Machine Learning
Data-driven approaches to design intelligent algorithms.
MERL has a long history of research activity in machine learning, including the development of various boosting algorithms and contributing to the theory and practice of highly scalable collaborative filtering. Our recent work has focused on deep learning and reinforcement learning, with application to a wide range of applications including automotive, robotics, factory automation, transportation, as well as building and home systems.
Quick Links
-
Researchers
Toshiaki
Koike-Akino
Ye
Wang
Jonathan
Le Roux
Ankush
Chakrabarty
Anoop
Cherian
Gordon
Wichern
Tim K.
Marks
Michael J.
Jones
Philip V.
Orlik
Stefano
Di Cairano
Daniel N.
Nikovski
Kieran
Parsons
Christopher R.
Laughman
Devesh K.
Jha
Diego
Romeres
Pu
(Perry)
WangKarl
Berntorp
Chiori
Hori
Bingnan
Wang
Yebin
Wang
Mouhacine
Benosman
Suhas
Lohit
Hassan
Mansour
Matthew
Brand
Petros T.
Boufounos
Arvind
Raghunathan
Moitreya
Chatterjee
Abraham P.
Vinod
Jianlin
Guo
Siddarth
Jain
Kuan-Chuan
Peng
Scott A.
Bortoff
Vedang M.
Deshpande
Jing
Liu
Hongtao
Qiao
William S.
Yerazunis
Radu
Corcodel
François
Germain
Chungwei
Lin
Saviz
Mowlavi
Dehong
Liu
Pedro
Miraldo
Hongbo
Sun
Wataru
Tsujita
Sameer
Khurana
James
Queeney
Ryo
Aihara
Yanting
Ma
Anthony
Vetro
Jinyun
Zhang
Jose
Amaya
Purnanand
Elango
Abraham
Goldsmith
Joshua
Rapp
Alexander
Schperberg
Avishai
Weiss
Janek
Ebbers
-
Awards
-
AWARD MERL team wins the Listener Acoustic Personalisation (LAP) 2024 Challenge Date: August 29, 2024
Awarded to: Yoshiki Masuyama, Gordon Wichern, Francois G. Germain, Christopher Ick, and Jonathan Le Roux
MERL Contacts: François Germain; Jonathan Le Roux; Gordon Wichern
Research Areas: Artificial Intelligence, Machine Learning, Speech & AudioBrief- MERL's Speech & Audio team ranked 1st out of 7 teams in Task 2 of the 1st SONICOM Listener Acoustic Personalisation (LAP) Challenge, which focused on "Spatial upsampling for obtaining a high-spatial-resolution HRTF from a very low number of directions". The team was led by Yoshiki Masuyama, and also included Gordon Wichern, Francois Germain, MERL intern Christopher Ick, and Jonathan Le Roux.
The LAP Challenge workshop and award ceremony was hosted by the 32nd European Signal Processing Conference (EUSIPCO 24) on August 29, 2024 in Lyon, France. Yoshiki Masuyama presented the team's method, "Retrieval-Augmented Neural Field for HRTF Upsampling and Personalization", and received the award from Prof. Michele Geronazzo (University of Padova, IT, and Imperial College London, UK), Chair of the Challenge's Organizing Committee.
The LAP challenge aims to explore challenges in the field of personalized spatial audio, with the first edition focusing on the spatial upsampling and interpolation of head-related transfer functions (HRTFs). HRTFs with dense spatial grids are required for immersive audio experiences, but their recording is time-consuming. Although HRTF spatial upsampling has recently shown remarkable progress with approaches involving neural fields, HRTF estimation accuracy remains limited when upsampling from only a few measured directions, e.g., 3 or 5 measurements. The MERL team tackled this problem by proposing a retrieval-augmented neural field (RANF). RANF retrieves a subject whose HRTFs are close to those of the target subject at the measured directions from a library of subjects. The HRTF of the retrieved subject at the target direction is fed into the neural field in addition to the desired sound source direction. The team also developed a neural network architecture that can handle an arbitrary number of retrieved subjects, inspired by a multi-channel processing technique called transform-average-concatenate.
