72 citations · 151 across the 16 of their papers we have counts for
11 papers · 1 filter
Catastrophic Compositional Generation: Why Vanilla Diffusion Models Fail to Extrapolate
Duncan Soiffer, Chandler Squires, Yuan Guan +2
The task of compositional generation involves using a conditional generative model, trained only on a subset of the possible conditions, to produce samples from compositionally-def…
Learning What Matters: Steering Diffusion via Spectrally Anisotropic Forward Noise
Luca Scimeca, Thomas Jiralerspong, Berton Earnshaw +2
Diffusion Probabilistic Models (DPMs) have achieved strong generative performance, yet their inductive biases remain largely implicit. In this work, we aim to build inductive biase…
Shaping Inductive Bias in Diffusion Models through Frequency-Based Noise Control
Thomas Jiralerspong, Berton Earnshaw, Jason Hartford +2
Diffusion Probabilistic Models (DPMs) are powerful generative models that have achieved unparalleled success in a number of generative tasks. In this work, we aim to build inductiv…
Sparsity regularization via tree-structured environments for disentangled representations
Elliot Layne, Jason Hartford, Sébastien Lachapelle +2
Many causal systems such as biological processes in cells can only be observed indirectly via measurements, such as gene expression. Causal representation learning -- the task of c…
Object-centric architectures enable efficient causal representation learning
Amin Mansouri, Jason Hartford, Yan Zhang +1
Causal representation learning has showed a variety of settings in which we can disentangle latent variables with identifiability guarantees (up to some reasonable equivalence clas…
DynGFN: Towards Bayesian Inference of Gene Regulatory Networks with GFlowNets
Lazar Atanackovic, Alexander Tong, Bo Wang +3
One of the grand challenges of cell biology is inferring the gene regulatory network (GRN) which describes interactions between genes and their products that control gene expressio…
GFlowNets for AI-Driven Scientific Discovery
Moksh Jain, Tristan Deleu, Jason Hartford +3
Tackling the most pressing problems for humanity, such as the climate crisis and the threat of global pandemics, requires accelerating the pace of scientific discovery. While scien…
Weakly Supervised Representation Learning with Sparse Perturbations
Kartik Ahuja, Jason Hartford, Yoshua Bengio
The theory of representation learning aims to build methods that provably invert the data generating process with minimal domain knowledge or any source of supervision. Most prior…
Properties from Mechanisms: An Equivariance Perspective on Identifiable Representation Learning
Kartik Ahuja, Jason Hartford, Yoshua Bengio
A key goal of unsupervised representation learning is "inverting" a data generating process to recover its latent properties. Existing work that provably achieves this goal relies…
The Perils of Learning Before Optimizing
Chris Cameron, Jason Hartford, Taylor Lundy +1
Formulating real-world optimization problems often begins with making predictions from historical data (e.g., an optimizer that aims to recommend fast routes relies upon travel-tim…
Exemplar Guided Active Learning
Jason Hartford, Kevin Leyton-Brown, Hadas Raviv +3
We consider the problem of wisely using a limited budget to label a small subset of a large unlabeled dataset. We are motivated by the NLP problem of word sense disambiguation. For…