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
Gordon
Wichern
Anoop
Cherian
Tim K.
Marks
Pu
(Perry)
Wang
Michael J.
Jones
Christopher R.
Laughman
Kieran
Parsons
Stefano
Di Cairano
Philip V.
Orlik
Daniel N.
Nikovski
Diego
Romeres
Jing
Liu
Chiori
Hori
Suhas
Lohit
Bingnan
Wang
Yebin
Wang
Hassan
Mansour
Matthew
Brand
Petros T.
Boufounos
Yoshiki
Masuyama
Kuan-Chuan
Peng
Moitreya
Chatterjee
Abraham P.
Vinod
Arvind
Raghunathan
Vedang M.
Deshpande
Jianlin
Guo
Siddarth
Jain
Pedro
Miraldo
Hongtao
Qiao
Scott A.
Bortoff
Saviz
Mowlavi
Radu
Corcodel
William S.
Yerazunis
Chungwei
Lin
Dehong
Liu
Hongbo
Sun
Joshua
Rapp
Nobuyuki
Yoshikawa
Wael H.
Ali
Christoph
Boeddeker
Yanting
Ma
Anthony
Vetro
Jinyun
Zhang
Purnanand
Elango
Abraham
Goldsmith
Kaen
Kogashi
Zhaolin
Ren
Alexander
Schperberg
Avishai
Weiss
Kenji
Inomata
Kei
Suzuki
-
Awards
-
AWARD MERL team wins the Generative Data Augmentation of Room Acoustics (GenDARA) 2025 Challenge Date: April 7, 2025
Awarded to: Christopher Ick, Gordon Wichern, Yoshiki Masuyama, François G. Germain, and Jonathan Le Roux
MERL Contacts: Jonathan Le Roux; Yoshiki Masuyama; Gordon Wichern
Research Areas: Artificial Intelligence, Machine Learning, Speech & AudioBrief- MERL's Speech & Audio team ranked 1st out of 3 teams in the Generative Data Augmentation of Room Acoustics (GenDARA) 2025 Challenge, which focused on “generating room impulse responses (RIRs) to supplement a small set of measured examples and using the augmented data to train speaker distance estimation (SDE) models". The team was led by MERL intern Christopher Ick, and also included Gordon Wichern, Yoshiki Masuyama, François G. Germain, and Jonathan Le Roux.
The GenDARA Challenge was organized as part of the Generative Data Augmentation (GenDA) workshop at the 2025 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2025), and held on April 7, 2025 in Hyderabad, India. Yoshiki Masuyama presented the team's method, "Data Augmentation Using Neural Acoustic Fields With Retrieval-Augmented Pre-training".
The GenDARA challenge aims to promote the use of generative AI to synthesize RIRs from limited room data, as collecting or simulating RIR datasets at scale remains a significant challenge due to high costs and trade-offs between accuracy and computational efficiency. The challenge asked participants to first develop RIR generation systems capable of expanding a sparse set of labeled room impulse responses by generating RIRs at new source–receiver positions. They were then tasked with using this augmented dataset to train speaker distance estimation systems. Ranking was determined by the overall performance on the downstream SDE task. MERL’s approach to the GenDARA challenge centered on a geometry-aware neural acoustic field model that was first pre-trained on a large external RIR dataset to learn generalizable mappings from 3D room geometry to room impulse responses. For each challenge room, the model was then adapted or fine-tuned using the small number of provided RIRs, enabling high-fidelity generation of RIRs at unseen source–receiver locations. These augmented RIR sets were subsequently used to train the SDE system, improving speaker distance estimation by providing richer and more diverse acoustic training data.
- MERL's Speech & Audio team ranked 1st out of 3 teams in the Generative Data Augmentation of Room Acoustics (GenDARA) 2025 Challenge, which focused on “generating room impulse responses (RIRs) to supplement a small set of measured examples and using the augmented data to train speaker distance estimation (SDE) models". The team was led by MERL intern Christopher Ick, and also included Gordon Wichern, Yoshiki Masuyama, François G. Germain, and Jonathan Le Roux.
