Artificial Intelligence

Making machines smarter for improved safety, efficiency and comfort.

Our AI research encompasses advances in computer vision, speech and audio processing, as well as data analytics. Key research themes include improved perception based on machine learning techniques, learning control policies through model-based reinforcement learning, as well as cognition and reasoning based on learned semantic representations. We apply our work to a broad range of automotive and robotics applications, as well as building and home systems.

Quick Links
Researchers
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 & Audio
  Brief
  - 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.
- 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 Security
  Brief
  - 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 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: Jonathan Le Roux; Gordon Wichern; Yoshiki Masuyama
  Research Areas: Artificial Intelligence, Machine Learning, Speech & Audio
  Brief
  - 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.
See All Awards for Artificial Intelligence
News & Events
- EVENT MERL Contributes to ICASSP 2026
  Date: Monday, May 4, 2026 - , May 8, 2026
  Location: Barcelona, Spain
  MERL Contacts: Wael H. Ali; Petros T. Boufounos; Chiori Hori; Jonathan Le Roux; Yanting Ma; Hassan Mansour; Yoshiki Masuyama; Joshua Rapp; Anthony Vetro; Pu (Perry) Wang; Gordon Wichern
  Research Areas: Artificial Intelligence, Computational Sensing, Computer Vision, Machine Learning, Optimization, Signal Processing, Speech & Audio
  Brief
  - MERL has made numerous contributions to both the organization and technical program of ICASSP 2026, which is being held in Barcelona, Spain from May 4-8, 2026.
    
    Sponsorship
    
    MERL is proud to be a Silver Patron of the conference and will participate in the student job fair on Thursday, May 7. Please join this session to learn more about employment opportunities at MERL, including openings for research scientists, post-docs, and interns. MERL Distinguished Research Scientists Petros T. Boufounos and Jonathan Le Roux will also present a spotlight session on MERL’s research in signal processing on Tuesday, May 5 at 13:05.
    
    MERL is also pleased to be the sponsor of two IEEE Awards that will be presented at the conference. We congratulate Prof. Nasir Ahmed, the recipient of the 2026 IEEE Fourier Award for Signal Processing, and Dr. Alex Acero, the recipient of the 2026 IEEE James L. Flanagan Speech and Audio Processing Award.
    
    Technical Program
    
    MERL is presenting 7 papers in the main conference on a wide range of topics including source separation, spatial audio, neural audio codecs, radar-based pose estimation, camera-based airflow sensing, radar array processing, and optimization. Another paper on neural speech codecs will be presented at the Low-Resource Audio Codec (LRAC) Satellite Workshop. MERL researchers will also present two articles published in IEEE Open Journal of Signal Processing (OJSP) on music source separation and head-related transfer function (HRTF) modeling. Finally, Speech and Audio Team members Yoshiki Masuyama and Jonathan Le Roux co-organized a Special Session on Neural Spatial Audio Processing, which will feature six oral presentations.
    
