Publications

Towards Efficient Optimizer Design for LLM via Structured Fisher Approximation with a Low-Rank Extension
Wenbo Gong * , M Scetbon * , C Ma * , E Meeds
* Equal contribution (authors marked).
arXiv:2502.07752 • 2025
optimization learning dynamics LLM
PDF Cite Source Document
SWAN: SGD with Normalization and Whitening Enables Stateless LLM Training
C Ma * , Wenbo Gong * , M Scetbon * , E Meeds
* Equal contribution (authors marked).
ICML 2025 • 2025
optimization LLM learning dynamics
PDF Cite Source Document
Gradient Multi-Normalization for Stateless and Scalable LLM Training
M Scetbon * , C Ma * , Wenbo Gong * , E Meeds
* Equal contribution (authors marked).
NeurIPS 2025 • 2025
optimization LLM learning dynamics
PDF Cite Source Document
The essential role of causality in foundation world models for embodied AI
T Gupta , Wenbo Gong , C Ma , N Pawlowski , A Hilmkil , M Scetbon , M Rigter , Et Al.
arXiv:2402.06665 • 2024
causality
PDF Cite Source Document
ProxyTune: Hyperparameter tuning through iteratively refined proxies
A Hilmkil * , Wenbo Gong * , N Pawlowski , C Zhang
* Equal contribution (authors marked).
ICML 2024 Workshop on Structured Probabilistic Inference and Generative Modeling • 2024
PDF Cite Source Document
Neural structure learning with stochastic differential equations
B Wang * , J Jennings , Wenbo Gong *
* Equal contribution (authors marked).
ICLR 2024 • 2024
approximate inference causality time series bayesian inference
PDF Cite Source Document
Deep end-to-end causal inference
T Geffner , J Antoran , A Foster , Wenbo Gong , C Ma , E Kiciman , A Sharma , Et Al.
Transactions on Machine Learning Research • 2024
causality approximate inference bayesian inference
PDF Cite Code Source Document
Understanding causality with large language models: Feasibility and opportunities
C Zhang , S Bauer , P Bennett , J Gao , Wenbo Gong , A Hilmkil , J Jennings , C Ma , Et Al.
arXiv:2304.05524 • 2023
causality
PDF Cite Source Document
Rhino: Deep causal temporal relationship learning with history-dependent noise
Wenbo Gong , J Jennings , C Zhang , N Pawlowski
ICLR 2023 (Spotlight) • 2023
Spotlight causality time series approximate inference bayesian inference
PDF Cite Code Source Document
CausalEdu: A real-world education dataset for temporal causal discovery and inference
Wenbo Gong , D Smith , Z Wang , C Barton , S Woodhead , N Pawlowski , Et Al.
CLeaR • 2023
causality
PDF Cite Code Source Document
Page 1 of 2