Ye Wang

Ye Wang
Ye's Quick Links

  • Biography

    Ye was a member of the Information Systems and Sciences Laboratory at Boston University, where he studied information-theoretically secure multiparty computation. His current research interests include information security, biometric authentication, and data privacy.

  • Recent News & Events

    •  NEWS    MERL Papers and Workshops at CVPR 2025
      Date: June 11, 2025 - June 15, 2025
      Where: Nashville, TN, USA
      MERL Contacts: Matthew Brand; Moitreya Chatterjee; Anoop Cherian; François Germain; Michael J. Jones; Toshiaki Koike-Akino; Jing Liu; Suhas Lohit; Tim K. Marks; Pedro Miraldo; Kuan-Chuan Peng; Naoko Sawada; Pu (Perry) Wang; Ye Wang
      Research Areas: Artificial Intelligence, Computer Vision, Machine Learning, Signal Processing, Speech & Audio
      Brief
      • MERL researchers are presenting 2 conference papers, co-organizing two workshops, and presenting 7 workshop papers at the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2025 conference, which will be held in Nashville, TN, USA from June 11-15, 2025. CVPR is one of the most prestigious and competitive international conferences in the area of computer vision. Details of MERL contributions are provided below:


        Main Conference Papers:

        1. "UWAV: Uncertainty-weighted Weakly-supervised Audio-Visual Video Parsing" by Y.H. Lai, J. Ebbers, Y. F. Wang, F. Germain, M. J. Jones, M. Chatterjee

        This work deals with the task of weakly‑supervised Audio-Visual Video Parsing (AVVP) and proposes a novel, uncertainty-aware algorithm called UWAV towards that end. UWAV works by producing more reliable segment‑level pseudo‑labels while explicitly weighting each label by its prediction uncertainty. This uncertainty‑aware training, combined with a feature‑mixup regularization scheme, promotes inter‑segment consistency in the pseudo-labels. As a result, UWAV achieves state‑of‑the‑art performance on two AVVP datasets across multiple metrics, demonstrating both effectiveness and strong generalizability.

        Paper: https://www.merl.com/publications/TR2025-072

        2. "TailedCore: Few-Shot Sampling for Unsupervised Long-Tail Noisy Anomaly Detection" by Y. G. Jung, J. Park, J. Yoon, K.-C. Peng, W. Kim, A. B. J. Teoh, and O. Camps.

        This work tackles unsupervised anomaly detection in complex scenarios where normal data is noisy and has an unknown, imbalanced class distribution. Existing models face a trade-off between robustness to noise and performance on rare (tail) classes. To address this, the authors propose TailSampler, which estimates class sizes from embedding similarities to isolate tail samples. Using TailSampler, they develop TailedCore, a memory-based model that effectively captures tail class features while remaining noise-robust, outperforming state-of-the-art methods in extensive evaluations.

        paper: https://www.merl.com/publications/TR2025-077


        MERL Co-Organized Workshops:

        1. Multimodal Algorithmic Reasoning (MAR) Workshop, organized by A. Cherian, K.-C. Peng, S. Lohit, H. Zhou, K. Smith, L. Xue, T. K. Marks, and J. Tenenbaum.

        Workshop link: https://marworkshop.github.io/cvpr25/

        2. The 6th Workshop on Fair, Data-Efficient, and Trusted Computer Vision, organized by N. Ratha, S. Karanam, Z. Wu, M. Vatsa, R. Singh, K.-C. Peng, M. Merler, and K. Varshney.

        Workshop link: https://fadetrcv.github.io/2025/


        Workshop Papers:

        1. "FreBIS: Frequency-Based Stratification for Neural Implicit Surface Representations" by N. Sawada, P. Miraldo, S. Lohit, T.K. Marks, and M. Chatterjee (Oral)

        With their ability to model object surfaces in a scene as a continuous function, neural implicit surface reconstruction methods have made remarkable strides recently, especially over classical 3D surface reconstruction methods, such as those that use voxels or point clouds. Towards this end, we propose FreBIS - a neural implicit‑surface framework that avoids overloading a single encoder with every surface detail. It divides a scene into several frequency bands and assigns a dedicated encoder (or group of encoders) to each band, then enforces complementary feature learning through a redundancy‑aware weighting module. Swapping this frequency‑stratified stack into an off‑the‑shelf reconstruction pipeline markedly boosts 3D surface accuracy and view‑consistent rendering on the challenging BlendedMVS dataset.

        paper: https://www.merl.com/publications/TR2025-074

        2. "Multimodal 3D Object Detection on Unseen Domains" by D. Hegde, S. Lohit, K.-C. Peng, M. J. Jones, and V. M. Patel.