-
AWARD Mitsubishi Electric Team Wins Awards at GalFer Contest Date: June 23, 2025
Awarded to: Bingnan Wang, Tatsuya Yamamoto, Yusuke Sakamoto, Siyuan Sun, Toshiaki Koike-Akino, and Ye Wang
MERL Contacts: Toshiaki Koike-Akino; Bingnan Wang; Ye Wang
Research Areas: Machine Learning, Multi-Physical Modeling, OptimizationBrief- The MELSUR (Mitsubishi Electric SURrogate) team, consisting of a group of MERL and Mitsubishi Electric researchers, ranked first in two out of three categories in the GalFer Contest.
The GalFer (Galileo Ferraris) contest aims to compare the accuracy and efficiency of data-driven methodologies for the multi-physics simulation of traction electric machines. A total of 26 teams worldwide participated in the contest, which consists of three categories. The MELSUR team, including MERL staff Bingnan Wang, Toshiaki Koike-Akino, Ye Wang, MERL intern Siyuan Sun, Mitsubishi Electric researchers Tatsuya Yamamoto and Yusuke Sakamoto, ranked first for the category of "Novelty" and "Interpolation". The results were announced during an award ceremony at the COMPUMAG 2025 conference in Naples, Italy.
- The MELSUR (Mitsubishi Electric SURrogate) team, consisting of a group of MERL and Mitsubishi Electric researchers, ranked first in two out of three categories in the GalFer Contest.
-
AWARD MERL work receives IEEE Transactions on Automation Science and Engineering Best New Application Paper Award from IEEE Robotics and Automation Society Date: May 19, 2025
Awarded to: Yehan Ma, Yebin Wang, Stefano Di Cairano, Toshiaki Koike-Akino, Jianlin Guo, Philip Orlik, Xinping Guan and Chenyang Lu
MERL Contacts: Stefano Di Cairano; Jianlin Guo; Toshiaki Koike-Akino; Philip V. Orlik; Yebin Wang
Research Areas: Communications, Control, Machine LearningBrief- The paper “Smart Actuation for End-Edge Industrial Control Systems”, co-authored by MERL intern Yehan Ma, MERL researchers Yebin Wang, Stefano Di Cairano, Toshiaki Koike-Akino, Jianlin Guo, and Philip Orlik, and academic collaborators Xinping Guan and Chenyang Lu, was recognized as the Best New Application Paper of the IEEE Transactions on Automation Science and Engineering (T-ASE), for "a new industrial automation solution that ensures safety operation through coordinated co-design of edge model predictive control and local actuation".
The award recognizes the best application paper published in T-ASE over the previous calendar year, for the significance of new applications, technical merit, originality, potential impact on the field, and clarity of presentation.
- The paper “Smart Actuation for End-Edge Industrial Control Systems”, co-authored by MERL intern Yehan Ma, MERL researchers Yebin Wang, Stefano Di Cairano, Toshiaki Koike-Akino, Jianlin Guo, and Philip Orlik, and academic collaborators Xinping Guan and Chenyang Lu, was recognized as the Best New Application Paper of the IEEE Transactions on Automation Science and Engineering (T-ASE), for "a new industrial automation solution that ensures safety operation through coordinated co-design of edge model predictive control and local actuation".
See All Awards for Machine Learning -
-
News & Events
-
NEWS Toshiaki Koike-Akino delivers an invited talk as a panelist at OFC 2026 Date: March 17, 2026
MERL Contact: Toshiaki Koike-Akino
Research Areas: Artificial Intelligence, Communications, Machine Learning, Signal ProcessingBrief- MERL researcher Toshiaki Koike-Akino will serve as a panelist at OFC 2026, the premier global event for optical communications and networking, to be held in Los Angeles, March 15–19.
Dr. Koike-Akino will participate in the special panel session titled “Machine Learning is Taking Over Optical Communications—But Which Algorithms Should We Use?” He will deliver a panel talk titled “Scaling AI with Light: AI Is Taking Over Optics — But Optics May Take Over AI.” His talk will discuss the growing synergy between AI and optical technologies, highlighting the emerging vision of leveraging optical physics not only as an application domain for AI, but also as a platform for scaling future AI systems.
