# Publications Search Within Results Search Within Results search ## 19 results Show filters filter\_alt Sort by Year of PublicationAlphabetical A-Z sort ## 19 results Download 19 citations download- [BibTeX](/node/851426/export?format=bibtex) - [EndNote X3 XML](/node/851426/export?format=endnote8) - [EndNote 7 XML](/node/851426/export?format=endnote7) - [Endnote tagged](/node/851426/export?format=tagged) - [Marc](/node/851426/export?format=marc) - [PubMedId](/node/851426/export?format=pubmed_id) - [RIS](/node/851426/export?format=ris) ### Working Paper Binxu Wang and John Vastola. “[Diffusion Models Generate Images Like Painters: An Analytical Theory of Outline First, Details Later](/publications/diffusion-models-generate-images-painters-analytical-theory-outline-first)” Binxu Wang and John Vastola. “[Diffusion Models Generate Images Like Painters: An Analytical Theory of Outline First, Details Later](/publications/diffusion-models-generate-images-painters-analytical-theory-outline-first)” - add\_circle do\_not\_disturb\_on Abstract - [ descriptionPublisher's Version](https://arxiv.org/abs/2303.02490) How do diffusion generative models convert pure noise into meaningful images? In a variety of pretrained diffusion models (including conditional latent space models like Stable Diffusion), we observe that the reverse diffusion process that underlies image... - [ descriptionPublisher's Version](https://arxiv.org/abs/2303.02490) ### Submitted Binxu Wang. “[An Analytical Theory of Power Law Spectral Bias in the Learning Dynamics of Diffusion Models](https://arxiv.org/abs/2503.03206)”. ArXiv Preprint ArXiv:2503.03206 Binxu Wang. “[An Analytical Theory of Power Law Spectral Bias in the Learning Dynamics of Diffusion Models](https://arxiv.org/abs/2503.03206)”. ArXiv Preprint ArXiv:2503.03206 - add\_circle do\_not\_disturb\_on Abstract - [ descriptionPublisher's Version](https://arxiv.org/abs/2503.03206) We developed an analytical framework for understanding how the learned distribution evolves during diffusion model training. Leveraging the Gaussian equivalence principle, we derived exact solutions for the gradient-flow dynamics of weights in one- or two... - [ descriptionPublisher's Version](https://arxiv.org/abs/2503.03206) Binxu Wang and Carlos Ponce. “[Neural Dynamics of Object Manifold Alignment in the Ventral Stream](https://www.biorxiv.org/content/10.1101/2024.06.20.596072v1)”. BioRxiv, Pp. 2024–06 Binxu Wang and Carlos Ponce. “[Neural Dynamics of Object Manifold Alignment in the Ventral Stream](https://www.biorxiv.org/content/10.1101/2024.06.20.596072v1)”. BioRxiv, Pp. 2024–06 - add\_circle do\_not\_disturb\_on Abstract - [ descriptionPublisher's Version](https://www.biorxiv.org/content/10.1101/2024.06.20.596072v1) Visual neurons respond across a vast landscape of images, comprising objects, textures, and places. Natural images can be parameterized using deep generative networks, raising the question of whether latent factors learned by some networks control images... - [ descriptionPublisher's Version](https://www.biorxiv.org/content/10.1101/2024.06.20.596072v1) ### 2024 Binxu Wang, Jiaqi Shang, and Haim Sompolinsky. 2024. “[Do Diffusion Models Generalize on Abstract Rules for Reasoning?](/publications/do-diffusion-models-generalize-abstract-rules-reasoning)”. In 2024 Conference on Cognitive Computational Neuroscience Binxu Wang, Jiaqi Shang, and Haim Sompolinsky. 2024. “[Do Diffusion Models Generalize on Abstract Rules for Reasoning?](/publications/do-diffusion-models-generalize-abstract-rules-reasoning)”. In 2024 Conference on Cognitive Computational Neuroscience Binxu Wang, Jiaqi Shang, and Haim Sompolinsky. 2024. “[Diverse Capability and Scaling of Diffusion and Auto-Regressive Models When Learning Abstract Rules](https://arxiv.org/abs/2411.07873)”. In The First Workshop on System-2 Reasoning at Scale, NeurIPS’24 Binxu Wang, Jiaqi Shang, and Haim Sompolinsky. 