- MERL's Speech & Audio team ranked 1st out of 7 teams in Task 2 of the 1st SONICOM Listener Acoustic Personalisation (LAP) Challenge, which focused on "Spatial upsampling for obtaining a high-spatial-resolution HRTF from a very low number of directions". The team was led by Yoshiki Masuyama, and also included Gordon Wichern, Francois Germain, MERL intern Christopher Ick, and Jonathan Le Roux.
-
AWARD Jonathan Le Roux elevated to IEEE Fellow Date: January 1, 2024
Awarded to: Jonathan Le Roux
MERL Contact: Jonathan Le Roux
Research Areas: Artificial Intelligence, Machine Learning, Speech & AudioBrief- MERL Distinguished Scientist and Speech & Audio Senior Team Leader Jonathan Le Roux has been elevated to IEEE Fellow, effective January 2024, "for contributions to multi-source speech and audio processing."
Mitsubishi Electric celebrated Dr. Le Roux's elevation and that of another researcher from the company, Dr. Shumpei Kameyama, with a worldwide news release on February 15.
Dr. Jonathan Le Roux has made fundamental contributions to the field of multi-speaker speech processing, especially to the areas of speech separation and multi-speaker end-to-end automatic speech recognition (ASR). His contributions constituted a major advance in realizing a practically usable solution to the cocktail party problem, enabling machines to replicate humans’ ability to concentrate on a specific sound source, such as a certain speaker within a complex acoustic scene—a long-standing challenge in the speech signal processing community. Additionally, he has made key contributions to the measures used for training and evaluating audio source separation methods, developing several new objective functions to improve the training of deep neural networks for speech enhancement, and analyzing the impact of metrics used to evaluate the signal reconstruction quality. Dr. Le Roux’s technical contributions have been crucial in promoting the widespread adoption of multi-speaker separation and end-to-end ASR technologies across various applications, including smart speakers, teleconferencing systems, hearables, and mobile devices.
IEEE Fellow is the highest grade of membership of the IEEE. It honors members with an outstanding record of technical achievements, contributing importantly to the advancement or application of engineering, science and technology, and bringing significant value to society. Each year, following a rigorous evaluation procedure, the IEEE Fellow Committee recommends a select group of recipients for elevation to IEEE Fellow. Less than 0.1% of voting members are selected annually for this member grade elevation.
- MERL Distinguished Scientist and Speech & Audio Senior Team Leader Jonathan Le Roux has been elevated to IEEE Fellow, effective January 2024, "for contributions to multi-source speech and audio processing."
-
AWARD Honorable Mention Award at NeurIPS 23 Instruction Workshop Date: December 15, 2023
Awarded to: Lingfeng Sun, Devesh K. Jha, Chiori Hori, Siddharth Jain, Radu Corcodel, Xinghao Zhu, Masayoshi Tomizuka and Diego Romeres
MERL Contacts: Radu Corcodel; Chiori Hori; Siddarth Jain; Devesh K. Jha; Diego Romeres
Research Areas: Artificial Intelligence, Machine Learning, RoboticsBrief- MERL Researchers received an "Honorable Mention award" at the Workshop on Instruction Tuning and Instruction Following at the NeurIPS 2023 conference in New Orleans. The workshop was on the topic of instruction tuning and Instruction following for Large Language Models (LLMs). MERL researchers presented their work on interactive planning using LLMs for partially observable robotic tasks during the oral presentation session at the workshop.
See All Awards for Machine Learning -
-
News & Events
-
TALK [MERL Seminar Series 2024] Tom Griffiths presents talk titled Tools from cognitive science to understand the behavior of large language models Date & Time: Wednesday, September 18, 2024; 1:00 PM
Speaker: Tom Griffiths, Princeton University
MERL Host: Mouhacine Benosman
Research Areas: Artificial Intelligence, Data Analytics, Machine Learning, Human-Computer InteractionAbstract- Large language models have been found to have surprising capabilities, even what have been called “sparks of artificial general intelligence.” However, understanding these models involves some significant challenges: their internal structure is extremely complicated, their training data is often opaque, and getting access to the underlying mechanisms is becoming increasingly difficult. As a consequence, researchers often have to resort to studying these systems based on their behavior. This situation is, of course, one that cognitive scientists are very familiar with — human brains are complicated systems trained on opaque data and typically difficult to study mechanistically. In this talk I will summarize some of the tools of cognitive science that are useful for understanding the behavior of large language models. Specifically, I will talk about how thinking about different levels of analysis (and Bayesian inference) can help us understand some behaviors that don’t seem particularly intelligent, how tasks like similarity judgment can be used to probe internal representations, how axiom violations can reveal interesting mechanisms, and how associations can reveal biases in systems that have been trained to be unbiased.
