 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 ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (14) 🐣 Hot Topic Early Bird 🏆 Grand Slam
🌈
Renaissance Researcher
(5)
Venues
Top co-authors
Research topics
Machine Learning
(4)
Deep Learning
(2)
Reinforcement Learning
(2)
Learning Types · Deep Learning
(2)
Methods
(2)
Artificial Intelligence
(1)
Interdisciplinary
(1)
Mathematics & Optimization
(1)
Natural Language Processing
(1)
Application Areas
(1)
Cognitive Science
(1)
Core AI
(1)
Core Methods
(1)
Learning Types · Machine Learning
(1)
Mathematics
(1)
Keywords
representation learning
(1)
contrastive learning
(1)
reinforcement learning
(1)
offline reinforcement learning
(1)
compositionality
(1)
prototype learning
(1)
geometric analysis
(1)
semantic analysis
(1)
universal approximation
(1)
neural network optimization
(1)
intrinsic dimension
(1)
dynamical system
(1)
recurrent neural network
(1)
language model
(1)
intrinsic reward
(1)
credit assignment
(1)
algorithmic information theory
(1)
feedforward neural network
(1)
clinical decision support
(1)
fitted q-evaluation
(1)
Papers
Expressivity of Neural Networks with Random Weights and Learned Biases
ICLR 2025
Geometric Signatures of Compositionality Across a Language Model’s Lifetime
ACL 2025
Towards a Formal Theory of Representational Compositionality
ICML 2025
Contrastive Retrospection: honing in on critical steps for rapid learning and generalization in RL
NeurIPS 2023
Towards Safe Mechanical Ventilation Treatment Using Deep Offline Reinforcement Learning
AAAI 2023