- MERL researcher Toshiaki Koike-Akino will serve as a panelist at OFC 2026, the premier global event for optical communications and networking, to be held in Los Angeles, March 15–19.
-
TALK [MERL Seminar Series 2026] Alex Gu presents talk titled Proving and Improving: Language Models for Theorem Proving and Proof Shortening in Lean Date & Time: Wednesday, February 11, 2026; 1:00 PM
Speaker: Alex Gu, MIT
MERL Host: Pu (Perry) Wang
Research Areas: Artificial Intelligence, Machine Learning, OptimizationAbstract
Large language models (LLMs) have made steady progress in formal mathematics, achieving near–International Mathematical Olympiad (IMO) performance. This talk presents two complementary advances toward more capable and interpretable formal proving systems. First, we introduce LeanDojo, a foundational open-source toolkit bridging ML and Lean, enabling large-scale data extraction, interactive training, and the development of ReProver, a retrieval-augmented Lean prover. Next, we turn to a critical challenge: proofs produced by LLMs are often unnecessarily long, redundant, and opaque. To mitigate this, we introduce ProofOptimizer, a system that automatically simplifies Lean proofs while preserving correctness. It combines symbolic linting, a fine-tuned 7B model, and iterative refinement, reducing proof length by up to 87% on MiniF2F and 57% on PutnamBench, even halving some IMO-level proofs. Together, these systems demonstrate how AI can make automated proofs not only possible, but also increasingly comprehensible.
See All News & Events for Machine Learning -
-
Research Highlights
-
SAC-GNC: SAmple Consensus for adaptive Graduated Non-Convexity -
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 -
Private, Secure, and Reliable Artificial Intelligence -
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
-
EA0235: Internship - Planning and Control of Mobile Manipulators
-
CI0213: Internship - Efficient Foundation Models for Edge Intelligence
-
OR0262: Internship - Foundation Models in Robotics for Manufacturing
See All Internships for Machine Learning -
-
Openings
-
CI0177: Postdoctoral Research Fellow - Agentic AI
-
MS0268: Research Scientist - Multiphysical Systems
See All Openings at MERL -
-
Recent Publications
- , "Exploring Disentangled Neural Speech Codecs from Self-Supervised Representations", IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW), May 2026.BibTeX TR2026-035 PDF
- @inproceedings{Aihara2026may2,
- author = {Aihara, Ryo and Masuyama, Yoshiki and Germain, François G and Wichern, Gordon and {Le Roux}, Jonathan},
- title = {{Exploring Disentangled Neural Speech Codecs from Self-Supervised Representations}},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)},
- year = 2026,
- month = may,
- url = {https://www.merl.com/publications/TR2026-035}
- }
- , "SUNAC: Source-aware Unified Neural Audio Codec", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 2026.BibTeX TR2026-032 PDF
- @inproceedings{Aihara2026may,
- author = {Aihara, Ryo and Masuyama, Yoshiki and Paissan, Francesco and Germain, François G and Wichern, Gordon and {Le Roux}, Jonathan},
- title = {{SUNAC: Source-aware Unified Neural Audio Codec}},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2026,
- month = may,
- url = {https://www.merl.com/publications/TR2026-032}
- }
- , "Velocity Potential Neural Field for Efficient Ambisonics Impulse Response Modeling", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 2026.BibTeX TR2026-033 PDF
- @inproceedings{Masuyama2026may,
- author = {Masuyama, Yoshiki and Germain, François G and Wichern, Gordon and Hori, Chiori and {Le Roux}, Jonathan},
- title = {{Velocity Potential Neural Field for Efficient Ambisonics Impulse Response Modeling}},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2026,
- month = may,
- url = {https://www.merl.com/publications/TR2026-033}
- }
- , "FlexIO: Flexible Single- and Multi-Channel Speech Separation and Enhancement", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 2026.BibTeX TR2026-034 PDF