-
NEWS MERL researchers present 9 papers at ACC 2024 Date: July 10, 2024 - July 12, 2024
Where: Toronto, Canada
MERL Contacts: Karl Berntorp; Ankush Chakrabarty; Vedang M. Deshpande; Stefano Di Cairano; Christopher R. Laughman; Arvind Raghunathan; Abraham P. Vinod; Yebin Wang; Avishai Weiss
Research Areas: Artificial Intelligence, Control, Dynamical Systems, Machine Learning, Multi-Physical Modeling, Optimization, RoboticsBrief- MERL researchers presented 9 papers at the recently concluded American Control Conference (ACC) 2024 in Toronto, Canada. The papers covered a wide range of topics including data-driven spatial monitoring using heterogenous robots, aircraft approach management near airports, computation fluid dynamics-based motion planning for drones facing winds, trajectory planning for coordinated monitoring using a team of drones and a ground carrier vehicle, ensemble Kalman smoothing-based model predictive control for motion planning for autonomous vehicles, system identification for Lithium-ion batteries, physics-constrained deep Kalman filters for vapor compression systems, switched reference governors for constrained systems, and distributed road-map monitoring using onboard sensors.
As a sponsor of the conference, MERL maintained a booth for open discussions with researchers and students, and hosted a special session to discuss highlights of MERL research and work philosophy.
In addition, Abraham Vinod served as a panelist at the Student Networking Event at the conference. The student networking event provides an opportunity for all interested students to network with professionals working in industry, academia, and national laboratories during a structured event, and encourages their continued participation as the future leaders in the field.
- MERL researchers presented 9 papers at the recently concluded American Control Conference (ACC) 2024 in Toronto, Canada. The papers covered a wide range of topics including data-driven spatial monitoring using heterogenous robots, aircraft approach management near airports, computation fluid dynamics-based motion planning for drones facing winds, trajectory planning for coordinated monitoring using a team of drones and a ground carrier vehicle, ensemble Kalman smoothing-based model predictive control for motion planning for autonomous vehicles, system identification for Lithium-ion batteries, physics-constrained deep Kalman filters for vapor compression systems, switched reference governors for constrained systems, and distributed road-map monitoring using onboard sensors.
See All News & Events for Machine Learning -
-
Research Highlights
-
PS-NeuS: A Probability-guided Sampler for Neural Implicit Surface Rendering -
TI2V-Zero: Zero-Shot Image Conditioning for Text-to-Video Diffusion Models -
Gear-NeRF: Free-Viewpoint Rendering and Tracking with Motion-Aware Spatio-Temporal Sampling -
Steered Diffusion -
Edge-Assisted Internet of Vehicles for Smart Mobility -
Robust Machine Learning -
mmWave Beam-SNR Fingerprinting (mmBSF) -
Video Anomaly Detection -
Biosignal Processing for Human-Machine Interaction -
MERL Shopping Dataset
-
-
Internships
-
SA0044: Internship - Multimodal scene-understanding
We are looking for a graduate student interested in helping advance the field of multimodal scene understanding, focusing on scene understanding using natural language for robot dialog and/or indoor monitoring using a large language model. The intern will collaborate with MERL researchers to derive and implement new models and optimization methods, conduct experiments, and prepare results for publication. Internships regularly lead to one or more publications in top-tier venues, which can later become part of the intern''''s doctoral work. The ideal candidates are senior Ph.D. students with experience in deep learning for audio-visual, signal, and natural language processing. Good programming skills in Python and knowledge of deep learning frameworks such as PyTorch are essential. Multiple positions are available with flexible start date (not just Spring/Summer but throughout 2024) and duration (typically 3-6 months).