    About ICASSP
    
    ICASSP is the flagship conference of the IEEE Signal Processing Society, and the world's largest and most comprehensive technical conference focused on the research advances and latest technological development in signal and information processing. The event attracts more than 4000 participants each year.
- TALK [MERL Seminar Series 2026] Jialong Wu presents talk titled World Models and Human-like Reasoning
  Date & Time: Wednesday, March 25, 2026; 11:00 AM
  Speaker: Jialong Wu, Tsinghua University
  MERL Host: Anoop Cherian
  Research Areas: Artificial Intelligence, Computer Vision, Machine Learning
  Abstract
  - This talk introduces the background and key findings of our recent work, "Visual Generation Unlocks Human-Like Reasoning through Multimodal World Models," which answers the question of when and how visual generation enabled by unified multimodal models (UMMs) benefits reasoning. We take a world model perspective, inspired by human cognition. Specifically, humans construct mental models of the world, representing information and knowledge through two complementary channels—verbal and visual—to support reasoning, planning, and decision-making. In contrast, recent advances in large language models (LLMs) and vision–language models (VLMs) largely rely on verbal chain-of-thought reasoning, leveraging primarily symbolic and linguistic world knowledge. Unified multimodal models (UMMs) open a new paradigm by using visual generation for visual world modeling, advancing more human-like reasoning on tasks grounded in the physical world. In this work, we formalize the atomic capabilities of world models and world model-based chain-of-thought reasoning. We highlight the richer informativeness and complementary prior knowledge afforded by visual world modeling, leading to our visual superiority hypothesis for tasks grounded in the physical world. We identify and design tasks that necessitate interleaved visual-verbal CoT reasoning, constructing a new evaluation suite, VisWorld-Eval. Through controlled experiments on BAGEL, we show that interleaved CoT significantly outperforms purely verbal CoT on tasks that favor visual world modeling, strongly supporting our insights.
See All News & Events for Artificial Intelligence
Research Highlights
Internships
See All Internships for Artificial Intelligence
Openings
- CI0177: Postdoctoral Research Fellow - Agentic AI
- SA0297: Postdoctoral Research Fellow - AI for Science
See All Openings at MERL
Recent Publications
- Aihara, R., Masuyama, Y., Germain, F.G., Wichern, G., Le Roux, J., "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}
  - }
- Aihara, R., Masuyama, Y., Paissan, F., Germain, F.G., Wichern, G., Le Roux, J., "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}
  - }
- Kato, S., Wang, P., Fujihashi, T., Markham, A., "Heatmap-to-SMPL Multi-View Radar Transformer for Multi-Person 3D Pose Estimation", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 2026.
  BibTeX TR2026-040 PDF
  - @inproceedings{Kato2026may,
  - author = {Kato, Sorachi and Wang, Pu and Fujihashi, Takuya and Markham, Andrew},
  - title = {{Heatmap-to-SMPL Multi-View Radar Transformer for Multi-Person 3D Pose Estimation}},
  - booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
  - year = 2026,
  - month = may,
  - url = {https://www.merl.com/publications/TR2026-040}
  - }
- Masuyama, Y., Germain, F.G., Wichern, G., Hori, C., Le Roux, J., "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}
  - }
- Masuyama, Y., Saijo, K., Paissan, F., Han, J., Delcroix, M., Aihara, R., Germain, F.G., Wichern, G., Le Roux, J., "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}
  - }
- Koike-Akino, T., Liu, J., Wang, Y., "TTQ: Activation-Aware Test-Time Quantization to Accelerate LLM Inference on the Fly", International Conference on Learning Representations (ICLR) Workshop, April 2026.
  BibTeX TR2026-044 PDF
  - @inproceedings{Koike-Akino2026apr,
  - author = {Koike-Akino, Toshiaki and Liu, Jing and Wang, Ye},
  - title = {{TTQ: Activation-Aware Test-Time Quantization to Accelerate LLM Inference on the Fly}},
  - booktitle = {International Conference on Learning Representations (ICLR) Workshop},
  - year = 2026,
  - month = apr,
  - url = {https://www.merl.com/publications/TR2026-044}
  - }
- Wang, Z., Hu, H., Deng, X., Mowlavi, S., Nakahira, Y., "OpInf-LLM: Parametric PDE Solving with LLMs via Operator Inference", International Conference on Learning Representations (ICLR) Workshop on AI and Partial Differential Equations (AI&PDE), April 2026.
  BibTeX TR2026-043 PDF
  - @inproceedings{Wang2026apr2,
  - author = {Wang, Zhuoyuan and Hu, Hanjiang and Deng, Xiyu and Mowlavi, Saviz and Nakahira, Yorie},
  - title = {{OpInf-LLM: Parametric PDE Solving with LLMs via Operator Inference}},
  - booktitle = {International Conference on Learning Representations (ICLR) Workshop on AI and Partial Differential Equations (AI\&PDE)},
  - year = 2026,
  - month = apr,
  - url = {https://www.merl.com/publications/TR2026-043}
  - }
- Wang, R., Wang, Y., Liu, J., Koike-Akino, T., "Quantum Diffusion Models for Few-Shot Learning", Springer Nature, April 2026.
  BibTeX TR2026-042 PDF
  - @article{Wang2026apr,
  - author = {Wang, Ruhan and Wang, Ye and Liu, Jing and Koike-Akino, Toshiaki},
  - title = {{Quantum Diffusion Models for Few-Shot Learning}},
  - journal = {Springer Nature},
  - year = 2026,
  - month = apr,
  - url = {https://www.merl.com/publications/TR2026-042}
  - }
See All Publications for Artificial Intelligence
Videos

[MERL Seminar Series Spring 2026] World Models and Human-like Reasoning

[MERL Seminar Series Spring 2026] Proving and Improving: Language Models for Theorem Proving and Proof Shortening in Lean

