Thomas Jiralerspong
5 papers · 2023–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π Cross-Pollinator (14) π Conference Polyglot (5) π Renaissance Researcher (6) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (12)
π§
Keyword Pioneer
π£
Hot Topic Early Bird
π
Grand Slam
Conferences
AAAI (1)
ACL (1)
ICLR (1)
ICML (1)
NIPS (1)
Top co-authors
Keywords
representation learning
(1)
contrastive learning
(1)
reinforcement learning
(1)
offline reinforcement learning
(1)
prototype learning
(1)
geometric analysis
(1)
semantic analysis
(1)
intrinsic dimension
(1)
language model
(1)
intrinsic reward
(1)
credit assignment
(1)
fitted q evaluation
(1)
clinical decision support
(1)
state generalization
(1)
mechanical ventilation
(1)
conservative q-learning
(1)
patient vital
(1)
Papers
Geometric Signatures of Compositionality Across a Language Modelβs Lifetime
ACL 2025
Expressivity of Neural Networks with Random Weights and Learned Biases
ICLR 2025
Towards a Formal Theory of Representational Compositionality
ICML 2025
Contrastive Retrospection: honing in on critical steps for rapid learning and generalization in RL
NIPS 2023
Towards Safe Mechanical Ventilation Treatment Using Deep Offline Reinforcement Learning
AAAI 2023