Vikram Voleti

2024-03-21

Annals of Mathematics and Artificial Intelligence (publié)

Are Diffusion Models Vision-And-Language Reasoners?

Benno Krojer

Elinor Poole-Dayan

Vikram Voleti

Siva Reddy

Text-conditioned image generation models have recently shown immense qualitative success using denoising diffusion processes. However, unlik… (voir plus)e discriminative vision-and-language models, it is a non-trivial task to subject these diffusion-based generative models to automatic fine-grained quantitative evaluation of high-level phenomena such as compositionality. Towards this goal, we perform two innovations. First, we transform diffusion-based models (in our case, Stable Diffusion) for any image-text matching (ITM) task using a novel method called DiffusionITM. Second, we introduce the Generative-Discriminative Evaluation Benchmark (GDBench) benchmark with 7 complex vision-and-language tasks, bias evaluation and detailed analysis. We find that Stable Diffusion + DiffusionITM is competitive on many tasks and outperforms CLIP on compositional tasks like like CLEVR and Winoground. We further boost its compositional performance with a transfer setup by fine-tuning on MS-COCO while retaining generative capabilities. We also measure the stereotypical bias in diffusion models, and find that Stable Diffusion 2.1 is, for the most part, less biased than Stable Diffusion 1.5. Overall, our results point in an exciting direction bringing discriminative and generative model evaluation closer. We will release code and benchmark setup soon.

Score-based Diffusion Models in Function Space

Jae Hyun Lim

Nikola B. Kovachki

R. Baptista

Christopher Beckham

Kamyar Azizzadenesheli

Jean Kossaifi

Vikram Voleti

Jiaming Song

Karsten Kreis

J. Kautz

Arash Vahdat

Animashree Anandkumar

2023-02-14

ArXiv (prépublication)

Factors Influencing Generalization in Chaotic Dynamical Systems

Luã Streit

Vikram Voleti

Tegan Maharaj

Many real-world systems exhibit chaotic behaviour, for example: weather, fluid dynamics, stock markets, natural ecosystems, and disease tran… (voir plus)smission. While chaotic systems are often thought to be completely unpredictable, in fact there are patterns within and across that experts frequently describe and contrast qualitatively. We hypothesize that given the right supervision / task definition, representation learning systems will be able to pick up on these patterns, and successfully generalize both in- and out-of-distribution (OOD). Thus, this work explores and identifies key factors which lead to good generalization. We observe a variety of interesting phenomena, including: learned representations transfer much better when fine-tuned vs. frozen; forecasting appears to be the best pre-training task; OOD robustness falls off very quickly outside the training distribution; recurrent architectures generally outperform others on OOD generalization. Our findings are of interest to any domain of prediction where chaotic dynamics play a role.

2023-02-01

ICLR.cc/2023/Conference (rejected)

SMPL-IK: Learned Morphology-Aware Inverse Kinematics for AI Driven Artistic Workflows

Vikram Voleti

Boris Oreshkin

Florent Bocquelet

Félix Harvey

Louis-Simon Ménard

2022-11-22

SIGGRAPH Asia 2022 Technical Communications (publié)

Generative Models of Brain Dynamics

Mahta Ramezanian-Panahi

Germán Abrevaya

Jean-Christophe Gagnon-Audet

Vikram Voleti

Irina Rish

Guillaume Dumas

2022-07-15

Frontiers in Artificial Intelligence (publié)

MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation

Vikram Voleti

Alexia Jolicoeur-Martineau

Video prediction is a challenging task. The quality of video frames from current state-of-the-art (SOTA) generative models tends to be poor … (voir plus)and generalization beyond the training data is difficult. Furthermore, existing prediction frameworks are typically not capable of simultaneously handling other video-related tasks such as unconditional generation or interpolation. In this work, we devise a general-purpose framework called Masked Conditional Video Diffusion (MCVD) for all of these video synthesis tasks using a probabilistic conditional score-based denoising diffusion model, conditioned on past and/or future frames. We train the model in a manner where we randomly and independently mask all the past frames or all the future frames. This novel but straightforward setup allows us to train a single model that is capable of executing a broad range of video tasks, specifically: future/past prediction -- when only future/past frames are masked; unconditional generation -- when both past and future frames are masked; and interpolation -- when neither past nor future frames are masked. Our experiments show that this approach can generate high-quality frames for diverse types of videos. Our MCVD models are built from simple non-recurrent 2D-convolutional architectures, conditioning on blocks of frames and generating blocks of frames. We generate videos of arbitrary lengths autoregressively in a block-wise manner. Our approach yields SOTA results across standard video prediction and interpolation benchmarks, with computation times for training models measured in 1-12 days using

Generative Models of Brain Dynamics -- A review

Mahta Ramezanian Panahi

Germán Abrevaya

Jean-Christophe Gagnon-Audet

Vikram Voleti

Irina Rish

Guillaume Dumas

The principled design and discovery of biologically- and physically-informed models of neuronal dynamics has been advancing since the mid-tw… (voir plus)entieth century. Recent developments in artificial intelligence (AI) have accelerated this progress. This review article gives a high-level overview of the approaches across different scales of organization and levels of abstraction. The studies covered in this paper include fundamental models in computational neuroscience, nonlinear dynamics, data-driven methods, as well as emergent practices. While not all of these models span the intersection of neuroscience, AI, and system dynamics, all of them do or can work in tandem as generative models, which, as we argue, provide superior properties for the analysis of neuroscientific data. We discuss the limitations and unique dynamical traits of brain data and the complementary need for hypothesis- and data-driven modeling. By way of conclusion, we present several hybrid generative models from recent literature in scientific machine learning, which can be efficiently deployed to yield interpretable models of neural dynamics.

2021-12-22

ArXiv (prépublication)

Accounting for Variance in Machine Learning Benchmarks

Xavier Bouthillier

Pierre Delaunay

Mirko Bronzi

Assya Trofimov

Brennan Nichyporuk

Justin Szeto

Naz Sepah

Edward Raff

Kanika Madan

Vikram Voleti

Samira Ebrahimi Kahou

Vincent Michalski

Dmitriy Serdyuk

Tal Arbel

Gael Varoquaux

Pascal Vincent

Strong empirical evidence that one machine-learning algorithm A outperforms another one B ideally calls for multiple trials optimizing the l… (voir plus)earning pipeline over sources of variation such as data sampling, data augmentation, parameter initialization, and hyperparameters choices. This is prohibitively expensive, and corners are cut to reach conclusions. We model the whole benchmarking process, revealing that variance due to data sampling, parameter initialization and hyperparameter choice impact markedly the results. We analyze the predominant comparison methods used today in the light of this variance. We show a counter-intuitive result that adding more sources of variation to an imperfect estimator approaches better the ideal estimator at a 51 times reduction in compute cost. Building on these results, we study the error rate of detecting improvements, on five different deep-learning tasks/architectures. This study leads us to propose recommendations for performance comparisons.

2021-01-01

MLSys (publié)