-
SA0040: Internship - Sound event and anomaly detection
We are seeking graduate students interested in helping advance the fields of sound event detection/localization, anomaly detection, and physics informed deep learning for machine sounds. The interns will collaborate with MERL researchers to derive and implement novel algorithms, record data, conduct experiments, integrate audio signals with other sensors (electrical, vision, vibration, etc.), and prepare results for publication. Internships regularly lead to one or more publications in top-tier venues, which can later become part of the intern's doctoral work. The ideal candidates are senior Ph.D. students with experience in some of the following: audio signal processing, microphone array processing, physics informed machine learning, outlier detection, and unsupervised learning. Multiple positions are available with flexible start dates (not just Spring/Summer but throughout 2025) and duration (typically 3-6 months).
-
SA0041: Internship - Audio separation, generation, and analysis
We are seeking graduate students interested in helping advance the fields of generative audio, source separation, speech enhancement, spatial audio, and robust ASR in challenging multi-source and far-field scenarios. The interns will collaborate with MERL researchers to derive and implement new models and optimization methods, conduct experiments, and prepare results for publication. Internships regularly lead to one or more publications in top-tier venues, which can later become part of the intern's doctoral work. The ideal candidates are senior Ph.D. students with experience in some of the following: audio signal processing, microphone array processing, spatial audio reproduction, probabilistic modeling, deep generative modeling, and physics informed machine learning techniques (e.g., neural fields, PINNs, sound field and reverberation modeling). Multiple positions are available with flexible start dates (not just Spring/Summer but throughout 2025) and duration (typically 3-6 months).
See All Internships for Machine Learning -
-
Openings
See All Openings at MERL -
Recent Publications
- "Decentralized, Safe, Multi-agent Motion Planning for Drones Under Uncertainty via Filtered Reinforcement Learning", IEEE Transactions on Control Systems Technology, January 2025.BibTeX TR2024-136 PDF
- @article{Vinod2025jan,
- author = {Vinod, Abraham P. and Safaoui, Sleiman and Summers, Tyler and Yoshikawa, Nobuyuki and Di Cairano, Stefano}},
- title = {Decentralized, Safe, Multi-agent Motion Planning for Drones Under Uncertainty via Filtered Reinforcement Learning},
- journal = {IEEE Transactions on Control Systems Technology},
- year = 2025,
- month = jan,
- url = {https://www.merl.com/publications/TR2024-136}
- }
, - "Integrating Generative Machine Learning Models and Physics-Based Models for Building Energy Simulation", American Modelica Conference, October 2024.BibTeX TR2024-140 PDF
- @inproceedings{Vanfretti2024oct,
- author = {Vanfretti, Luigi and Laughman, Christopher R. and Chakrabarty, Ankush}},
- title = {Integrating Generative Machine Learning Models and Physics-Based Models for Building Energy Simulation},
- booktitle = {American Modelica Conference},
- year = 2024,
- month = oct,
- url = {https://www.merl.com/publications/TR2024-140}
- }
, - "Reinforcement Learning-Based Estimation for Spatio-Temporal Systems", Nature Scientific Reports, DOI: 10.1038/s41598-024-72055-1, Vol. 14, pp. 22464, October 2024.BibTeX TR2024-134 PDF
- @article{Mowlavi2024oct,
- author = {Mowlavi, Saviz and Benosman, Mouhacine}},
- title = {Reinforcement Learning-Based Estimation for Spatio-Temporal Systems},
- journal = {Nature Scientific Reports},
- year = 2024,
- volume = 14,
- pages = 22464,
- month = oct,
- doi = {10.1038/s41598-024-72055-1},
- url = {https://www.merl.com/publications/TR2024-134}
- }
, - "ROSE-Opt: Robust and Efficient Analog Circuit Parameter Optimization with Knowledge-infused Reinforcement Learning", IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, September 2024.BibTeX TR2024-132 PDF
