publications
2024
-
-
-
-
-
GenEFT: Understanding Statics and Dynamics of Model Generalization via Effective TheoryarXiv:2402.05916, 2024
-
Do Diffusion Models Learn Semantically Meaningful and Efficient Representations?arXiv:2402.03305, 2024
2023
-
Seeing is believing: Brain-inspired modular training for mechanistic interpretabilityEntropy, 2023
-
Grokking as Simplification: A Nonlinear Complexity PerspectiveIn UniReps: the First Workshop on Unifying Representations in Neural Models , 2023
-
-
Growing Brains in Recurrent Neural Networks for Multiple Cognitive TasksIn NeurIPS 2023 Workshop on Symmetry and Geometry in Neural Representations , 2023
-
-
-
The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural NetworksIn Thirty-seventh Conference on Neural Information Processing Systems , 2023
-
Restart Sampling for Improving Generative ProcessesIn Thirty-seventh Conference on Neural Information Processing Systems , 2023
-
PFGM++: Unlocking the Potential of Physics-Inspired Generative ModelsIn Proceedings of the 40th International Conference on Machine Learning , 2023
-
-
Omnigrok: Grokking Beyond Algorithmic DataIn The Eleventh International Conference on Learning Representations , 2023
-
-
The Quantization Model of Neural ScalingIn Thirty-seventh Conference on Neural Information Processing Systems , 2023
2022
-
-
Towards Understanding Grokking: An Effective Theory of Representation LearningIn Advances in Neural Information Processing Systems , 2022
-
-
-
2021
-
-
Physics-Augmented Learning: A New Paradigm Beyond Physics-Informed LearningIn NeurIPS 2021 AI for Science Workshop , 2021
-
Schrödinger principal-component analysis: On the duality between principal-component analysis and the Schrödinger equationPhys. Rev. E, 2021
-
-
2020
-
Robustness of principal component analysis of harmonic flow in heavy ion collisionsPhys. Rev. C, 2020
2019
-
-
Principal component analysis of collective flow in relativistic heavy-ion collisionsThe European Physical Journal C, 2019