        LiDAR-based object detection models often suffer performance drops when deployed in unseen environments due to biases in data properties like point density and object size. Unlike domain adaptation methods that rely on access to target data, this work tackles the more realistic setting of domain generalization without test-time samples. We propose CLIX3D, a multimodal framework that uses both LiDAR and image data along with supervised contrastive learning to align same-class features across domains and improve robustness. CLIX3D achieves state-of-the-art performance across various domain shifts in 3D object detection.

        paper: https://www.merl.com/publications/TR2025-078

        3. "Improving Open-World Object Localization by Discovering Background" by A. Singh, M. J. Jones, K.-C. Peng, M. Chatterjee, A. Cherian, and E. Learned-Miller.

        This work tackles open-world object localization, aiming to detect both seen and unseen object classes using limited labeled training data. While prior methods focus on object characterization, this approach introduces background information to improve objectness learning. The proposed framework identifies low-information, non-discriminative image regions as background and trains the model to avoid generating object proposals there. Experiments on standard benchmarks show that this method significantly outperforms previous state-of-the-art approaches.

        paper: https://www.merl.com/publications/TR2025-058

        4. "PF3Det: A Prompted Foundation Feature Assisted Visual LiDAR 3D Detector" by K. Li, T. Zhang, K.-C. Peng, and G. Wang.

        This work addresses challenges in 3D object detection for autonomous driving by improving the fusion of LiDAR and camera data, which is often hindered by domain gaps and limited labeled data. Leveraging advances in foundation models and prompt engineering, the authors propose PF3Det, a multi-modal detector that uses foundation model encoders and soft prompts to enhance feature fusion. PF3Det achieves strong performance even with limited training data. It sets new state-of-the-art results on the nuScenes dataset, improving NDS by 1.19% and mAP by 2.42%.

        paper: https://www.merl.com/publications/TR2025-076

        5. "Noise Consistency Regularization for Improved Subject-Driven Image Synthesis" by Y. Ni., S. Wen, P. Konius, A. Cherian

        Fine-tuning Stable Diffusion enables subject-driven image synthesis by adapting the model to generate images containing specific subjects. However, existing fine-tuning methods suffer from two key issues: underfitting, where the model fails to reliably capture subject identity, and overfitting, where it memorizes the subject image and reduces background diversity. To address these challenges, two auxiliary consistency losses are porposed for diffusion fine-tuning. First, a prior consistency regularization loss ensures that the predicted diffusion noise for prior (non- subject) images remains consistent with that of the pretrained model, improving fidelity. Second, a subject consistency regularization loss enhances the fine-tuned model’s robustness to multiplicative noise modulated latent code, helping to preserve subject identity while improving diversity. Our experimental results demonstrate the effectiveness of our approach in terms of image diversity, outperforming DreamBooth in terms of CLIP scores, background variation, and overall visual quality.

        paper: https://www.merl.com/publications/TR2025-073

        6. "LatentLLM: Attention-Aware Joint Tensor Compression" by T. Koike-Akino, X. Chen, J. Liu, Y. Wang, P. Wang, M. Brand

        We propose a new framework to convert a large foundation model such as large language models (LLMs)/large multi- modal models (LMMs) into a reduced-dimension latent structure. Our method uses a global attention-aware joint tensor decomposition to significantly improve the model efficiency. We show the benefit on several benchmark including multi-modal reasoning tasks.

        paper: https://www.merl.com/publications/TR2025-075

        7. "TuneComp: Joint Fine-Tuning and Compression for Large Foundation Models" by T. Koike-Akino, X. Chen, J. Liu, Y. Wang, P. Wang, M. Brand

