# Inferring response times of perceptual decisions with Poisson variational autoencoders

arXiv: https://arxiv.org/abs/2511.11480 · HTML: https://mlsanity.com/paper/2511.11480/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 46 references that are in the map.
- First posted on arXiv 14 Nov 2025.

## Builds on (most cited first, 8 of 8)

- [Unsupervised deep learning identifies semantic disentanglement in single inferotemporal neurons](https://mlsanity.com/paper/2006.14304/) (2020)
- [Poisson Variational Autoencoder](https://mlsanity.com/paper/2405.14473/) (2024)
- [Modeling Category-Selective Cortical Regions with Topographic Variational Autoencoders](https://mlsanity.com/paper/2110.13911/) (2021)
- [Computing a human-like reaction time metric from stable recurrent vision models](https://mlsanity.com/paper/2306.11582/) (2023)
- [Brain-like Variational Inference](https://mlsanity.com/paper/2410.19315/) (2024)
- [RTify: Aligning Deep Neural Networks with Human Behavioral Decisions](https://mlsanity.com/paper/2411.03630/) (2024)
- [Seeing into Darkness: Scotopic Visual Recognition](https://mlsanity.com/paper/1610.00405/) (2016)
- [An image-computable model of speeded decision-making](https://mlsanity.com/paper/2403.16382/) (2024)

## Built on by (most cited first, 2 of 2)

- [A hitchhiker's guide to Poisson gradient estimation](https://mlsanity.com/paper/2602.03896/) (2026)
- [Metabolic cost of information processing in Poisson variational autoencoders](https://mlsanity.com/paper/2602.13421/) (2026)

## Abstract (arXiv)

Many properties of perceptual decision making are well-modeled by deep neural networks. However, such architectures typically treat decisions as instantaneous readouts, overlooking the temporal dynamics of the decision process. We present an image-computable model of perceptual decision making in which choices and response times arise from efficient sensory encoding and Bayesian decoding of neural spiking activity. We use a Poisson variational autoencoder to learn unsupervised representations of visual stimuli in a population of rate-coded neurons, modeled as independent homogeneous Poisson processes. A task-optimized decoder then continually infers an approximate posterior over actions conditioned on incoming spiking activity. Combining these components with an entropy-based stopping rule yields a principled and image-computable model of perceptual decisions capable of generating trial-by-trial patterns of choices and response times. Applied to MNIST digit classification, the model reproduces key empirical signatures of perceptual decision making, including stochastic variability, right-skewed response time distributions, logarithmic scaling of response times with the number of alternatives (Hick's law), and speed-accuracy trade-offs.