AIConfPaper
← Search

Adeel Pervez

10 accepted papers

2026

Learning Explicit Single-Cell Dynamics Using ODE Representations

Jan-Philipp von Bassewitz, Adeel Pervez, Marco Fumero, Matthew R Robinson, Theofanis Karaletsos, Francesco Locatello
ICLR 2026poster

Modeling the dynamics of cellular differentiation is fundamental to advancing the understanding and treatment of diseases associated with this process, such as cancer. With the rapid growth of single-cell datasets, this has also become a particularly promising and active domain for machine learning.…

Cited by 0Source ↗code ↗Scholar ↗
2026

The Perception–Physics Paradox: Probing Scientific Alignment with TC-Atlas

Dingling Yao, Andrea Polesello, Adeel Pervez, Caroline Muller, Francesco Locatello
ICML 2026poster

While Vision Foundation Models (VFMs) excel at predictive tasks on satellite imagery, their performance can arise from visual correlations rather than underlying structural invariants, making certain perception-based out-of-distribution accuracy a poor proxy for scientific utility. As a result, mode…

Cited by 0Source ↗Scholar ↗
2025

Mechanistic PDE Networks for Discovery of Governing Equations

Adeel Pervez, Efstratios Gavves, Francesco Locatello
ICML 2025poster

We present Mechanistic PDE Networks -- a model for discovery of governing *partial differential equations* from data. Mechanistic PDE Networks represent spatiotemporal data as space-time dependent *linear* partial differential equations in neural network hidden representations. The represented PDEs…

Cited by 1Source ↗PDF ↗Scholar ↗
2025

Scalable Mechanistic Neural Networks

Jiale Chen, Dingling Yao, Adeel Pervez, Dan Alistarh, Francesco Locatello
ICLR 2025poster

We propose Scalable Mechanistic Neural Network (S-MNN), an enhanced neural network framework designed for scientific machine learning applications involving long temporal sequences. By reformulating the original Mechanistic Neural Network (MNN) (Pervez et al., 2024), we reduce the computational time…

Cited by 1Source ↗PDF ↗code ↗Scholar ↗
2024

Mechanistic Neural Networks for Scientific Machine Learning

Adeel Pervez, Francesco Locatello, Stratis Gavves
ICML 2024poster

This paper presents *Mechanistic Neural Networks*, a neural network design for machine learning applications in the sciences. It incorporates a new *Mechanistic Block* in standard architectures to explicitly learn governing differential equations as representations, revealing the underlying dynamics…

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

Differentiable Mathematical Programming for Object-Centric Representation Learning

Adeel Pervez, Phillip Lippe, Efstratios Gavves
ICLR 2023poster

We propose topology-aware feature partitioning into $k$ disjoint partitions for given scene features as a method for object-centric representation learning. To this end, we propose to use minimum $s$-$t$ graph cuts as a partitioning method which is represented as a linear program. The method is topo…

Cited by 7Source ↗PDF ↗Scholar ↗
2021

Spectral Smoothing Unveils Phase Transitions in Hierarchical Variational Autoencoders

Adeel Pervez, Efstratios Gavves
ICML 2021oral

Variational autoencoders with deep hierarchies of stochastic layers have been known to suffer from the problem of posterior collapse, where the top layers fall back to the prior and become independent of input. We suggest that the hierarchical VAE objective explicitly includes the variance of the fu…

Cited by 10Source ↗PDF ↗Scholar ↗
2020

Low Bias Low Variance Gradient Estimates for Boolean Stochastic Networks

Adeel Pervez, Taco Cohen, Efstratios Gavves
ICML 2020poster

Stochastic neural networks with discrete random variables are an important class of models for their expressiveness and interpretability. Since direct differentiation and backpropagation is not possible, Monte Carlo gradient estimation techniques are a popular alternative. Efficient stochastic gradi…

Cited by 17Source ↗PDF ↗Scholar ↗