        To reduce model size during post-training, compression methods, including knowledge distillation, low-rank approximation, and pruning, are often applied after fine- tuning the model. However, sequential fine-tuning and compression sacrifices performance, while creating a larger than necessary model as an intermediate step. In this work, we aim to reduce this gap, by directly constructing a smaller model while guided by the downstream task. We propose to jointly fine-tune and compress the model by gradually distilling it to a pruned low-rank structure. Experiments demonstrate that joint fine-tuning and compression significantly outperforms other sequential compression methods.

        paper: https://www.merl.com/publications/TR2025-079
    •  
    •  TALK    [MERL Seminar Series 2025] Andy Zou presents talk titled Red Teaming AI Agents in-the-wild: Revealing Deployment Vulnerabilities
      Date & Time: Wednesday, March 26, 2025; 1:00 PM
      Speaker: Andy Zou, CMU & Gray Swan AI
      MERL Host: Ye Wang
      Research Areas: Artificial Intelligence, Machine Learning, Information Security
      Abstract
      • This presentation demonstrates how red teaming uncovers critical vulnerabilities in AI agents that challenge assumptions about safe deployment. The talk discusses the risks of integrating AI into real-world applications and recommends practical safeguards to enhance resilience and ensure dependable deployment in high-risk settings.
    •  

    See All News & Events for Ye

  • 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 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’s Paper on Wi-Fi Sensing Earns Top 3% Paper Recognition at ICASSP 2023, Selected as a Best Student Paper Award Finalist
      Date: June 9, 2023
      Awarded to: Cristian J. Vaca-Rubio, Pu Wang, Toshiaki Koike-Akino, Ye Wang, Petros Boufounos and Petar Popovski
      MERL Contacts: Petros T. Boufounos; Toshiaki Koike-Akino; Pu (Perry) Wang; Ye Wang
      Research Areas: Artificial Intelligence, Communications, Computational Sensing, Dynamical Systems, Machine Learning, Signal Processing
      Brief
      • A MERL Paper on Wi-Fi sensing was recognized as a Top 3% Paper among all 2709 accepted papers at the 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2023). Co-authored by Cristian Vaca-Rubio and Petar Popovski from Aalborg University, Denmark, and MERL researchers Pu Wang, Toshiaki Koike-Akino, Ye Wang, and Petros Boufounos, the paper "MmWave Wi-Fi Trajectory Estimation with Continous-Time Neural Dynamic Learning" was also a Best Student Paper Award finalist.

        Performed during Cristian’s stay at MERL first as a visiting Marie Skłodowska-Curie Fellow and then as a full-time intern in 2022, this work capitalizes on standards-compliant Wi-Fi signals to perform indoor localization and sensing. The paper uses a neural dynamic learning framework to address technical issues such as low sampling rate and irregular sampling intervals.

        ICASSP, a flagship conference of the IEEE Signal Processing Society (SPS), was hosted on the Greek island of Rhodes from June 04 to June 10, 2023. ICASSP 2023 marked the largest ICASSP in history, boasting over 4000 participants and 6128 submitted papers, out of which 2709 were accepted.
    •  
    •  AWARD    MERL Ranked 1st Place in Cross-Subject Transfer Learning Task and 4th Place Overall at the NeurIPS2021 BEETL Competition for EEG Transfer Learning.
      Date: November 11, 2021
      Awarded to: Niklas Smedemark-Margulies, Toshiaki Koike-Akino, Ye Wang, Deniz Erdogmus
      MERL Contacts: Toshiaki Koike-Akino; Ye Wang
      Research Areas: Artificial Intelligence, Signal Processing, Human-Computer Interaction
      Brief
      • The MERL Signal Processing group achieved first place in the cross-subject transfer learning task and fourth place overall in the NeurIPS 2021 BEETL AI Challenge for EEG Transfer Learning. The team included Niklas Smedemark-Margulies (intern from Northeastern University), Toshiaki Koike-Akino, Ye Wang, and Prof. Deniz Erdogmus (Northeastern University). The challenge addresses two types of transfer learning tasks for EEG Biosignals: a homogeneous transfer learning task for cross-subject domain adaptation; and a heterogeneous transfer learning task for cross-data domain adaptation. There were 110+ registered teams in this competition, MERL ranked 1st in the homogeneous transfer learning task, 7th place in the heterogeneous transfer learning task, and 4th place for the combined overall score. For the homogeneous transfer learning task, MERL developed a new pre-shot learning framework based on feature disentanglement techniques for robustness against inter-subject variation to enable calibration-free brain-computer interfaces (BCI). MERL is invited to present our pre-shot learning technique at the NeurIPS 2021 workshop.
    •  
    See All Awards for MERL