[WACV 2026] MMHOI: Modeling Complex Multi-Person Multi-Object Interactions

[MERL Seminar Series Spring 2026] Robust Decision Making Without Compromising Learning Efficiency

[AAAI 2026] LatentLLM: Activation-Aware Transform to Multi-Head Latent Attention

[BMVC 2025] Towards Open-Vocabulary Multimodal 3D Object Detection with Attributes

[ICCV Workshop 2025] Joint Training of Image Generator and Detector for Road Defect Detection

[ICCV 2025] Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts

In-Context Iterative Policy Improvement for Dynamic Manipulation

[CVPR 2025] TailedCore: Few-Shot Sampling for Unsupervised Long-Tail Noisy Anomaly Detection

[MERL Seminar Series Spring 2025] Red Teaming AI Agents in-the-wild: Revealing Deployment Vulnerabilities

[MERL Seminar Series Spring 2025] The Emergence of Generalizability and Semantic Low-Dim Subspaces in Diffusion Models

[MERL Seminar Series Spring 2025] Amplifying human performance in combinatorial competitive programming

[WACV 2025] Towards Zero-shot 3D Anomaly Localization

[NeurIPS 2024] MEL-PETs Defense for the NeurIPS 2024 LLM Privacy Challenge Blue Team Track

[NeurIPS 2024] MEL-PETs Joint-Context Attack for the NeurIPS 2024 LLM Privacy Challenge Red Team Track

[MERL Seminar Series Fall 2024] AI-assisted Power Grid Dispatch and Control: Optimization, Safety, and Real-world Demonstrations

[NeurIPS 2024] Evaluating Large Vision-and-Language Models on Children's Mathematical Olympiads

[MERL Seminar Series Fall 2024] Audio for Object and Spatial Awareness

[IROS 2024] Few-shot Transparent Instance Segmentation for Bin Picking

[MERL Seminar Series Fall 2024] Tools from cognitive science to understand the behavior of large language models

[ECCV 2024] PS-NEUS: A Probability-guided Sampler for Neural Implicit Surface Rendering

[ECCV 2024] Equivariant Spatio-Temporal Self-Supervision for LiDAR Object Detection

Gear-NeRF: Free-Viewpoint Rendering and Tracking with Motion-aware Spatio-Temporal Sampling

[MERL Seminar Series Spring 2024] Are Emergent Abilities of Large Language Models a Mirage?

MERL's Quantum AI Technology

[MERL Seminar Series Spring 2024] The Debate Over 'Understanding' in AI's Large Language Models

[MERL Seminar Series Spring 2024] Computational models of human auditory and language processing

[MERL Seminar Series Fall 2023] Multiplicity in Machine Learning

Multi-level Reasoning for Robotic Assembly: From Sequence Inference to Contact Selection

[MERL Seminar Series Fall 2023] Visual Programming - A compositional approach to building General Purpose Vision Systems

[MERL Seminar Series Fall 2023] The Confluence of Vision, Language, and Robotics

Are Deep Neural Networks SMARTer than Second Graders?

[MERL Seminar Series Spring 2023] Fine-grained wildlife sound recognition: Towards the accuracy of a naturalist

[MERL Seminar Series Spring 2023] Pitfalls and Opportunities in Interpretable Machine Learning

Human Perspective Scene Understanding via Multimodal Sensing

[MERL Seminar Series Spring 2022] Self-Supervised Scene Representation Learning

[MERL Seminar Series Spring 2022] Learning Speech Representations with Multimodal Self-Supervision

[MERL Seminar Series 2021] Deep probabilistic regression

[MERL Seminar Series 2021] Learning to See by Moving: Self-supervising 3D scene representations for perception, control, and visual reasoning

[MERL Seminar Series 2021] Look and Listen: From Semantic to Spatial Audio-Visual Perception

Application of Deep Learning for Nanophotonic Device Design (Invited)

Machine Learning Power Amplifier

Scene-Aware Interaction Technology
Software & Data Downloads

Software & Data Downloads

MERL is making Artificial Intelligence software and data available to the research community:

Physics-Aware Assembly of Complex Industrial Objects (AssemblyBench)
Embracing Cacophony (embracing-cacophony)
MMHOI Dataset: Modeling Complex 3D Multi-Human Multi-Object Interactions (MMHOI)
Subject- and Dataset-Aware Neural Field for HRTF Modeling (SuDaField)
Open Vocabulary Attribute Detection Dataset (OVAD)
Task-Aware Unified Source Separation (TUSS)

See All Downloads