Thomas Jiralerspong

According to our database, Thomas Jiralerspong authored at least 16 papers between 2023 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

Noticing the Watcher: LLM Agents Can Infer CoT Monitoring from Blocking Feedback.

Thomas Jiralerspong, Flemming Kondrup, Yoshua Bengio

CoRR, March, 2026

Delta-Crosscoder: Robust Crosscoder Model Diffing in Narrow Fine-Tuning Regimes.

Aly M. Kassem, Thomas Jiralerspong, Negar Rostamzadeh, Golnoosh Farnadi

CoRR, March, 2026

Cross-Architecture Model Diffing with Crosscoders: Unsupervised Discovery of Differences Between LLMs.

Thomas Jiralerspong, Trenton Bricken

CoRR, February, 2026

2025

Learning What Matters: Steering Diffusion via Spectrally Anisotropic Forward Noise.

Luca Scimeca, Thomas Jiralerspong, Berton Earnshaw, Jason S. Hartford, Yoshua Bengio

CoRR, October, 2025

Shaping Inductive Bias in Diffusion Models through Frequency-Based Noise Control.

Thomas Jiralerspong, Berton Earnshaw, Jason S. Hartford, Yoshua Bengio, Luca Scimeca

CoRR, February, 2025

Towards a Formal Theory of Representational Compositionality.

Eric Elmoznino, Thomas Jiralerspong, Yoshua Bengio, Guillaume Lajoie

Proceedings of the Forty-second International Conference on Machine Learning, 2025

Expressivity of Neural Networks with Random Weights and Learned Biases.

Ezekiel Williams, Alexandre Payeur, Avery Hee-Woon Ryoo, Thomas Jiralerspong, Matthew G. Perich, Luca Mazzucato, Guillaume Lajoie

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Geometric Signatures of Compositionality Across a Language Model's Lifetime.

Jin Hwa Lee, Thomas Jiralerspong, Lei Yu, Yoshua Bengio, Emily Cheng

Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

2024

General Causal Imputation via Synthetic Interventions.

Marco Jiralerspong, Thomas Jiralerspong, Vedant Shah, Dhanya Sridhar, Gauthier Gidel

CoRR, 2024

A Complexity-Based Theory of Compositionality.

Eric Elmoznino, Thomas Jiralerspong, Yoshua Bengio, Guillaume Lajoie

CoRR, 2024

Efficient Causal Graph Discovery Using Large Language Models.

Thomas Jiralerspong, Xiaoyin Chen, Yash More, Vedant Shah, Yoshua Bengio

CoRR, 2024

2023

Network Analysis of the iNaturalist Citizen Science Community.

Yu Lu Liu, Thomas Jiralerspong

CoRR, 2023

Forecaster: Towards Temporally Abstract Tree-Search Planning from Pixels.

Thomas Jiralerspong, Flemming Kondrup, Doina Precup, Khimya Khetarpal

CoRR, 2023

A Comparison of Classical and Deep Reinforcement Learning Methods for HVAC Control.

Marshall Wang, John Willes, Thomas Jiralerspong, Matin Moezzi

CoRR, 2023

Contrastive Retrospection: honing in on critical steps for rapid learning and generalization in RL.

Chen Sun, Wannan Yang, Thomas Jiralerspong, Dane Malenfant, Benjamin Alsbury-Nealy, Yoshua Bengio, Blake A. Richards

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Towards Safe Mechanical Ventilation Treatment Using Deep Offline Reinforcement Learning.

Flemming Kondrup, Thomas Jiralerspong, Elaine Lau, Nathan de Lara, Jacob Shkrob, My Duc Tran, Doina Precup, Sumana Basu

Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023