Ferran Alet

I am a PhD student at MIT CSAIL, where I work on machine learning and robotics advised by Leslie Kaelbling and Tomas Lozano-Perez, and meeting regularly with Josh Tenenbaum. I am also the organizer of the MIT Embodied Intelligence Seminar. Currently mentoring Giray Kuru, Max Thomsen (with Maria Bauza), Katie Wu (with Yilun Du), Javier Lopez-Contreras and Jan Olivetti.

Past mentees: Martin Schneider(now PhD at MIT), Erica Weng(now PhD at CMU), Edgar Gonzalez, Patrick John Chia , ShengTong Zhang, Margaret Wang, Scott Perry, Catherine Zeng, Adarsh Keshav Jeewajee and Paolo Gentili.

Twitter  /  Email  /  CV  /  Google Scholar  /  LinkedIn

profile photo

How do we make machines that invent new algorithms, design novel molecules or achieve goals on their first attempt? I am interested in using machine learning models for robustly designing and achieving novel things. Most ML algorithms generalize well within their training distribution, but are not robust once we extrapolate beyond it. One possible approach is to leverage priors from similar tasks or concepts, i.e. meta-learning, which broadens the training distribution to a meta-distribution that includes other tasks. I also work on leveraging combinatorial generalization, reusing learned concepts in novel ways, to exponentially increase the generalization capabilities of current methods. Finally, I search general paradigms for encoding inductive biases, to help networks generalize in more robust, interpretable, meaningful ways.

Invited talks

Representative papers are highlighted.

Tailoring: encoding inductive biases by optimizing unsupervised objectives at prediction time
Ferran Alet , Kenji Kawaguchi, Maria Bauza, Nurullah Giray Kuru, Tomás Lozano-Pérez, Leslie Pack Kaelbling
spotlight at the NeurIPS Interpretable Inductive Biases and Physically Structured Learning workshop; submitted to ICLR '21,

During prediction we can optimize any loss that depends only on the input, allowing us to encode inductive biases in the form of losses and train models to do well after fine-tuning on the unsupervised loss. We show its breadth of applicability on contrastive learning, physics and adversarial examples.

Meta-learning curiosity algorithms
Ferran Alet* , Martin Schneider*, Tomás Lozano-Pérez, Leslie Pack Kaelbling
ICLR, 2020; NeurIPS meta-learning and reinforcement learning workshops, 2019
code / report explaining discovered algorithms / video Press: VentureBeat | MIT news

By meta-learning program-like structures instead of neural network weights, we can increase meta-learning generalization. We discover new algorithms in simple environments that generalize to completely new complex domains.

Neural Relational Inference with Fast Modular Meta-learning
Ferran Alet , Erica Weng, Tomás Lozano-Pérez, Leslie Pack Kaelbling
NeurIPS, 2019  

We frame neural relational inference as a case of modular meta-learning and speed up the original modular meta-learning algorithms by two orders of magnitude, making them practical.

Omnipush: accurate, diverse, real-world dataset of pushing dynamics with RGB-D video
Maria Bauza, Ferran Alet Yen-Chen Lin, Tomás Lozano-Pérez, Leslie Pack Kaelbling, Phillip Isola, Alberto Rodriguez
IROS, 2019
project website / code / data / press

Diverse dataset of 250 objects pushed 250 times each, all with RGB-D video. First probabilistic meta-learning benchmark.

Graph Element Networks: adaptive, structured computation and memory
Ferran Alet , Adarsh K. Jeewajee, Maria Bauza, Alberto Rodriguez, Tomás Lozano-Pérez, Leslie Pack Kaelbling
ICML, 2019   (Long talk)
talk/ code

We learn to map functions to functions by combining graph networks and attention to build computational meshes and show this new framework can solve very diverse problems.

Modular meta-learning
Ferran Alet , Tomás Lozano-Pérez, Leslie Pack Kaelbling
CoRL, 2018  
video/ code

We propose to do meta-learning by training a set of neural networks to be composable, adapting to new tasks by composing modules in novel ways, similar to how we compose known words to express novel ideas.

Finding Frequent Entities in Continuous Data
Ferran Alet , Rohan Chitnis, Tomás Lozano-Pérez, Leslie Pack Kaelbling
IJCAI, 2018  

People often find entities by clustering; we suggest that, instead, entities can be described as dense regions and propose a very simple algorithm for detecting them, with provable guarantees.

Robotic Pick-and-Place of Novel Objects in Clutter with Multi-Affordance Grasping and Cross-Domain Image Matching
Andy Zeng et al.
IROS, 2018  
talk/ project website

Description of the system for the Amazon Robotics Challenge 2017 competition, in which we won the stowing task.