AIConfPaper
← Search

Gabriel Kreiman

20 accepted papers

2026

Stretching Beyond the Obvious: A Gradient-Free Framework to Unveil the Hidden Landscape of Visual Invariance

Lorenzo Tausani, Paolo Muratore, Morgan Bruce Talbot, Giacomo Amerio, Gabriel Kreiman, Davide Zoccolan
ICLR 2026poster

Uncovering which feature combinations are encoded by visual units is critical to understanding how images are transformed into representations that support recognition. While existing feature visualization approaches typically infer a unit's most exciting images, this is insufficient to reveal the m…

Cited by 0Source ↗Scholar ↗
2025

HumorDB: Can AI understand graphical humor?

Vedaant V Jain, Gabriel Kreiman, Felipe dos Santos Alves Feitosa
ICCV 2025poster

Despite significant advancements in image segmentation and object detection, understanding complex scenes remains a significant challenge. Here, we focus on graphical humor as a paradigmatic example of image interpretation that requires elucidating the interaction of different scene elements in the…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

L-WISE: Boosting Human Visual Category Learning Through Model-Based Image Selection and Enhancement

Morgan Bruce Talbot, Gabriel Kreiman, James J. DiCarlo, Guy Gaziv
ICLR 2025poster

The currently leading artificial neural network models of the visual ventral stream - which are derived from a combination of performance optimization and robustification methods - have demonstrated a remarkable degree of behavioral alignment with humans on visual categorization tasks. We show that…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

The Indoor-Training Effect: Unexpected Gains from Distribution Shifts in the Transition Function

Serena Bono, Spandan Madan, Ishaan Grover, Mao Yasueda, Cynthia Breazeal, Hanspeter Pfister +1
AAAI 2025technical

Is it better to perform tennis training in a pristine indoor environment or a noisy outdoor one? To model this problem, here we investigate whether shifts in the transition probabilities between the training and testing environments in reinforcement learning problems can lead to better performance u…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2024

Benchmarking Out-of-Distribution Generalization Capabilities of DNN-based Encoding Models for the Ventral Visual Cortex.

Spandan Madan, Will Xiao, Mingran Cao, Hanspeter Pfister, Margaret Livingstone, Gabriel Kreiman
NeurIPS 2024poster

We characterized the generalization capabilities of deep neural network encoding models when predicting neuronal responses from the visual cortex to flashed images. We collected MacaqueITBench, a large-scale dataset of neuronal population responses from the macaque inferior temporal (IT) cortex to o…

Cited by 4Source ↗PDF ↗code ↗Scholar ↗
2024

Brain Treebank: Large-scale intracranial recordings from naturalistic language stimuli

Christopher Wang, Adam Uri Yaari, Aaditya K Singh, Vighnesh Subramaniam, Dana Rosenfarb, Jan DeWitt +7
NeurIPS 2024oral

We present the Brain Treebank, a large-scale dataset of electrophysiological neural responses, recorded from intracranial probes while 10 subjects watched one or more Hollywood movies. Subjects watched on average 2.6 Hollywood movies, for an average viewing time of 4.3 hours, and a total of 43 hours…

Cited by 3Source ↗PDF ↗Scholar ↗
2024

Forward Learning with Top-Down Feedback: Empirical and Analytical Characterization

Ravi Francesco Srinivasan, Francesca Mignacco, Martino Sorbaro, Maria Refinetti, Avi Cooper, Gabriel Kreiman +1
ICLR 2024poster

"Forward-only" algorithms, which train neural networks while avoiding a backward pass, have recently gained attention as a way of solving the biologically unrealistic aspects of backpropagation. Here, we first address compelling challenges related to the "forward-only" rules, which include reducing…

Cited by 21Source ↗PDF ↗Scholar ↗
2024

Revealing Vision-Language Integration in the Brain with Multimodal Networks

Vighnesh Subramaniam, Colin Conwell, Christopher Wang, Gabriel Kreiman, Boris Katz, Ignacio Cases +1
ICML 2024poster

We use (multi)modal deep neural networks (DNNs) to probe for sites of multimodal integration in the human brain by predicting stereoencephalography (SEEG) recordings taken while human subjects watched movies. We operationalize sites of multimodal integration as regions where a multimodal vision-lang…

Cited by 7Source ↗PDF ↗code ↗Scholar ↗
2023

BrainBERT: Self-supervised representation learning for intracranial recordings

Christopher Wang, Vighnesh Subramaniam, Adam Uri Yaari, Gabriel Kreiman, Boris Katz, Ignacio Cases +1
ICLR 2023poster

