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
Kieran
Parsons
Stefano
Di Cairano
Christopher R.
Laughman
Daniel N.
Nikovski
Pu
(Perry)
WangDevesh K.
Jha
Diego
Romeres
Chiori
Hori
Suhas
Lohit
Bingnan
Wang
Jing
Liu
Yebin
Wang
Hassan
Mansour
Petros T.
Boufounos
Matthew
Brand
François
Germain
Moitreya
Chatterjee
Arvind
Raghunathan
Kuan-Chuan
Peng
Abraham P.
Vinod
Vedang M.
Deshpande
Jianlin
Guo
Siddarth
Jain
Scott A.
Bortoff
Pedro
Miraldo
Hongtao
Qiao
William S.
Yerazunis
Radu
Corcodel
Chungwei
Lin
Saviz
Mowlavi
Dehong
Liu
Yoshiki
Masuyama
Hongbo
Sun
Wataru
Tsujita
Joshua
Rapp
Ryo
Aihara
Yanting
Ma
Anthony
Vetro
Jinyun
Zhang
Wael H.
Ali
Purnanand
Elango
Abraham
Goldsmith
Alexander
Schperberg
Avishai
Weiss
Kenji
Inomata
-
Awards
-
AWARD MERL Wins Awards at NeurIPS LLM Privacy Challenge Date: December 15, 2024
Awarded to: Jing Liu, Ye Wang, Toshiaki Koike-Akino, Tsunato Nakai, Kento Oonishi, Takuya Higashi
MERL Contacts: Toshiaki Koike-Akino; Jing Liu; Ye Wang
Research Areas: Artificial Intelligence, Machine Learning, Information SecurityBrief- The Mitsubishi Electric Privacy Enhancing Technologies (MEL-PETs) team, consisting of a collaboration of MERL and Mitsubishi Electric researchers, won awards at the NeurIPS 2024 Large Language Model (LLM) Privacy Challenge. In the Blue Team track of the challenge, we won the 3rd Place Award, and in the Red Team track, we won the Special Award for Practical Attack.
-
AWARD University of Padua and MERL team wins the AI Olympics with RealAIGym competition at IROS24 Date: October 17, 2024
Awarded to: Niccolò Turcato, Alberto Dalla Libera, Giulio Giacomuzzo, Ruggero Carli, Diego Romeres
MERL Contact: Diego Romeres
Research Areas: Artificial Intelligence, Dynamical Systems, Machine Learning, RoboticsBrief- The team composed of the control group at the University of Padua and MERL's Optimization and Robotic team ranked 1st out of the 4 finalist teams that arrived to the 2nd AI Olympics with RealAIGym competition at IROS 24, which focused on control of under-actuated robots. The team was composed by Niccolò Turcato, Alberto Dalla Libera, Giulio Giacomuzzo, Ruggero Carli and Diego Romeres. The competition was organized by the German Research Center for Artificial Intelligence (DFKI), Technical University of Darmstadt and Chalmers University of Technology.
The competition and award ceremony was hosted by IEEE International Conference on Intelligent Robots and Systems (IROS) on October 17, 2024 in Abu Dhabi, UAE. Diego Romeres presented the team's method, based on a model-based reinforcement learning algorithm called MC-PILCO.
- The team composed of the control group at the University of Padua and MERL's Optimization and Robotic team ranked 1st out of the 4 finalist teams that arrived to the 2nd AI Olympics with RealAIGym competition at IROS 24, which focused on control of under-actuated robots. The team was composed by Niccolò Turcato, Alberto Dalla Libera, Giulio Giacomuzzo, Ruggero Carli and Diego Romeres. The competition was organized by the German Research Center for Artificial Intelligence (DFKI), Technical University of Darmstadt and Chalmers University of Technology.
-
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; Yoshiki Masuyama
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.
