41 citations · 186 across the 21 of their papers we have counts for
21 papers
Visual prompt engineering for video models
Robert Geirhos, Yuxuan Li, Thaddäus Wiedemer +7
In the age of foundation models, a model is only as good as its prompt. For this reason, prompt engineering has become an essential technique for improving language model performan…
Physics-IQ Verified
Tim Rädsch, Yuki M Asano, Hilde Kuehne +4
Video generative models ( VGMs) have become a new frontier that can be used not just for video generation but for a multitude of downstream tasks, including world modeling. To adva…
Unified Neural Scaling Laws
Ethan Caballero, Priyank Jaini, David Krueger +1
We present a functional form (that we refer to as a Unified Neural Scaling Law (UNSL)) that accurately models and extrapolates the scaling behaviors of deep neural networks as mult…
Video models are zero-shot learners and reasoners
Thaddäus Wiedemer, Yuxuan Li, Paul Vicol +6
The remarkable zero-shot capabilities of Large Language Models (LLMs) have propelled natural language processing from task-specific models to unified, generalist foundation models.…
Do generative video models understand physical principles?
Saman Motamed, Laura Culp, Kevin Swersky +2
AI video generation is undergoing a revolution, with quality and realism advancing rapidly. These advances have led to a passionate scientific debate: Do video models learn "world…
Amortized In-Context Bayesian Posterior Estimation
Sarthak Mittal, Niels Leif Bracher, Guillaume Lajoie +2
Bayesian inference provides a natural way of incorporating prior beliefs and assigning a probability measure to the space of hypotheses. Current solutions rely on iterative routine…
Decoupling Semantic Similarity from Spatial Alignment for Neural Networks
Tassilo Wald, Constantin Ulrich, Gregor Köhler +6
What representation do deep neural networks learn? How similar are images to each other for neural networks? Despite the overwhelming success of deep learning methods key questions…
Towards flexible perception with visual memory
Robert Geirhos, Priyank Jaini, Austin Stone +5
Training a neural network is a monolithic endeavor, akin to carving knowledge into stone: once the process is completed, editing the knowledge in a network is hard, since all infor…
Intriguing properties of generative classifiers
Priyank Jaini, Kevin Clark, Robert Geirhos
What is the best paradigm to recognize objects -- discriminative inference (fast but potentially prone to shortcut learning) or using a generative model (slow but potentially more…
Text-to-Image Diffusion Models are Zero-Shot Classifiers
Kevin Clark, Priyank Jaini
The excellent generative capabilities of text-to-image diffusion models suggest they learn informative representations of image-text data. However, what knowledge their representat…
Stochastic Optimal Control for Collective Variable Free Sampling of Molecular Transition Paths
Lars Holdijk, Yuanqi Du, Ferry Hooft +3
We consider the problem of sampling transition paths between two given metastable states of a molecular system, e.g. a folded and unfolded protein or products and reactants of a ch…
Particle Dynamics for Learning EBMs
Kirill Neklyudov, Priyank Jaini, Max Welling
Energy-based modeling is a promising approach to unsupervised learning, which yields many downstream applications from a single model. The main difficulty in learning energy-based…
Learning Equivariant Energy Based Models with Equivariant Stein Variational Gradient Descent
Priyank Jaini, Lars Holdijk, Max Welling
We focus on the problem of efficient sampling and learning of probability densities by incorporating symmetries in probabilistic models. We first introduce Equivariant Stein Variat…
Sampling in Combinatorial Spaces with SurVAE Flow Augmented MCMC
Priyank Jaini, Didrik Nielsen, Max Welling
Hybrid Monte Carlo is a powerful Markov Chain Monte Carlo method for sampling from complex continuous distributions. However, a major limitation of HMC is its inability to be appli…
Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions
Emiel Hoogeboom, Didrik Nielsen, Priyank Jaini +2
Generative flows and diffusion models have been predominantly trained on ordinal data, for example natural images. This paper introduces two extensions of flows and diffusion for c…
Self Normalizing Flows
T. Anderson Keller, Jorn W. T. Peters, Priyank Jaini +3
Efficient gradient computation of the Jacobian determinant term is a core problem in many machine learning settings, and especially so in the normalizing flow framework. Most propo…
SurVAE Flows: Surjections to Bridge the Gap between VAEs and Flows
Didrik Nielsen, Priyank Jaini, Emiel Hoogeboom +2
Normalizing flows and variational autoencoders are powerful generative models that can represent complicated density functions. However, they both impose constraints on the models:…
A Positivstellensatz for Conditional SAGE Signomials
Allen Houze Wang, Priyank Jaini, Yaoliang Yu +1
Recently, the conditional SAGE certificate has been proposed as a sufficient condition for signomial positivity over a convex set. In this article, we show that the conditional SAG…
Tails of Lipschitz Triangular Flows
Priyank Jaini, Ivan Kobyzev, Yaoliang Yu +1
We investigate the ability of popular flow based methods to capture tail-properties of a target density by studying the increasing triangular maps used in these flow methods acting…
Sum-of-Squares Polynomial Flow
Priyank Jaini, Kira A. Selby, Yaoliang Yu
Triangular map is a recent construct in probability theory that allows one to transform any source probability density function to any target density function. Based on triangular…
Online and Distributed learning of Gaussian mixture models by Bayesian Moment Matching
Priyank Jaini, Pascal Poupart
The Gaussian mixture model is a classic technique for clustering and data modeling that is used in numerous applications. With the rise of big data, there is a need for parameter e…