Paper-Conference
13 items tagged
(2026).
Circuit Mechanisms for Spatial Relation Generation in Diffusion Transformers.
Conference on Computer Vision and Pattern Recognition (CVPR) 2026 (highlight, top 3%).
(2026).
Where the Score Lives: A Wavelet View of Diffusion.
International Conference on Artificial Intelligence and Statistics (AISTATS) 2026.
(2025).
When Rule Learning Breaks: Diffusion Fails to Learn Parity of Many Bits.
Workshop on Structured Probabilistic Inference & Generative Modeling, NeurIPS 2025 (oral).
(2025).
Into the Rabbit Hull: From Task-Relevant Concepts in DINO to Minkowski Geometry.
International Conference on Learning Representations (ICLR) 2025.
(2024).
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.
(2024).
Do diffusion models generalize on abstract rules for reasoning?.
2024 Conference on Cognitive Computational Neuroscience.
(2023).
Understanding Learning Dynamics of Neural Representations via Feature Visualization at Scale.
NeurIPS 2023 UniReps Workshop: the First Workshop on Unifying Representations in Neural Models.
(2023).
The hidden linear structure in score-based models and its application.
NeurIPS 2023 Workshop on Diffusion Models (arXiv:2311.10892).
(2022).
On the Level Sets and Invariance of Neural Tuning Landscapes.
NeurIPS 2022 Workshop on Symmetry and Geometry in Neural Representations.
(2022).
High-performance Evolutionary Algorithms for Online Neuron Control.
GECCO ‘22: Proceedings of the Genetic and Evolutionary Computation Conference (Best paper nomination).
(2022).
Factorized convolution models for interpreting neuron-guided images synthesis.
2022 Conference on Cognitive Computational Neuroscience.
(2021).
On the use of Cortical Magnification and Saccades as Biological Proxies for Data Augmentation.
NeurIPS 2021 SVRHM Workshop.
(2021).
The Geometry of Deep Generative Image Models and its Applications.
International Conference on Learning Representations, 2021.