See All Awards for Machine Learning -
-
News & Events
-
EVENT SANE 2023 - Speech and Audio in the Northeast Date: Thursday, October 26, 2023
Location: New York University, Brooklyn, New York, NY
MERL Contacts: Jonathan Le Roux; Gordon Wichern
Research Areas: Artificial Intelligence, Machine Learning, Speech & AudioBrief- SANE 2023, a one-day event gathering researchers and students in speech and audio from the Northeast of the American continent, was held on Thursday October 26, 2023 at NYU in Brooklyn, New York.
It was the 10th edition in the SANE series of workshops, which started in 2012 and is typically held every year alternately in Boston and New York. Since the first edition, the audience has steadily grown, and SANE 2023 broke SANE 2019's record with 200 participants and 51 posters.
This year's SANE took place in conjunction with the WASPAA workshop, held October 22-25 in upstate New York.
SANE 2023 featured invited talks by seven leading researchers from the Northeast and beyond: Arsha Nagrani (Google), Gaël Richard (Télécom Paris), Gordon Wichern (MERL), Kyunghyun Cho (NYU / Prescient Design), Anna Huang (Google DeepMind / MILA), Wenwu Wang (University of Surrey), and Yuan Gong (MIT). It also featured a lively poster session with 51 posters.
SANE 2023 was co-organized by Jonathan Le Roux (MERL), Juan P. Bello (NYU), and John R. Hershey (Google). SANE remained a free event thanks to generous sponsorship by NYU, MERL, Google, Adobe, Bose, Meta Reality Labs, and Amazon.
Slides and videos of the talks are available from the SANE workshop website.
- SANE 2023, a one-day event gathering researchers and students in speech and audio from the Northeast of the American continent, was held on Thursday October 26, 2023 at NYU in Brooklyn, New York.
-
NEWS Suhas Lohit presents invited talk at Boston Symmetry Day 2025 Date: March 31, 2025
Where: Northeastern University, Boston, MA
MERL Contact: Suhas Lohit
Research Areas: Artificial Intelligence, Computer Vision, Machine LearningBrief- MERL researcher Suhas Lohit was an invited speaker at Boston Symmetry Day, held at Northeastern University. Boston Symmetry Day, an annual workshop organized by researchers at MIT and Northeastern, brought together attendees interested in symmetry-informed machine learning and its applications. Suhas' talk, titled “Efficiency for Equivariance, and Efficiency through Equivariance” discussed recent MERL works that show how to build general and efficient equivariant neural networks, and how equivariance can be utilized in self-supervised learning to yield improved 3D object detection. The abstract and slides can be found in the link below.
See All News & Events for Machine Learning -
-
Research Highlights
-
PS-NeuS: A Probability-guided Sampler for Neural Implicit Surface Rendering -
Quantum AI Technology -
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 -
Sustainable AI -
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 -
Task-aware Unified Source Separation - Audio Examples
-
-
Internships
-
CA0129: Internship - LLM-guided Active SLAM for Mobile Robots
MERL is seeking interns passionate about robotics to contribute to the development of an Active Simultaneous Localization and Mapping (Active SLAM) framework guided by Large Language Models (LLM). The core objective is to achieve autonomous behavior for mobile robots. The methods will be implemented and evaluated in high performance simulators and (time-permitting) in actual robotic platforms, such as legged and wheeled robots. The expectation at the end of the internship is a publication at a top-tier robotic or computer vision conference and/or journal.
The internship has a flexible start date (Spring/Summer 2025), with a duration of 3-6 months depending on agreed scope and intermediate progress.
