Into the Rabbit Hull: From Task-Relevant Concepts in DINO to Minkowski Geometry
International Conference on Learning Representations (ICLR) 2026
Thomas Fel, Binxu Wang, Michael A. Lepori, Matthew Kowal, Andrew Lee, Randall Balestriero, Stella Joseph, Ekdeep S. Lubana, Talia Konkle, Demba E. Ba, Martin Wattenberg
Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models
ICML 2025 (arXiv:2502.12892)
Thomas Fel, Ekdeep Singh Lubana, Jacob S Prince, Matthew Kowal, Victor Boutin, Isabel Papadimitriou, Binxu Wang, Martin Wattenberg, Demba Ba, Talia Konkle
The Unreasonable Effectiveness of Gaussian Score Approximation for Diffusion Models and its Applications
Transactions on Machine Learning Research (arXiv:2412.09726)
Binxu Wang, John J Vastola
Diverse capability and scaling of diffusion and auto-regressive models when learning abstract rules
The First Workshop on System-2 Reasoning at Scale, NeurIPS'24
Binxu Wang, Jiaqi Shang, Haim Sompolinsky
Do diffusion models generalize on abstract rules for reasoning?
2024 Conference on Cognitive Computational Neuroscience
Binxu Wang, Jiaqi Shang, Haim Sompolinsky
Understanding Learning Dynamics of Neural Representations via Feature Visualization at Scale
NeurIPS 2023 UniReps Workshop: the First Workshop on Unifying Representations in Neural Models
Chandana Kuntala, Carlos R Ponce, Deepak Kumar Sharma, Binxu Wang
The hidden linear structure in score-based models and its application
NeurIPS 2023 Workshop on Diffusion Models (arXiv:2311.10892)
Binxu Wang, John J Vastola
Diffusion models generate images like painters: an analytical theory of outline first, details later
arXiv preprint arXiv:2303.02490
Binxu Wang, John J Vastola