We create a reusable Transformer, BrainBERT, for intracranial recordings bringing modern representation learning approaches to neuroscience. Much like in NLP and speech recognition, this Transformer enables classifying complex concepts, i.e., decoding neural data, with higher accuracy and with much…

Cited by 39Source ↗PDF ↗code ↗Scholar ↗
2023

Emergence of Sparse Representations from Noise

Trenton Bricken, Rylan Schaeffer, Bruno Olshausen, Gabriel Kreiman
ICML 2023poster

A hallmark of biological neural networks, which distinguishes them from their artificial counterparts, is the high degree of sparsity in their activations. This discrepancy raises three questions our work helps to answer: (i) Why are biological networks so sparse? (ii) What are the benefits of this…

Cited by 16Source ↗PDF ↗Scholar ↗
2023

Learning to Learn: How to Continuously Teach Humans and Machines

Parantak Singh, You Li, Ankur Sikarwar, Stan Weixian Lei, Difei Gao, Morgan B. Talbot +4
ICCV 2023poster

Curriculum design is a fundamental component of education. For example, when we learn mathematics at school, we build upon our knowledge of addition to learn multiplication. These and other concepts must be mastered before our first algebra lesson, which also reinforces our addition and multiplicati…

Cited by 5PDF ↗Scholar ↗
2023

Sparse Distributed Memory is a Continual Learner

Trenton Bricken, Xander Davies, Deepak Singh, Dmitry Krotov, Gabriel Kreiman
ICLR 2023poster

Continual learning is a problem for artificial neural networks that their biological counterparts are adept at solving. Building on work using Sparse Distributed Memory (SDM) to connect a core neural circuit with the powerful Transformer model, we create a modified Multi-Layered Perceptron (MLP) tha…

Cited by 20Source ↗PDF ↗code ↗Scholar ↗
2022

Error-driven Input Modulation: Solving the Credit Assignment Problem without a Backward Pass

Giorgia Dellaferrera, Gabriel Kreiman
ICML 2022spotlight

Supervised learning in artificial neural networks typically relies on backpropagation, where the weights are updated based on the error-function gradients and sequentially propagated from the output layer to the input layer. Although this approach has proven effective in a wide domain of application…

Cited by 62Source ↗PDF ↗code ↗Scholar ↗
2022

Robust Feature-Level Adversaries are Interpretability Tools

Stephen Casper, Max Nadeau, Dylan Hadfield-Menell, Gabriel Kreiman
NeurIPS 2022accept

The literature on adversarial attacks in computer vision typically focuses on pixel-level perturbations. These tend to be very difficult to interpret. Recent work that manipulates the latent representations of image generators to create "feature-level" adversarial perturbations gives us an opportuni…

Cited by 35Source ↗PDF ↗code ↗Scholar ↗
2021

Frivolous Units: Wider Networks Are Not Really That Wide

Stephen Casper, Xavier Boix, Vanessa D'Amario, Ling Guo, Martin Schrimpf, Kasper Vinken +1
AAAI 2021technical

A remarkable characteristic of overparameterized deep neural networks (DNNs) is that their accuracy does not degrade when the network width is increased. Recent evidence suggests that developing compressible representations allows the complexity of large networks to be adjusted for the learning task…

Cited by 29Source ↗PDF ↗code ↗Scholar ↗
2021

Visual Search Asymmetry: Deep Nets and Humans Share Similar Inherent Biases

Shashi Kant Gupta, Mengmi Zhang, Chia-Chien Wu, Jeremy M. Wolfe, Gabriel Kreiman
NeurIPS 2021poster

Visual search is a ubiquitous and often challenging daily task, exemplified by looking for the car keys at home or a friend in a crowd. An intriguing property of some classical search tasks is an asymmetry such that finding a target A among distractors B can be easier than finding B among A. To eluc…

Cited by 20Source ↗PDF ↗code ↗Scholar ↗
2021

When Pigs Fly: Contextual Reasoning in Synthetic and Natural Scenes

Philipp Bomatter, Mengmi Zhang, Dimitar Karev, Spandan Madan, Claire Tseng, Gabriel Kreiman
ICCV 2021poster

Context is of fundamental importance to both human and machine vision; e.g., an object in the air is more likely to be an airplane than a pig. The rich notion of context incorporates several aspects including physics rules, statistical co-occurrences, and relative object sizes, among others. While p…

Cited by 25PDF ↗code ↗Scholar ↗
2017

Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning

William Lotter, Gabriel Kreiman, David Cox
ICLR 2017poster

While great strides have been made in using deep learning algorithms to solve supervised learning tasks, the problem of unsupervised learning - leveraging unlabeled examples to learn about the structure of a domain - remains a difficult unsolved challenge. Here, we explore prediction of future frame…

Cited by 1230Source ↗Scholar ↗