Portrait de Michael Rabbat n'est pas disponible

Michael Rabbat

Membre industriel associé
Professeur associé, McGill University, Département de génie électrique et informatique
Chercheur scientifique, Facebook AI Research
Sujets de recherche
Apprentissage de représentations
Optimisation
Systèmes distribués

Biographie

Mike Rabbat est membre affilié de Mila – Institut québécois d’intelligence artificielle et directeur de la recherche scientifique au sein de l'équipe FAIR (Fundamental AI Research) de Meta. Ses recherches portent sur l'apprentissage efficace et robuste des représentations, en particulier l'apprentissage autosupervisé. Il s'intéresse également à l'optimisation pour un apprentissage efficace des modèles.

Publications

Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces
DiJia Su
Sainbayar Sukhbaatar
Yuandong Tian
Qinqing Zheng
In human cognition theory, human thinking is governed by two systems: the fast and intuitive System 1 and the slower but more deliberative S… (voir plus)ystem 2. Recent studies have shown that incorporating System 2 process into Transformers including large language models (LLMs), significantly enhances their reasoning capabilities. Nevertheless, models that purely resemble System 2 thinking require substantially higher computational costs and are much slower to respond. To address this challenge, we present Dualformer, a single Transformer model that seamlessly integrates both the fast and slow reasoning modes. Dualformer is obtained by training on data with randomized reasoning traces, where different parts of the traces are dropped during training. The dropping strategies are specifically tailored according to the trace structure, analogous to analyzing our thinking process and creating shortcuts with patterns. At inference time, our model can be configured to output only the solutions (fast mode) or both the reasoning chain and the final solution (slow mode), or automatically decide which mode to engage (auto mode). In all cases, Dualformer outperforms the corresponding baseline models in both performance and computational efficiency: (1) in slow mode, Dualformer optimally solves unseen 30 x 30 maze navigation tasks 97.6% of the time, surpassing the Searchformer (trained on data with complete reasoning traces) baseline performance of 93.3%, while only using 45.5% fewer reasoning steps; (2) in fast mode, Dualformer completes those tasks with an 80% optimal rate, significantly outperforming the Solution-Only model (trained on solution-only data), which has an optimal rate of only 30%. For math problems, our techniques have also achieved improved performance with LLM fine-tuning, showing its generalization beyond task-specific models.
The Factorization Curse: Which Tokens You Predict Underlie the Reversal Curse and More
Ouail Kitouni
Niklas Nolte
Adina Williams
Diane Bouchacourt
Mark Ibrahim
Revisiting Feature Prediction for Learning Visual Representations from Video
Adrien Bardes
Quentin Garrido
Jean Ponce
Xinlei Chen
Yann LeCun
Mahmoud Assran
Nicolas Ballas
Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrapping
Lucas Lehnert
Sainbayar Sukhbaatar
DiJia Su
Paul McVay
Qinqing Zheng
Yuandong Tian
While Transformers have enabled tremendous progress in various application settings, such architectures still lag behind traditional symboli… (voir plus)c planners for solving complex decision making tasks. In this work, we demonstrate how to train Transformers to solve complex planning tasks. This is accomplished by training an encoder-decoder Transformer model to predict the _search dynamics_ of the
DP-RDM: Adapting Diffusion Models to Private Domains Without Fine-Tuning
Jonathan Lebensold
Maziar Sanjabi
Pietro Astolfi
Kamalika Chaudhuri
Chuan Guo
Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrapping
Lucas Lehnert
Sainbayar Sukhbaatar
Paul McVay
Yuandong Tian
While Transformers have enabled tremendous progress in various application settings, such architectures still trail behind traditional symbo… (voir plus)lic planners for solving complex decision making tasks. In this work, we demonstrate how to train Transformers to solve complex planning tasks. This is accomplished by training an encoder-decoder Transformer model to predict the search dynamics of the
Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrapping
Lucas Lehnert
Sainbayar Sukhbaatar
Paul McVay
Yuandong Tian
While Transformers have enabled tremendous progress in various application settings, such architectures still trail behind traditional symbo… (voir plus)lic planners for solving complex decision making tasks. In this work, we demonstrate how to train Transformers to solve complex planning tasks. This is accomplished by training an encoder-decoder Transformer model to predict the search dynamics of the
Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrapping
Lucas Lehnert
Sainbayar Sukhbaatar
Paul McVay
Yuandong Tian
While Transformers have enabled tremendous progress in various application settings, such architectures still lag behind traditional symboli… (voir plus)c planners for solving complex decision making tasks. In this work, we demonstrate how to train Transformers to solve complex planning tasks and present Searchformer, a Transformer model that optimally solves previously unseen Sokoban puzzles 93.7% of the time, while using up to 26.8% fewer search steps than standard
Revisiting Feature Prediction for Learning Visual Representations from Video
Adrien Bardes
Quentin Garrido
Jean Ponce
Xinlei Chen
Yann LeCun
Mahmoud Assran
Nicolas Ballas
This paper explores feature prediction as a stand-alone objective for unsupervised learning from video and introduces V-JEPA, a collection o… (voir plus)f vision models trained solely using a feature prediction objective, without the use of pretrained image encoders, text, negative examples, reconstruction, or other sources of supervision. The models are trained on 2 million videos collected from public datasets and are evaluated on downstream image and video tasks. Our results show that learning by predicting video features leads to versatile visual representations that perform well on both motion and appearance-based tasks, without adaption of the model's parameters; e.g., using a frozen backbone. Our largest model, a ViT-H/16 trained only on videos, obtains 81.9% on Kinetics-400, 72.2% on Something-Something-v2, and 77.9% on ImageNet1K.
Revisiting Feature Prediction for Learning Visual Representations from Video
Adrien Bardes
Quentin Garrido
Jean Ponce
Xinlei Chen
Yann LeCun
Mahmoud Assran
Nicolas Ballas
This paper explores feature prediction as a stand-alone objective for unsupervised learning from video and introduces V-JEPA, a collection o… (voir plus)f vision models trained solely using a feature prediction objective, without the use of pretrained image encoders, text, negative examples, reconstruction, or other sources of supervision. The models are trained on 2 million videos collected from public datasets and are evaluated on downstream image and video tasks. Our results show that learning by predicting video features leads to versatile visual representations that perform well on both motion and appearance-based tasks, without adaption of the model's parameters; e.g., using a frozen backbone. Our largest model, a ViT-H/16 trained only on videos, obtains 81.9% on Kinetics-400, 72.2% on Something-Something-v2, and 77.9% on ImageNet1K.
DINOv2: Learning Robust Visual Features without Supervision
Maxime Oquab
Timothée Darcet
Théo Moutakanni
Huy V. Vo
Marc Szafraniec
Vasil Khalidov
Pierre Fernandez
Daniel HAZIZA
Francisco Massa
Alaaeldin El-Nouby
Mahmoud Assran
Nicolas Ballas
Wojciech Galuba
Russell Howes
Po-Yao Huang
Shang-Wen Li
Ishan Misra
Vasu Sharma
Gabriel Synnaeve … (voir 8 de plus)
Hu Xu 0001
Hu Xu
Huijiao Xu
Herve Jegou
Julien Mairal
Patrick Labatut
Armand Joulin
Piotr Bojanowski
The recent breakthroughs in natural language processing for model pretraining on large quantities of data have opened the way for similar fo… (voir plus)undation models in computer vision. These models could greatly simplify the use of images in any system by producing all-purpose visual features, i.e., features that work across image distributions and tasks without finetuning. This work shows that existing pretraining methods, especially self-supervised methods, can produce such features if trained on enough curated data from diverse sources. We revisit existing approaches and combine different techniques to scale our pretraining in terms of data and model size. Most of the technical contributions aim at accelerating and stabilizing the training at scale. In terms of data, we propose an automatic pipeline to build a dedicated, diverse, and curated image dataset instead of uncurated data, as typically done in the self-supervised literature. In terms of models, we train a ViT model with 1B parameters and distill it into a series of smaller models that surpass the best available all-purpose features, OpenCLIP on most of the benchmarks at image and pixel levels.
A Distributed Data-Parallel PyTorch Implementation of the Distributed Shampoo Optimizer for Training Neural Networks At-Scale
Hao-Jun Michael Shi
Tsung-Hsien Lee
Shintaro Iwasaki
Jose Gallego-Posada
Zhijing Li
Kaushik Rangadurai
Dheevatsa Mudigere