Required Specific Experience
- Current/Past Enrollment in a PhD Program in Computer Engineering, Computer Science, Electrical Engineering, Mechanical Engineering, or related field
- Experience with employing and fine-tuning LLM and/or Visual Language Models (VLM) for high-level context-aware planning and navigation
- 2+ years experience with 3D computer vision (e.g., point cloud, voxels, camera pose estimation) and mapping, filter-based methods (e.g., EKF), and in at least some of: motion planning algorithms, factor graphs, control, and optimization
- Excellent programming skills in Python and/or C/C++, with prior knowledge in ROS2 and high-fidelity simulators such as Gazebo, Isaac Lab, and/or Mujoco
Additional Desired Experience
- Prior experience with implementation and/or development of SLAM algorithms on robotic hardware, including acquisition, processing, and fusion of multimodal sensor data such as proprioceptive and exteroceptive sensors
-
MS0098: Internship - Control and Estimation for Large-Scale Thermofluid Systems
MERL is seeking a motivated graduate student to research methods for state and parameter estimation and optimization of large-scale systems for process applications. Representative applications include large vapor-compression cycles and other multiphysical systems for energy conversion that couple thermodynamic, fluid, and electrical domains. The ideal candidate would have a solid background in control and estimation, numerical methods, and optimization; strong programming skills and experience with Julia/Python/Matlab are also expected. Knowledge of the fundamental physics of thermofluid flows (e.g., thermodynamics, heat transfer, and fluid mechanics), nonlinear dynamics, or equation-oriented languages (Modelica, gPROMS) is a plus. The expected duration of this internship is 3 months.
-
OR0115: Internship - Whole-body dexterous manipulation
MERL is looking for a highly motivated individual to work on whole-body dexterous manipulation. The research will develop robot motor skills for whole-body, dexterous manipulation using optimization and/or learning algorithms. The ideal candidate should have experience in either one or multiple of the following topics: Optimization Algorithms for contact systems, Reinforcement Learning, control through contacts, and Behavioral cloning. Senior PhD students in robotics and engineering with a focus on contact-rich manipulation are encouraged to apply. Prior experience working with physical robotic systems (and vision and tactile sensors) is required as results need to be implemented on a physical hardware. Good coding skills in Python ML libraries like PyTorch etc. and/or relevant Optimization packages is required. A successful internship will result in submission of results to a peer-reviewed robotics journal in collaboration with MERL researchers. The expected duration of internship is 4-5 months with start date in May/June 2025. This internship is preferred to be onsite at MERL.
Required Specific Experience
- Prior experience working with physical hardware system is required.
- Prior publication experience in robotics venues like ICRA,RSS, CoRL.
See All Internships for Machine Learning -
-
Openings
-
CA0093: Research Scientist - Control for Autonomous Systems
-
EA0042: Research Scientist - Control & Learning
-
CI0130: Postdoctoral Research Fellow - Artificial General Intelligence (AGI)
See All Openings at MERL -
-
Recent Publications
- "Quantum-PEFT: Ultra Parameter-Efficient Fine-Tuning", International Conference on Learning Representations (ICLR), April 2025.BibTeX TR2025-051 PDF
- @inproceedings{Koike-Akino2025apr,
- author = {Koike-Akino, Toshiaki and Tonin,Francesco and Wu,Yongtao and Wu,Frank Zhengqing and Candogan,Leyla Naz and Cevher, Volkan},
- title = {{Quantum-PEFT: Ultra Parameter-Efficient Fine-Tuning}},
- booktitle = {International Conference on Learning Representations (ICLR)},
- year = 2025,
- month = apr,
- url = {https://www.merl.com/publications/TR2025-051}
- }
, - "Programmatic Video Prediction Using Large Language Models", International Conference on Learning Representations Workshops (ICLRW), April 2025.BibTeX TR2025-049 PDF
- @inproceedings{Tang2025apr,
- author = {Tang, Hao and Ellis, Kevin and Lohit, Suhas and Jones, Michael J. and Chatterjee, Moitreya},
- title = {{Programmatic Video Prediction Using Large Language Models}},