- @article{Cao2024sep,
- author = {Cao, Weidong and Gao, Jian and Ma, Tianrui and Ma, Rui and Benosman, Mouhacine and Zhang, Xuan}},
- title = {ROSE-Opt: Robust and Efficient Analog Circuit Parameter Optimization with Knowledge-infused Reinforcement Learning},
- journal = {IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems},
- year = 2024,
- month = sep,
- url = {https://www.merl.com/publications/TR2024-132}
- }
, - "Equivariant Spatio-Temporal Self-Supervision for LiDAR Object Detection", European Conference on Computer Vision (ECCV), September 2024.BibTeX TR2024-130 PDF Video Presentation
- @inproceedings{Hegde2024sep,
- author = {{Hegde, Deepti and Lohit, Suhas and Peng, Kuan-Chuan and Jones, Michael J. and Patel, Vishal M.}},
- title = {Equivariant Spatio-Temporal Self-Supervision for LiDAR Object Detection},
- booktitle = {European Conference on Computer Vision (ECCV)},
- year = 2024,
- month = sep,
- url = {https://www.merl.com/publications/TR2024-130}
- }
, - "A Probability-guided Sampler for Neural Implicit Surface Rendering", European Conference on Computer Vision (ECCV), September 2024.BibTeX TR2024-129 PDF
- @inproceedings{Pais2024sep,
- author = {Pais, Goncalo and Piedade, Valter and Chatterjee, Moitreya and Greiff, Marcus and Miraldo, Pedro}},
- title = {A Probability-guided Sampler for Neural Implicit Surface Rendering},
- booktitle = {European Conference on Computer Vision (ECCV)},
- year = 2024,
- month = sep,
- url = {https://www.merl.com/publications/TR2024-129}
- }
, - "Few-shot Transparent Instance Segmentation for Bin Picking", IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), September 2024.BibTeX TR2024-127 PDF
- @inproceedings{Cherian2024sep,
- author = {Cherian, Anoop and Jain, Siddarth and Marks, Tim K.}},
- title = {Few-shot Transparent Instance Segmentation for Bin Picking},
- booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
- year = 2024,
- month = sep,
- url = {https://www.merl.com/publications/TR2024-127}
- }
, - "Disentangled Acoustic Fields For Multimodal Physical Scene Understanding", IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), September 2024.BibTeX TR2024-125 PDF
- @inproceedings{Yin2024sep,
- author = {Yin, Jie and Luo, Andrew and Du, Yilun and Cherian, Anoop and Marks, Tim K. and Le Roux, Jonathan and Gan, Chuang}},
- title = {Disentangled Acoustic Fields For Multimodal Physical Scene Understanding},
- booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
- year = 2024,
- month = sep,
- url = {https://www.merl.com/publications/TR2024-125}
- }
,
- "Decentralized, Safe, Multi-agent Motion Planning for Drones Under Uncertainty via Filtered Reinforcement Learning", IEEE Transactions on Control Systems Technology, January 2025.
-
Videos
-
Software & Data Downloads
-
DeepBornFNO -
ComplexVAD Dataset -
Millimeter-wave Multi-View Radar Dataset -
Gear Extensions of Neural Radiance Fields -
Long-Tailed Anomaly Detection (LTAD) Dataset -
Target-Speaker SEParation -
Pixel-Grounded Prototypical Part Networks -
Steered Diffusion -
BAyesian Network for adaptive SAmple Consensus -
Simple Multimodal Algorithmic Reasoning Task Dataset -
Partial Group Convolutional Neural Networks -
SOurce-free Cross-modal KnowledgE Transfer -
Audio-Visual-Language Embodied Navigation in 3D Environments -
Nonparametric Score Estimators -
3D MOrphable STyleGAN -
Instance Segmentation GAN -
Audio Visual Scene-Graph Segmentor -
Generalized One-class Discriminative Subspaces -
Hierarchical Musical Instrument Separation -
Generating Visual Dynamics from Sound and Context -
Adversarially-Contrastive Optimal Transport -
Online Feature Extractor Network -
MotionNet -
FoldingNet++ -
Quasi-Newton Trust Region Policy Optimization -
Landmarks’ Location, Uncertainty, and Visibility Likelihood -
Robust Iterative Data Estimation -
Gradient-based Nikaido-Isoda -
Circular Maze Environment -
Discriminative Subspace Pooling -
Kernel Correlation Network -
Fast Resampling on Point Clouds via Graphs -
FoldingNet -
Deep Category-Aware Semantic Edge Detection -
MERL Shopping Dataset
-