2024. “[Diverse Capability and Scaling of Diffusion and Auto-Regressive Models When Learning Abstract Rules](https://arxiv.org/abs/2411.07873)”. In The First Workshop on System-2 Reasoning at Scale, NeurIPS’24 - add\_circle do\_not\_disturb\_on Abstract - [ descriptionPublisher's Version](https://arxiv.org/abs/2411.07873) Humans excel at discovering regular structures from limited samples and applying inferred rules to novel settings. We investigate whether modern generative models can similarly learn underlying rules from finite samples and perform reasoning through... - [ descriptionPublisher's Version](https://arxiv.org/abs/2411.07873) Binxu Wang and John Vastola. 2024. “[The Unreasonable Effectiveness of Gaussian Score Approximation for Diffusion Models and Its Applications](https://arxiv.org/abs/2412.09726)”. Transactions on Machine Learning Research Binxu Wang and John Vastola. 2024. “[The Unreasonable Effectiveness of Gaussian Score Approximation for Diffusion Models and Its Applications](https://arxiv.org/abs/2412.09726)”. Transactions on Machine Learning Research - add\_circle do\_not\_disturb\_on Abstract - [ descriptionPublisher's Version](https://openreview.net/forum?id=I0uknSHM2j) By learning the gradient of smoothed data distributions, diffusion models can iteratively generate samples from complex distributions. The learned score function enables their generalization capabilities, but how the learned score relates to the score of... - [ descriptionPublisher's Version](https://openreview.net/forum?id=I0uknSHM2j) ### 2023 Binxu Wang and John Vastola. 2023. “[The Hidden Linear Structure in Score-Based Models and Its Application](https://arxiv.org/abs/2311.10892)”. In NeurIPS 2023 Workshop on Diffusion Models Binxu Wang and John Vastola. 2023. “[The Hidden Linear Structure in Score-Based Models and Its Application](https://arxiv.org/abs/2311.10892)”. In NeurIPS 2023 Workshop on Diffusion Models - add\_circle do\_not\_disturb\_on Abstract - [ descriptionPublisher's Version](https://arxiv.org/abs/2311.10892) Score-based models have achieved remarkable results in the generative modeling of many domains. By learning the gradient of smoothed data distribution, they can iteratively generate samples from complex distribution e.g. natural images. However, is there... - [ descriptionPublisher's Version](https://arxiv.org/abs/2311.10892) Chandana Kuntala, Carlos Ponce, Deepak Kumar Sharma, and Binxu Wang. 2023. “[Understanding Learning Dynamics of Neural Representations via Feature Visualization at Scale](/publications/understanding-learning-dynamics-neural-representations-feature-visualization)”. In NeurIPS 2023 UniReps Workshop: The First Workshop on Unifying Representations in Neural Models Chandana Kuntala, Carlos Ponce, Deepak Kumar Sharma, and Binxu Wang. 2023. “[Understanding Learning Dynamics of Neural Representations via Feature Visualization at Scale](/publications/understanding-learning-dynamics-neural-representations-feature-visualization)”. In NeurIPS 2023 UniReps Workshop: The First Workshop on Unifying Representations in Neural Models - add\_circle do\_not\_disturb\_on Abstract - [ descriptionPublisher's Version](https://openreview.net/forum?id=j641gZOD7m&referrer=%5Bthe%20profile%20of%20Chandana%20Kuntala%5D(%2Fprofile%3Fid%3D) How does feature learning happen during the training of a neural network? We developed an accelerated pipeline to synthesize maximally activating images ("prototypes") for hidden units in a parallel fashion. Through this, we were able to perform feature... - [ descriptionPublisher's Version](https://openreview.net/forum?id=j641gZOD7m&referrer=%5Bthe%20profile%20of%20Chandana%20Kuntala%5D(%2Fprofile%3Fid%3D) Binxu Wang. 2023. “[Charting the Landscape of Ventral Stream Neural Code on Generative Image Manifolds](/publications/charting-landscape-ventral-stream-neural-code-generative-image-manifolds-0)”. Department of Neuroscience, Washington University in St. Louis Binxu Wang. 2023. “[Charting the Landscape of Ventral Stream Neural Code on Generative Image