AIConfPaper
← Search

Eva L. Dyer

19 accepted papers

2025

A Scalable, Causal, and Energy Efficient Framework for Neural Decoding with Spiking Neural Networks

Georgios Mentzelopoulos, Ioannis Asmanis, Konrad Kording, Eva L Dyer, Kostas Daniilidis, Flavia Vitale
NeurIPS 2025poster

Brain-computer interfaces (BCIs) promise to enable vital functions, such as speech and prosthetic control, for individuals with neuromotor impairments. Central to their success are neural decoders, models that map neural activity to intended behavior. Current learning-based decoding approaches fall…

Cited by 0Source ↗Scholar ↗
2025

Generalizable, real-time neural decoding with hybrid state-space models

Avery Hee-Woon Ryoo, Nanda H Krishna, Ximeng Mao, Mehdi Azabou, Eva L Dyer, Matthew G Perich +1
NeurIPS 2025poster

Real-time decoding of neural activity is central to neuroscience and neurotechnology applications, from closed-loop experiments to brain-computer interfaces, where models are subject to strict latency constraints. Traditional methods, including simple recurrent neural networks, are fast and lightwei…

Cited by 0Source ↗Scholar ↗
2025

In vivo cell-type and brain region classification via multimodal contrastive learning

Han Yu, Hanrui Lyu, YiXun Xu, Charlie Windolf, Eric Kenji Lee, Fan Yang +8
ICLR 2025spotlight

Current electrophysiological approaches can track the activity of many neurons, yet it is usually unknown which cell-types or brain areas are being recorded without further molecular or histological analysis. Developing accurate and scalable algorithms for identifying the cell-type and brain region…

Cited by 1Source ↗PDF ↗Scholar ↗
2025

Know Thyself by Knowing Others: Learning Neuron Identity from Population Context

Vinam Arora, Divyansha Lachi, Ian Jarratt Knight, Mehdi Azabou, Blake Aaron Richards, Cole Lincoln Hurwitz +2
NeurIPS 2025poster

Identifying the functional identity of individual neurons is essential for interpreting circuit dynamics, yet it remains a major challenge in large-scale _in vivo_ recordings where anatomical and molecular labels are often unavailable. Here we introduce NuCLR, a self-supervised framework that learns…

Cited by 0Source ↗code ↗Scholar ↗
2025

Multi-session, multi-task neural decoding from distinct cell-types and brain regions

Mehdi Azabou, Krystal Xuejing Pan, Vinam Arora, Ian Jarratt Knight, Eva L Dyer, Blake Aaron Richards
ICLR 2025spotlight

Recent work has shown that scale is important for improved brain decoding, with more data leading to greater decoding accuracy. However, large-scale decoding across many different datasets is challenging because neural circuits are heterogeneous---each brain region contains a unique mix of cellular…

Cited by 1Source ↗PDF ↗Scholar ↗
2025

Neural Encoding and Decoding at Scale

Yizi Zhang, Yanchen Wang, Mehdi Azabou, Alexandre Andre, Zixuan Wang, Hanrui Lyu +4
ICML 2025spotlight

Recent work has demonstrated that large-scale, multi-animal models are powerful tools for characterizing the relationship between neural activity and behavior. Current large-scale approaches, however, focus exclusively on either predicting neural activity from behavior (encoding) or predicting behav…

Cited by 1Source ↗PDF ↗Scholar ↗
2024

Balanced Data, Imbalanced Spectra: Unveiling Class Disparities with Spectral Imbalance

Chiraag Kaushik, Ran Liu, Chi-Heng Lin, Amrit Khera, Matthew Y Jin, Wenrui Ma +2
ICML 2024poster

Classification models are expected to perform equally well for different classes, yet in practice, there are often large gaps in their performance. This issue of class bias is widely studied in cases of datasets with sample imbalance, but is relatively overlooked in balanced datasets. In this work,…

Cited by 4Source ↗PDF ↗Scholar ↗
2024

Towards a "Universal Translator" for Neural Dynamics at Single-Cell, Single-Spike Resolution

Yizi Zhang, Yanchen Wang, Donato M. Jiménez-Benetó, Zixuan Wang, Mehdi Azabou, Blake Aaron Richards +6
NeurIPS 2024poster

Neuroscience research has made immense progress over the last decade, but our understanding of the brain remains fragmented and piecemeal: the dream of probing an arbitrary brain region and automatically reading out the information encoded in its neural activity remains out of reach. In this work, w…

Cited by 6Source ↗PDF ↗Scholar ↗
2024

Your contrastive learning problem is secretly a distribution alignment problem

Zihao Chen, Chi-Heng Lin, Ran Liu, Jingyun Xiao, Eva L Dyer
NeurIPS 2024poster

Despite the success of contrastive learning (CL) in vision and language, its theoretical foundations and mechanisms for building representations remain poorly understood. In this work, we build connections between noise contrastive estimation losses widely used in CL and distribution alignment with…

