Mikael Henaff

I am a research scientist at Meta AI.

Previously I was a postdoctoral researcher for two years at Microsoft Research NYC.

I received my Ph.D in computer science from the Courant Institute of Mathematical Sciences in 2018, advised by Yann LeCun.

During my Ph.D I interned for several summers at Facebook AI Research.

Before that I worked at the Center for Health Informatics and Bioinformatics at the NYU Medical Center, and completed my M.S. in math at NYU.

Earlier still, I did my undergrad in pure math at the University of Texas at Austin.

CV / Google Scholar / Twitter

Current Research & Interests

Papers

  • OpenEQA: Embodied Question Answering in the Era of Foundation Models
    Arjun Majumdar*, Anurag Ajay*, Xiaohan Zhang*, Pranav Putta, Sriram Yenamandra, Mikael Henaff, Sneha Silwal, Paul Mcvay, Oleksandr Maksymets, Sergio Arnaud, Karmesh Yadav, Qiyang Li, Ben Newman,
    Mohit Sharma, Vincent Berges, Shiqi Zhang, Pulkit Agrawal, Yonatan Bisk, Dhruv Batra, Mrinal Kalakrishnan, Franziska Meier, Chris Paxton, Sasha Sax, Aravind Rajeswaran (CVPR 2024)
    [pdf] [code] [blog post]

  • Motif: Intrinsic Motivation from Artificial Intelligence Feedback
    Martin Klissarov*, Pierluca D'Oro*, Shagun Sodhani, Roberta Raileanu, Pierre-Luc Bacon, Pascal Vincent, Amy Zhang and Mikael Henaff (ICLR 2024)
    [pdf] [code] [blog post]

  • Generalization to New Sequential Decision Making Tasks with In-Context Learning
    Sharath Chandra Raparthy, Eric Hambro, Robert Kirk, Mikael Henaff, Roberta Raileanu (arXiv 2023)
    [pdf]

  • A Study of Global and Episodic Bonuses for Exploration in Contextual MDPs
    Mikael Henaff, Minqi Jiang, Roberta Raileanu (ICML 2023 Oral)
    [pdf] [code]

  • Semi-Supervised Offline Reinforcement Learning with Action-Free Trajectories
    Qinqing Zheng, Mikael Henaff, Brandon Amos, Aditya Grover (ICML 2023)
    [pdf]

  • Exploration via Elliptical Episodic Bonuses
    Mikael Henaff, Roberta Raileanu, Minqi Jiang and Tim Rocktäschel (NeurIPS 2022)
    [pdf] [code]

  • PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning
    Alekh Agarwal*, Mikael Henaff*, Sham Kakade* and Wen Sun* (NeurIPS 2020)
    [pdf] [code]

  • Kinematic State Abstraction and Provably Efficient Rich-Observation Reinforcement Learning
    Dipendra Misra, Mikael Henaff, Akshay Krishnamurthy and John Langford (ICML 2020)
    [pdf (extended version)]

  • Disagreement-Regularized Imitation Learning
    Kianté Brantley, Wen Sun and Mikael Henaff (ICLR 2020 Spotlight)
    [pdf] [code]

  • Explicit Explore-Exploit Algorithms in Continuous State Spaces
    Mikael Henaff (NeurIPS 2019)
    [pdf] [code] [poster]

  • Model-Predictive Policy Learning with Uncertainty Regularization for Driving in Dense Traffic
    Mikael Henaff*, Alfredo Canziani* and Yann LeCun (ICLR 2019)
    [pdf] [code] [project site] [Press (MIT Tech Review)]

  • Model-Based Planning with Discrete and Continuous Actions
    Mikael Henaff, William Whitney and Yann LeCun (arXiv 2018)
    [pdf]

  • Tracking the World State with Recurrent Entity Networks
    Mikael Henaff, Jason Weston, Arthur Szlam, Antoine Bordes and Yann LeCun (ICLR 2017)
    [pdf] [code] [Press (Le Monde)]

  • Recurrent Orthogonal Networks and Long-Memory Tasks
    Mikael Henaff, Arthur Szlam and Yann LeCun (ICML 2016)
    [pdf]

  • Ultra-scalable and efficient methods for hybrid observational and experimental local causal pathway discovery
    Alexander Statnikov, Sisi Ma, Mikael Henaff, Nikita Lytkin, Efstratios Efstathiadis, Eric R Peskin, Constantin F Aliferis (JMLR 2016)
    [pdf]

  • The Loss Surface of Multilayer Networks
    Anna Choromanska, Mikael Henaff, Michael Mathieu, Gerard Ben Arous, Yann LeCun (AISTATS 2015)
    [pdf]

  • Deep Convolutional Networks on Graph-Structured Data
    Mikael Henaff, Joan Bruna and Yann LeCun (arXiv 2015)
    [pdf]

  • Fast Training of Convolutional Networks through FFTs
    Michael Mathieu, Mikael Henaff and Yann LeCun (ICLR 2014)
    [pdf]

  • Information Content and Analysis Methods for Multi-Modal High-Throughput Biomedical Data.
    Bisakha Ray, Mikael Henaff, Sisi Ma, Efstratios Efstathiadis, Eric Peskin, Marco Picone, Tito Poli, Constantin Aliferis and Alexander Statnikov (Nature Scientific Reports, 2014)
    [pdf]

  • Microbiomic Signatures of Psoriasis: Feasibility and Methodology Comparison.
    Alexander Statnikov, Alexander Alekseyenko, Zhiguo Li, Mikael Henaff, Martin Blaser and Constantin Aliferis (Nature Scientific Reports, 2013)
    [pdf]

  • A Comprehensive Evaluation of Multicategory Classification Methods for Microbiomic Data
    Alexander Statnikov, Mikael Henaff, Varun Narendra, Kranti Konganti, Zhiguo Li, Liying Yang, Zhiheng Pei, Martin Blaser, Constantin Aliferis and Alexander Alekseyenko. (Microbiome, 2013)
    [pdf]

  • New Methods for Separating Causes from Effects in Genomic Data
    Alexander Statnikov, Mikael Henaff, Nikita Lytkin and Constantin Aliferis. (BMC Genomics, 2012)
    [pdf]

  • Unsupervised Learning of Sparse Features for Scalable Audio Classification
    Mikael Henaff, Kevin Jarrett, Koray Kavukcuoglu and Yann LeCun (ISMIR 2011)
    [pdf]


    • *equal contribution or alphabetical order

    Contact: mbh305 [at] nyu [dot] edu