Shahab Bakhtiari

Laura Chen

Research Intern - McGill University University

Nastaran Darjani

PhD - Université de Montréal

Google Scholar

Parastoo Geranmayeh

Collaborating researcher - Concordia University University

Hafez Ghaemi

PhD - Université de Montréal

Principal supervisor :

PhD

Research Intern - Université de Montréal

Anh Thi Nguyen

Undergraduate - Université de Montréal

Ladan Shahshahani

Postdoctorate - Université de Montréal

Google Scholar

Liza Sycheva

Master's Research - Université de Montréal

Doris Voina

Postdoctorate - Université de Montréal

Charlotte Volk

PhD - McGill University

Principal supervisor :

Blake Richards

Publications

Shaped by meaning, weighted by reliability: New insights into multisensory integration

Elizaveta Sycheva

Léa St-Gelais

Karim Jerbi CoCo Lab

Franco Lepore

Vanessa Hadid

2026-01-04

bioRxiv (preprint)

Interpreting Physics in Video World Models

Sonia Joseph

Quentin Garrido

Randall Balestriero

Matthew Kowal

Thomas Fel

Blake Richards

Mike Rabbat

A long-standing question in physical reasoning is whether video-based models need to rely on factorized representations of physical variable… (see more)s in order to make physically accurate predictions, or whether they can implicitly represent such variables in a distributed manner. While modern video world models achieve strong performance on intuitive physics benchmarks, it remains unclear which of these representational regimes they implement internally. Here, we present the first interpretability study to directly examine physical representations inside large-scale video encoders. Using layerwise probing, subspace geometry, patch-level decoding, and targeted attention ablations, we characterize where physical information becomes accessible and how it is organized within encoder-based video transformers. Across architectures, we identify a sharp intermediate-depth transition— which we call the \emph{Physics Emergence Zone}—at which physical variables become accessible. Physics-related representations peak shortly after this transition and degrade toward the output layers. Decomposing motion into explicit variables, we find that scalar quantities such as speed and acceleration are available from early layers onwards, whereas motion direction becomes accessible only at the Physics Emergence Zone. Notably, we find that direction is encoded through a high-dimensional population structure with circular geometry, requiring coordinated multi-feature intervention to control. These findings suggest that modern video models do not use factorized representations of physical variables like a classical physics engine. Instead, they use a distributed representation that is nonetheless sufficient for making physical predictions.

2025-12-31

International Conference on Machine Learning (Accept (regular))

Context-Aware World Models for Task-Agnostic Control

Busra Tugce Gurbuz

Hafez Ghaemi

Christopher C. Pack

Eilif Benjamin Muller

2025-09-22

NeurIPS.cc/2025/Workshop/UniReps (published)

Why all roads don't lead to Rome: Representation geometry varies across the human visual cortical hierarchy

Arna Ghosh

Zahraa Chorghay

Blake Aaron Richards

2025-09-22

NeurIPS.cc/2025/Workshop/NeurReps (published)

The curriculum effect in visual learning: the role of readout dimensionality

Charlotte Volk

Christopher C. Pack

2025-09-19

bioRxiv (preprint)

seq-JEPA: Autoregressive Predictive Learning of Invariant-Equivariant World Models

Hafez Ghaemi

Eilif B. Muller

Current self-supervised algorithms commonly rely on transformations such as data augmentation and masking to learn visual representations. T… (see more)his is achieved by enforcing invariance or equivariance with respect to these transformations after encoding two views of an image. This dominant two-view paradigm often limits the flexibility of learned representations for downstream adaptation by creating performance trade-offs between high-level invariance-demanding tasks such as image classification and more fine-grained equivariance-related tasks. In this work, we proposes \emph{seq-JEPA}, a world modeling framework that introduces architectural inductive biases into joint-embedding predictive architectures to resolve this trade-off. Without relying on dual equivariance predictors or loss terms, seq-JEPA simultaneously learns two architecturally segregated representations: one equivariant to specified transformations and another invariant to them. To do so, our model processes short sequences of different views (observations) of inputs. Each encoded view is concatenated with an embedding of the relative transformation (action) that produces the next observation in the sequence. These view-action pairs are passed through a transformer encoder that outputs an aggregate representation. A predictor head then conditions this aggregate representation on the upcoming action to predict the representation of the next observation. Empirically, seq-JEPA demonstrates strong performance on both equivariant and invariant benchmarks without sacrificing one for the other. Furthermore, it excels at tasks that inherently require aggregating a sequence of observations, such as path integration across actions and predictive learning across eye movements.

2025-09-17

NeurIPS.cc/2025/Conference (poster)

Seeing the world as animals do: How to leverage generative AI for ecological neuroscience

2024-12-31

The Transmitter (published)

Exploiting large-scale neuroimaging datasets to reveal novel insights in vision science

Ian Charest

Peter Brotherwood

Catherine Landry

Jasper van den Bosch

Tim Kietzmann

Frédéric Gosselin

Adrien Doerig

2024-09-14

Journal of Vision (published)

Neural responses in space and time to a massive set of natural scenes

Peter Brotherwood

Emmanuel Lebeau

Mathias Salvas-Hébert

Marin Coignard

Frédéric Gosselin

Kendrick Kay

Ian Charest

2024-09-14

Journal of Vision (published)

Asymmetric stimulus representations bias visual perceptual learning

Pooya Laamerad

Asmara Awada

Christopher C. Pack

The primate visual cortex contains various regions that exhibit specialization for different stimulus properties, such as motion, shape, and… (see more) color. Within each region, there is often further specialization, such that particular stimulus features, such as horizontal and vertical orientations, are over-represented. These asymmetries are associated with well-known perceptual biases, but little is known about how they influence visual learning. Most theories would predict that learning is optimal, in the sense that it is unaffected by these asymmetries. However, other approaches to learning would result in specific patterns of perceptual biases. To distinguish between these possibilities, we trained human observers to discriminate between expanding and contracting motion patterns, which have a highly asymmetrical representation in the visual cortex. Observers exhibited biased percepts of these stimuli, and these biases were affected by training in ways that were often suboptimal. We simulated different neural network models and found that a learning rule that involved only adjustments to decision criteria, rather than connection weights, could account for our data. These results suggest that cortical asymmetries influence visual perception and that human observers often rely on suboptimal strategies for learning.

2024-01-28

Journal of Vision (published)

Spatial Distribution Modeling of Pistacia atlantica using Artificial Neural Network in Khohir National Park

Tymour Rostani Shahraji

Reza Akhavan

Reza Ebrahimi Atani

2023-10-31

Ecology of Iranian Forests (published)

Energy efficiency as a normative account for predictive coding

2022-12-08

Patterns (published)