Manifolds](/publications/charting-landscape-ventral-stream-neural-code-generative-image-manifolds-0)”. Department of Neuroscience, Washington University in St. Louis - add\_circle do\_not\_disturb\_on Abstract - [ descriptionPublisher's Version](https://www.proquest.com/openview/3f176e177b3650062920df21c8e7016c/1?pq-origsite=gscholar&cbl=18750&diss=y) - [ picture\_as\_pdfdissertationdraft\_landsca...](/sites/g/files/omnuum11221/files/dissertationdraft_landscape_geometry_final_final.pdf) The natural world features high-dimensional retinal inputs to the visual system. In contrast, to study vision in the lab, only sparsely sampled image sets are used. Given this immense natural image manifold, what is a principled way to sample and... - [ descriptionPublisher's Version](https://www.proquest.com/openview/3f176e177b3650062920df21c8e7016c/1?pq-origsite=gscholar&cbl=18750&diss=y) - [ picture\_as\_pdfdissertationdraft\_landsca...](/sites/g/files/omnuum11221/files/dissertationdraft_landscape_geometry_final_final.pdf) ### 2022 Binxu Wang and Carlos Ponce. 2022. “[High-Performance Evolutionary Algorithms for Online Neuron Control](https://arxiv.org/abs/2204.06765)”. The Genetic and Evolutionary Computation Conference (GECCO) 2022 Full Paper Binxu Wang and Carlos Ponce. 2022. “[High-Performance Evolutionary Algorithms for Online Neuron Control](https://arxiv.org/abs/2204.06765)”. The Genetic and Evolutionary Computation Conference (GECCO) 2022 Full Paper - add\_circle do\_not\_disturb\_on Abstract - [ picture\_as\_pdfFull Paper](/sites/g/files/omnuum11221/files/binxuw/files/analysis_and_development_of_optimizers_for_online_control_of_visual_neurons_camerareadyarxiv.pdf) Recently, optimization has become an emerging tool for neuroscientists to study neural code. In the visual system, neurons respond to images with graded and noisy responses. Image patterns eliciting highest responses are diagnostic of the coding content... - [ picture\_as\_pdfFull Paper](/sites/g/files/omnuum11221/files/binxuw/files/analysis_and_development_of_optimizers_for_online_control_of_visual_neurons_camerareadyarxiv.pdf) Binxu Wang and Carlos R. Ponce. 2022. “[Tuning Landscapes of the Ventral Stream](/publications/tuning-landscapes-ventral-stream)”. Cell Reports, 41, 6 Binxu Wang and Carlos R. Ponce. 2022. “[Tuning Landscapes of the Ventral Stream](/publications/tuning-landscapes-ventral-stream)”. Cell Reports, 41, 6 - add\_circle do\_not\_disturb\_on Abstract - [ descriptionPublisher's Version](https://www.cell.com/cell-reports/fulltext/S2211-1247(22)01460-7) A goal in visual neuroscience is to explain how neurons respond to natural scenes. However, neurons are generally tested using simpler stimuli, often because they can be transformed smoothly, allowing the measurement of tuning functions (i.e., response... - [ descriptionPublisher's Version](https://www.cell.com/cell-reports/fulltext/S2211-1247(22)01460-7) Binxu Wang and Carlos R. Ponce. 2022. “[On the Level Sets and Invariance of Neural Tuning Landscapes](/publications/level-sets-and-invariance-neural-tuning-landscapes)”. NeurIPS 2022 Workshop on Symmetry and Geometry in Neural Representations Binxu Wang and Carlos R. Ponce. 2022. “[On the Level Sets and Invariance of Neural Tuning Landscapes](/publications/level-sets-and-invariance-neural-tuning-landscapes)”. NeurIPS 2022 Workshop on Symmetry and Geometry in Neural Representations - add\_circle do\_not\_disturb\_on Abstract - [ descriptionPublisher's Version](https://openreview.net/forum?id=6UvnOdlbIbY) Visual representations can be defined as the activations of neuronal populations in response to images. The activation of a neuron as a function over all image space has been described as a "tuning landscape". As a function over a high-dimensional space... - [ descriptionPublisher's Version](https://openreview.net/forum?id=6UvnOdlbIbY) - Previous page chevron\_left - [1](?page=0 "Current page") - [2](?page=1 "Go to page 2") - [ Next page chevron\_right ](?page=1 "Go to next page")