Cited by 1Source ↗PDF ↗code ↗Scholar ↗
2023

A Unified, Scalable Framework for Neural Population Decoding

Mehdi Azabou, Vinam Arora, Venkataramana Ganesh, Ximeng Mao, Santosh B Nachimuthu, Michael Jacob Mendelson +4
NeurIPS 2023poster

Our ability to use deep learning approaches to decipher neural activity would likely benefit from greater scale, in terms of both the model size and the datasets. However, the integration of many neural recordings into one unified model is challenging, as each recording contains the activity of diff…

Cited by 41Source ↗PDF ↗Scholar ↗
2023

Half-Hop: A graph upsampling approach for slowing down message passing

Mehdi Azabou, Venkataramana Ganesh, Shantanu Thakoor, Chi-Heng Lin, Lakshmi Sathidevi, Ran Liu +3
ICML 2023poster

Message passing neural networks have shown a lot of success on graph-structured data. However, there are many instances where message passing can lead to over-smoothing or fail when neighboring nodes belong to different classes. In this work, we introduce a simple yet general framework for improving…

Cited by 31Source ↗PDF ↗code ↗Scholar ↗
2023

Relax, it doesn’t matter how you get there: A new self-supervised approach for multi-timescale behavior analysis

Mehdi Azabou, Michael Jacob Mendelson, Nauman Ahad, Maks Sorokin, Shantanu Thakoor, Carolina Urzay +1
NeurIPS 2023spotlight

Unconstrained and natural behavior consists of dynamics that are complex and unpredictable, especially when trying to predict what will happen multiple steps into the future. While some success has been found in building representations of animal behavior under constrained or simplified task-base…

Cited by 8Source ↗PDF ↗Scholar ↗
2022

Large-Scale Representation Learning on Graphs via Bootstrapping

Shantanu Thakoor, Corentin Tallec, Mohammad Gheshlaghi Azar, Mehdi Azabou, Eva L Dyer, Remi Munos +2
ICLR 2022poster

Self-supervised learning provides a promising path towards eliminating the need for costly label information in representation learning on graphs. However, to achieve state-of-the-art performance, methods often need large numbers of negative examples and rely on complex augmentations. This can be…

Cited by 324Source ↗PDF ↗code ↗Scholar ↗
2022

MTNeuro: A Benchmark for Evaluating Representations of Brain Structure Across Multiple Levels of Abstraction

Jorge Quesada, Lakshmi Sathidevi, Ran Liu, Nauman Ahad, Joy M Jackson, Mehdi Azabou +7
NeurIPS 2022accept

There are multiple scales of abstraction from which we can describe the same image, depending on whether we are focusing on fine-grained details or a more global attribute of the image. In brain mapping, learning to automatically parse images to build representations of both small-scale features (e.…

Cited by 5Source ↗PDF ↗code ↗Scholar ↗
2022

Seeing the forest and the tree: Building representations of both individual and collective dynamics with transformers

Ran Liu, Mehdi Azabou, Max Dabagia, Jingyun Xiao, Eva L Dyer
NeurIPS 2022accept

Complex time-varying systems are often studied by abstracting away from the dynamics of individual components to build a model of the population-level dynamics from the start. However, when building a population-level description, it can be easy to lose sight of each individual and how they contribu…

Cited by 21Source ↗PDF ↗code ↗Scholar ↗
2021

Bayesian optimization for modular black-box systems with switching costs

Chi-Heng Lin, Joseph D. Miano, Eva L. Dyer
UAI 2021poster

Most existing black-box optimization methods assume that all variables in the system being optimized have equal cost and can change freely at each iteration. However, in many real-world systems, inputs are passed through a sequence of different operations or modules, making variables in earlier stag…

Cited by 7Source ↗PDF ↗Scholar ↗
2021

Drop, Swap, and Generate: A Self-Supervised Approach for Generating Neural Activity

Ran Liu, Mehdi Azabou, Max Dabagia, Chi-Heng Lin, Mohammad Gheshlaghi Azar, Keith B Hengen +2
NeurIPS 2021oral

Meaningful and simplified representations of neural activity can yield insights into how and what information is being processed within a neural circuit. However, without labels, finding representations that reveal the link between the brain and behavior can be challenging. Here, we introduce a nove…

Cited by 31Source ↗PDF ↗Scholar ↗
2021

Neural Latents Benchmark ‘21: Evaluating latent variable models of neural population activity

Felix C Pei, Joel Ye, David M. Zoltowski, Anqi Wu, Raeed Hasan Chowdhury, Hansem Sohn +10
NeurIPS 2021poster

Advances in neural recording present increasing opportunities to study neural activity in unprecedented detail. Latent variable models (LVMs) are promising tools for analyzing this rich activity across diverse neural systems and behaviors, as LVMs do not depend on known relationships between the act…

Cited by 98Source ↗code ↗Scholar ↗