- @inproceedings{Masuyama2026may2,
- author = {Masuyama, Yoshiki and Saijo, Kohei and Paissan, Francesco and Han, Jiangyu and Delcroix, Marc and Aihara, Ryo and Germain, François G and Wichern, Gordon and {Le Roux}, Jonathan},
- title = {{FlexIO: Flexible Single- and Multi-Channel Speech Separation and Enhancement}},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2026,
- month = may,
- url = {https://www.merl.com/publications/TR2026-034}
- }
- , "Recovering Pulse Waves from Video Using Deep Unrolling and Deep Equilibrium Models", IEEE Transactions on Image Processing, March 2026.BibTeX TR2026-031 PDF
- @article{Shenoy2026mar,
- author = {Shenoy, Vineet and Lohit, Suhas and Mansour, Hassan and Chellappa, Rama and Marks, Tim K.},
- title = {{Recovering Pulse Waves from Video Using Deep Unrolling and Deep Equilibrium Models}},
- journal = {IEEE Transactions on Image Processing},
- year = 2026,
- month = mar,
- url = {https://www.merl.com/publications/TR2026-031}
- }
- , "Probabilistic Forecasting for Building Energy Systems using Time-Series Foundation Models", Energy and Buildings, March 2026.BibTeX TR2026-030 PDF
- @article{Park2026mar,
- author = {Park, Young-Jin and Germain, François G and Liu, Jing and Wang, Ye and Koike-Akino, Toshiaki and Wichern, Gordon and Azizan, Navid and Laughman, Christopher R. and Chakrabarty, Ankush},
- title = {{Probabilistic Forecasting for Building Energy Systems using Time-Series Foundation Models}},
- journal = {Energy and Buildings},
- year = 2026,
- month = mar,
- url = {https://www.merl.com/publications/TR2026-030}
- }
- , "MMHOI: Modeling Complex 3D Multi-Human Multi-Object Interactions", IEEE Winter Conference on Applications of Computer Vision (WACV), March 2026.BibTeX TR2026-029 PDF Video Data
- @inproceedings{Kogashi2026mar,
- author = {Kogashi, Kaen and Cherian, Anoop and Kuo, Meng-Yu Jennifer},
- title = {{MMHOI: Modeling Complex 3D Multi-Human Multi-Object Interactions}},
- booktitle = {IEEE Winter Conference on Applications of Computer Vision (WACV)},
- year = 2026,
- month = mar,
- url = {https://www.merl.com/publications/TR2026-029}
- }
- , "Output-Feedback Learning-based Adaptive Optimal Control of Nonlinear Systems", Automatica, March 2026.BibTeX TR2026-028 PDF
- @article{Gao2026mar,
- author = {Gao, Weinan and Wang, Yebin and Vamvoudakis, Kyriakos},
- title = {{Output-Feedback Learning-based Adaptive Optimal Control of Nonlinear Systems}},
- journal = {Automatica},
- year = 2026,
- month = mar,
- url = {https://www.merl.com/publications/TR2026-028}
- }
- , "Exploring Disentangled Neural Speech Codecs from Self-Supervised Representations", IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW), May 2026.
-
Videos
-
Software & Data Downloads
-
MMHOI Dataset: Modeling Complex 3D Multi-Human Multi-Object Interactions -
Radar-based 3D Pose Estimation using Transformer -
Open Vocabulary Attribute Detection Dataset -
multi-view Radar object dEtection with 3D bounding boX diffusiOn -
Long-Tailed Online Anomaly Detection dataset -
Group Representation Networks -
Stabilizing Subject Transfer in EEG Classification with Divergence Estimation -
Task-Aware Unified Source Separation -
Local Density-Based Anomaly Score Normalization for Domain Generalization -
Retrieval-Augmented Neural Field for HRTF Upsampling and Personalization -
ComplexVAD Dataset -
Self-Monitored Inference-Time INtervention for Generative Music Transformers -
Radar dEtection TRansformer -
Millimeter-wave Multi-View Radar Dataset -
Zero-Shot Image Conditioning for Text-to-Video Diffusion Models -
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 -
Subject- and Dataset-Aware Neural Field for HRTF Modeling -
MEL-PETs Joint-Context Attack for LLM Privacy Challenge -
MEL-PETs Defense for LLM Privacy Challenge -
Generalization in Deep RL with a Robust Adaptation Module -
Learned Born Operator for Reflection Tomographic Imaging -
Embracing Cacophony
-