- booktitle = {International Conference on Learning Representations Workshops (ICLRW)},
- year = 2025,
- month = apr,
- url = {https://www.merl.com/publications/TR2025-049}
- }
, - "30+ Years of Source Separation Research: Achievements and Future Challenges", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), April 2025.BibTeX TR2025-036 PDF
- @inproceedings{Araki2025mar,
- author = {Araki, Shoko and Ito, Nobutaka and Haeb-Umbach, Reinhold and Wichern, Gordon and Wang, Zhong-Qiu and Mitsufuji, Yuki},
- title = {{30+ Years of Source Separation Research: Achievements and Future Challenges}},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2025,
- month = mar,
- url = {https://www.merl.com/publications/TR2025-036}
- }
, - "No Class Left Behind: A Closer Look at Class Balancing for Audio Tagging", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), April 2025.BibTeX TR2025-037 PDF
- @inproceedings{Ebbers2025mar,
- author = {Ebbers, Janek and Germain, François G and Wilkinghoff, Kevin and Wichern, Gordon and {Le Roux}, Jonathan},
- title = {{No Class Left Behind: A Closer Look at Class Balancing for Audio Tagging}},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2025,
- month = mar,
- url = {https://www.merl.com/publications/TR2025-037}
- }
, - "O-EENC-SD: Efficient Online End-to-End Neural Clustering for Speaker Diarization", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), April 2025.BibTeX TR2025-031 PDF
- @inproceedings{Gruttadauria2025mar,
- author = {Gruttadauria, Elio and Fontaine, Mathieu and {Le Roux}, Jonathan and Essid, Slim},
- title = {{O-EENC-SD: Efficient Online End-to-End Neural Clustering for Speaker Diarization}},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2025,
- month = mar,
- url = {https://www.merl.com/publications/TR2025-031}
- }
, - "Retrieval-Augmented Neural Field for HRTF Upsampling and Personalization", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), April 2025.BibTeX TR2025-029 PDF Software
- @inproceedings{Masuyama2025mar,
- author = {Masuyama, Yoshiki and Wichern, Gordon and Germain, François G and Ick, Christopher and {Le Roux}, Jonathan},
- title = {{Retrieval-Augmented Neural Field for HRTF Upsampling and Personalization}},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2025,
- month = mar,
- url = {https://www.merl.com/publications/TR2025-029}
- }
, - "Leveraging Audio-Only Data for Text-Queried Target Sound Extraction", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), April 2025.BibTeX TR2025-033 PDF
- @inproceedings{Saijo2025mar2,
- author = {Saijo, Kohei and Ebbers, Janek and Germain, François G and Khurana, Sameer and Wichern, Gordon and {Le Roux}, Jonathan},
- title = {{Leveraging Audio-Only Data for Text-Queried Target Sound Extraction}},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2025,
- month = mar,
- url = {https://www.merl.com/publications/TR2025-033}
- }
, - "Task-Aware Unified Source Separation", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), April 2025.BibTeX TR2025-032 PDF
- @inproceedings{Saijo2025mar,
- author = {Saijo, Kohei and Ebbers, Janek and Germain, François G and Wichern, Gordon and {Le Roux}, Jonathan},
- title = {{Task-Aware Unified Source Separation}},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2025,
- month = mar,
- url = {https://www.merl.com/publications/TR2025-032}
- }
,
- "Quantum-PEFT: Ultra Parameter-Efficient Fine-Tuning", International Conference on Learning Representations (ICLR), April 2025.
-
Videos
-
Software & Data Downloads
-
Generalization in Deep RL with a Robust Adaptation Module -
ComplexVAD Dataset -
MEL-PETs Joint-Context Attack for LLM Privacy Challenge -
Learned Born Operator for Reflection Tomographic Imaging -
MEL-PETs Defense for LLM Privacy Challenge -
Stabilizing Subject Transfer in EEG Classification with Divergence Estimation -
Retrieval-Augmented Neural Field for HRTF Upsampling and Personalization -
Self-Monitored Inference-Time INtervention for Generative Music Transformers -
Radar dEtection TRansformer -
Millimeter-wave Multi-View Radar Dataset -
Gear Extensions of Neural Radiance Fields -
Long-Tailed Anomaly Detection Dataset -
Target-Speaker SEParation -
Pixel-Grounded Prototypical Part Networks -
Steered Diffusion -
BAyesian Network for adaptive SAmple Consensus -
Meta-Learning State Space Models -
Explainable Video Anomaly Localization -
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
-