Portrait of Hafez Ghaemi

Hafez Ghaemi

PhD - Université de Montréal
Supervisor
Eilif B. Muller
Co-supervisor
Shahab Bakhtiari
Research Topics
Computer Vision
Deep Learning
Reinforcement Learning
Representation Learning
Website
Google Scholar
GitHub

Publications

Self-Supervised Learning from Structural Invariance
Yipeng Zhang
Hafez Ghaemi
Jungyoon Lee
Shahab Bakhtiari
Laurent Charlin
Eilif Benjamin Muller
2025-09-22
NeurIPS.cc/2025/Workshop/UniReps (oral)
openreview.net
openreview.net
seq-JEPA: Autoregressive Predictive Learning of Invariant-Equivariant World Models
Hafez Ghaemi
Eilif B. Muller
Shahab Bakhtiari
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)
doi.org
openreview.net
Seq-JEPA: Autoregressive Predictive Learning of Invariant-Equivariant World Models
Hafez Ghaemi
Eilif Benjamin Muller
Shahab Bakhtiari
Joint-embedding predictive architecture (JEPA) is a self-supervised learning (SSL) paradigm with the capacity of world modeling via action-c… (see more)onditioned prediction. Previously, JEPA world models have been shown to learn action-invariant or action-equivariant representations by predicting one view of an image from another. Unlike JEPA and similar SSL paradigms, animals, including humans, learn to recognize new objects through a sequence of active interactions. To introduce \emph{sequential} interactions, we propose \textit{seq-JEPA}, a novel SSL world model equipped with an autoregressive memory module. Seq-JEPA aggregates a sequence of action-conditioned observations to produce a global representation of them. This global representation, conditioned on the next action, is used to predict the latent representation of the next observation. We empirically show the advantages of this sequence of action-conditioned observations and examine our sequential modeling paradigm in two settings: (1) \emph{predictive learning across saccades}; a method inspired by the role of eye movements in embodied vision. This approach learns self-supervised image representations by processing a sequence of low-resolution visual patches sampled from image saliencies, without any hand-crafted data augmentations. (2) \emph{invariance-equivariance trade-off}; seq-JEPA's architecture results in automatic separation of invariant and equivariant representations, with the aggregated autoregressor outputs being mostly action-invariant and the encoder output being equivariant. This is in contrast with many equivariant SSL methods that expect a single representational space to contain both invariant and equivariant features, potentially creating a trade-off between the two. Empirically, seq-JEPA achieves competitive performance on both invariance and equivariance-related benchmarks compared to existing methods. Importantly, both invariance and equivariance-related downstream performances increase as the number of available observations increases.
2024-10-13
NeurIPS.cc/2024/Workshop/SSL (published)
openreview.net
openreview.net
Seq-JEPA: Autoregressive Predictive Learning of Invariant-Equivariant World Models
Hafez Ghaemi
Eilif Benjamin Muller
Shahab Bakhtiari
Joint-embedding predictive architecture (JEPA) is a self-supervised learning (SSL) paradigm with the capacity of world modeling via action-c… (see more)onditioned prediction. Previously, JEPA world models have been shown to learn action-invariant or action-equivariant representations by predicting one view of an image from another. Unlike JEPA and similar SSL paradigms, animals, including humans, learn to recognize new objects through a sequence of active interactions. To introduce \emph{sequential} interactions, we propose \textit{seq-JEPA}, a novel SSL world model equipped with an autoregressive memory module. Seq-JEPA aggregates a sequence of action-conditioned observations to produce a global representation of them. This global representation, conditioned on the next action, is used to predict the latent representation of the next observation. We empirically show the advantages of this sequence of action-conditioned observations and examine our sequential modeling paradigm in two settings: (1) \emph{predictive learning across saccades}; a method inspired by the role of eye movements in embodied vision. This approach learns self-supervised image representations by processing a sequence of low-resolution visual patches sampled from image saliencies, without any hand-crafted data augmentations. (2) \emph{invariance-equivariance trade-off}; seq-JEPA's architecture results in automatic separation of invariant and equivariant representations, with the aggregated autoregressor outputs being mostly action-invariant and the encoder output being equivariant. This is in contrast with many equivariant SSL methods that expect a single representational space to contain both invariant and equivariant features, potentially creating a trade-off between the two. Empirically, seq-JEPA achieves competitive performance on both invariance and equivariance-related benchmarks compared to existing methods. Importantly, both invariance and equivariance-related downstream performances increase as the number of available observations increases.
2024-10-13
NeurIPS.cc/2024/Workshop/SSL (published)
doi.org
openreview.net