  • Research Highlights

  • MERL Publications

    •  Koike-Akino, T., Liu, J., Wang, Y., "u-MoE: Test-Time Pruning as Micro-Grained Mixture-of-Experts", arXiv, June 2025.
      BibTeX arXiv
      • @article{Koike-Akino2025jun2,
      • author = {Koike-Akino, Toshiaki and Liu, Jing and Wang, Ye},
      • title = {{u-MoE: Test-Time Pruning as Micro-Grained Mixture-of-Experts}},
      • journal = {arXiv},
      • year = 2025,
      • month = jun,
      • url = {https://arxiv.org/abs/2505.18451v1}
      • }
    •  Koike-Akino, T., Chen, X., Liu, J., Wang, Y., Wang, P., Brand, M., "LatentLLM: Attention-Aware Joint Tensor Compression", IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshop, June 2025.
      BibTeX TR2025-075 PDF
      • @inproceedings{Koike-Akino2025jun,
      • author = {Koike-Akino, Toshiaki and Chen, Xiangyu and Liu, Jing and Wang, Ye and Wang, Pu and Brand, Matthew},
      • title = {{LatentLLM: Attention-Aware Joint Tensor Compression}},
      • booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshop},
      • year = 2025,
      • month = jun,
      • url = {https://www.merl.com/publications/TR2025-075}
      • }
    •  Chen, X., Liu, J., Wang, Y., Brand, M., Wang, P., Koike-Akino, T., "TuneComp: Joint Fine-Tuning and Compression for Large Foundation Models", IEEE Conference on Computer Vision and Pattern Recognition (CVPR) workshop on Efficient and On-Device Generation, June 2025.
      BibTeX TR2025-079 PDF
      • @inproceedings{Chen2025jun,
      • author = {Chen, Xiangyu and Liu, Jing and Wang, Ye and Brand, Matthew and Wang, Pu and Koike-Akino, Toshiaki},
      • title = {{TuneComp: Joint Fine-Tuning and Compression for Large Foundation Models}},
      • booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR) workshop on Efficient and On-Device Generation},
      • year = 2025,
      • month = jun,
      • url = {https://www.merl.com/publications/TR2025-079}
      • }
    •  Liu, J., Koike-Akino, T., Wang, Y., Mansour, H., Brand, M., "AWP: Activation-Aware Weight Pruning and Quantization with Projected Gradient Descent", arXiv, June 2025.
      BibTeX arXiv
      • @article{Liu2025jun,
      • author = {Liu, Jing and Koike-Akino, Toshiaki and Wang, Ye and Mansour, Hassan and Brand, Matthew},
      • title = {{AWP: Activation-Aware Weight Pruning and Quantization with Projected Gradient Descent}},
      • journal = {arXiv},
      • year = 2025,
      • month = jun,
      • url = {https://arxiv.org/abs/2506.10205}
      • }
    •  Park, Y.-J., Germain, F.G., Liu, J., Wang, Y., Koike-Akino, T., Wichern, G., Azizan, N., Laughman, C.R., Chakrabarty, A., "Probabilistic Forecasting for Building Energy Systems using Time-Series Foundation Models", arXiv, May 2025.
      BibTeX arXiv
      • @article{Park2025may,
      • 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 = {arXiv},
      • year = 2025,
      • month = may,
      • url = {https://arxiv.org/abs/2506.00630}
      • }
    See All MERL Publications for Ye

