Generative Model

22 items tagged

Neuronal Tuning Aligns Dynamically with Object- and Texture Manifolds across the Visual Hierarchy

Nature Neuroscience

Binxu Wang, Carlos R. Ponce

PDF Project Video 📝 BLOG Visual Neuroscience NeuroAI Generative Model

When Rule Learning Breaks: Diffusion Fails to Learn Parity of Many Bits

Workshop on Structured Probabilistic Inference & Generative Modeling, NeurIPS 2025 (oral)

🎤 Oral presentation

Binxu Wang, Emma Lucia Byrnes Finn, Bingbin Liu

Diffusion Science of AI Generative Model

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

PDF Cite Diffusion NeuroAI Generative Model Science of AI

Do diffusion models generalize on abstract rules for reasoning?

2024 Conference on Cognitive Computational Neuroscience

Binxu Wang, Jiaqi Shang, Haim Sompolinsky

Cite Diffusion NeuroAI Generative Model Science of AI

Neural Dynamics of Object Manifold Alignment in the Ventral Stream

bioRxiv

Binxu Wang, Carlos R Ponce

PDF Cite Visual Neuroscience Geometry Generative Model Ventral Stream

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

PDF Cite Diffusion Geometry Generative Model Science of AI Theory

Charting the Landscape of Ventral Stream Neural Code on Generative Image Manifolds

Binxu Wang

PDF Cite Video Thesis Visual Neuroscience Generative Model

Diffusion models generate images like painters: an analytical theory of outline first, details later

arXiv preprint arXiv:2303.02490

Binxu Wang, John J Vastola

PDF Cite Diffusion Geometry Generative Model Science of AI Theory

Tuning landscapes of the ventral stream

Cell reports

Binxu Wang, Carlos R Ponce

PDF Cite Code Dataset Visual Neuroscience Geometry Generative Model Ventral Stream

The Geometry of Deep Generative Image Models and its Applications

International Conference on Learning Representations, 2021

Binxu Wang, Carlos R Ponce

PDF Cite Code Video Geometry Generative Model Optimization

Jun 1, 2026

Houston Computational Neuroscience Journal Club

Invited talk at the Houston Computational Neuroscience Journal Club

Visual Neuroscience NeuroAI

Apr 3, 2026

University of Texas at Austin — Xuexin Wei Lab Meeting

Neuronal Tuning Landscape on Generative Image Manifolds

Visual Neuroscience NeuroAI

Mar 9, 2026

Flatiron Institute / CUNY — M.S. in Cognitive Science Special Seminar

From Closed-Loop Vision to Creative Machines: Generative Models as Tools and Theories of Neural Representation and Creativity

Visual Neuroscience NeuroAI

Feb 16, 2026

University of Minnesota — Department of Neuroscience Special Seminar

From Closed-Loop Vision to Creative Machines: Generative Models as Tools and Theories of Neural Representation and Creativity

Visual Neuroscience NeuroAI

Feb 9, 2026

University of Cincinnati — Department of Biological Sciences Special Seminar

From Closed-Loop Vision to Creative Machines: Generative Models as Tools and Theories of Neural Representation and Creativity

Visual Neuroscience NeuroAI

Jan 15, 2026

University of Oregon, Knight Campus — Department of Bioengineering Special Symposium

Towards Generative and Predictive AI as Computational Interfaces to the Brain

Visual Neuroscience NeuroAI

Dec 1, 2025

University of Wisconsin–Madison — Department of Psychology Special Seminar

From Closed-Loop Vision to Creative Machines: Generative Models as Tools and Theories of Neural Representation and Creativity

Visual Neuroscience NeuroAI

Oct 10, 2025

Cold Spring Harbor Laboratory — NeuroAI Seminar

Model-Optimized Stimuli for Comparing Brain-Alignment of Generative Models and Encoding Models

Visual Neuroscience NeuroAI

Tech Note

Note on Variants of Diffusion Scheduler, DDPM DDIM PNDM

Motivation Given the popularity and power of diffusion models, the theoretical formulation of these models are not in unison. Because multiple groups have derived these models from different background, there exist multiple formulations, SDE, ODE, Markov Chain, Non-markov chain etc.

tech note Algorithm ODE SDE Dynamic System Generative Model Diffusion model

January 16, 2023

Tech Note

Note on Equivalent Score Matching Objective

TOC {:toc} Motivation Consider a distribution $p(x)$, we could “convolve” it with a kernel $p(\tilde{x}\mid x)=q(\tilde{x}-x)$. The marginal distribution of $\tilde{x}$ is denoted as $p_\sigma(\tilde{x})$. We want to model the score of this convolved distribution and that of the original distribution $\nabla\log p_\sigma(\tilde{x})$ .

tech note Algorithm Machine Learning Statistical Learning Generative Model probability

June 20, 2022

Tech Note

Note on Diffusion Generative Models

TOC {:toc} Motivation Recently, a line of research emerged in generative image models, diffusion models, which showed a competitive performance with GAN [^1]. More recently, a larger scale version of it gave rise to the ground breaking model DALL-E 2 and its precursor GLIDE.

tech note Algorithm Machine Learning Statistical Learning Generative Model

May 9, 2022

Academic Note

Note on Generative Adversarial Network

Note on GAN Note with reference to the Youtube lecture series Hongyi Li. Architecture Developments Self Attention Used in Self-Attention GAN and BigGAN class Self_Attn(nn.Module): """ Self attention Layer""" def __init__(self,in_dim,activation): super(Self_Attn,self).__init__() self.chanel_in = in_dim self.activation = activation self.query_conv = nn.Conv2d(in_channels = in_dim , out_channels = in_dim//8 , kernel_size= 1) self.key_conv = nn.Conv2d(in_channels = in_dim , out_channels = in_dim//8 , kernel_size= 1) self.value_conv = nn.Conv2d(in_channels = in_dim , out_channels = in_dim , kernel_size= 1) self.gamma = nn.Parameter(torch.zeros(1)) self.softmax = nn.Softmax(dim=-1) # def forward(self,x): """ inputs : x : input feature maps( B X C X W X H) returns : out : self attention value + input feature attention: B X N X N (N is Width*Height) """ m_batchsize,C,width ,height = x.size() proj_query = self.query_conv(x).view(m_batchsize,-1,width*height).permute(0,2,1) # B X CX(N) proj_key = self.key_conv(x).view(m_batchsize,-1,width*height) # B X C x (*W*H) energy = torch.bmm(proj_query,proj_key) # transpose check attention = self.softmax(energy) # BX (N) X (N) proj_value = self.value_conv(x).view(m_batchsize,-1,width*height) # B X C X N out = torch.bmm(proj_value,attention.permute(0,2,1) ) out = out.view(m_batchsize,C,width,height) out = self.gamma*out + x return out,attention Style GAN BigGAN Conditional GAN Text Conditioning Text is processed and combined with noise vector.

academic note generative model computer vision computer graphics machine learning deep learning

March 7, 2020

Generative Model

Related Tags