  • Software & Data Downloads

  • Videos

  • MERL Issued Patents

    • Title: "Generative Model for Inverse Design of Materials, Devices, and Structures"
      Inventors: Kojima, Keisuke; Koike-Akino, Toshiaki; Tang, Yingheng; Wang, Ye
      Patent No.: 12,260,339
      Issue Date: Mar 25, 2025
    • Title: "Automated Construction of Neural Network Architecture with Bayesian Graph Exploration"
      Inventors: Koike-Akino, Toshiaki; Wang, Ye; Demir, Andac; Erdogmus, Deniz
      Patent No.: 12,061,985
      Issue Date: Aug 13, 2024
    • Title: "Anomaly Detection and Diagnosis in Factory Automation System using Pre-Processed Time-Delay Neural Network with Loss Function Adaptation"
      Inventors: Guo, Jianlin; Liu, Bryan; Koike-Akino, Toshiaki; Wang, Ye; Kim, Kyeong-Jin; Parsons, Kieran; Orlik, Philip V.
      Patent No.: 12,007,760
      Issue Date: Jun 11, 2024
    • Title: "Multi-Band Wi-Fi Fusion for WLAN Sensing"
      Inventors: Wang, Pu; Yu, Jianyuan; Koike-Akino, Toshiaki; Wang, Ye; Orlik, Philip V.
      Patent No.: 11,902,811
      Issue Date: Feb 13, 2024
    • Title: "Apparatus and Method for Anomaly Detection"
      Inventors: Wang, Ye; Kim, Kyeong-Jin; Wang, Xiao
      Patent No.: 11,843,623
      Issue Date: Dec 12, 2023
    • Title: "System and Method for Manipulating Two-Dimensional (2D) Images of Three-Dimensional (3D) Objects"
      Inventors: Marks, Tim; Medin, Safa; Cherian, Anoop; Wang, Ye
      Patent No.: 11,663,798
      Issue Date: May 30, 2023
    • Title: "Non-Uniform Regularization in Artificial Neural Networks for Adaptable Scaling"
      Inventors: Wang, Ye; Koike-Akino, Toshiaki
      Patent No.: 11,651,225
      Issue Date: May 16, 2023
    • Title: "Protograph Quasi-Cyclic Polar Codes and Related Low-Density Generator Matrix Family"
      Inventors: Koike-Akino, Toshiaki; Wang, Ye
      Patent No.: 11,463,114
      Issue Date: Oct 4, 2022
    • Title: "Battery Diagnostic System for Estimating Remaining useful Life (RUL) of a Battery"
      Inventors: Gorrachategui, Ivan Sanz; Pajovic, Milutin; Wang, Ye
      Patent No.: 11,346,891
      Issue Date: May 31, 2022
    • Title: "Generative Model for Inverse Design of Materials, Devices, and Structures"
      Inventors: Kojima, Keisuke; Tang, Yingheng; Koike-Akino, Toshiaki; Wang, Ye
      Patent No.: 11,251,896
      Issue Date: Feb 15, 2022
    • Title: "DATA-DRIVEN PRIVACY-PRESERVING COMMUNICATION"
      Inventors: Wang, Ye; Ishwar, Prakash; Tripathy, Ardhendu S
      Patent No.: 11,132,453
      Issue Date: Sep 28, 2021
    • Title: "Irregular Polar Code Encoding"
      Inventors: Koike-Akino, Toshiaki; Wang, Ye; Draper, Stark C.
      Patent No.: 10,862,621
      Issue Date: Dec 8, 2020
    • Title: "Method and Systems using Privacy-Preserving Analytics for Aggregate Data"
      Inventors: Wang, Ye; Raval, Nisarg Jagdishbhai; Ishwar, Prakash
      Patent No.: 10,452,865
      Issue Date: Oct 22, 2019
    • Title: "Irregular Polar Code Encoding"
      Inventors: Koike-Akino, Toshiaki; Wang, Ye; Draper, Stark C.
      Patent No.: 10,313,056
      Issue Date: Jun 4, 2019
    • Title: "Soft-Output Decoding of Codewords Encoded with Polar Code"
      Inventors: Wang, Ye; Koike-Akino, Toshiaki; Draper, Stark C.
      Patent No.: 10,312,946
      Issue Date: Jun 4, 2019
    • Title: "Method and Systems using Privacy-Preserving Analytics for Aggregate Data"
      Inventors: Wang, Ye; Hattori, Mitsuhiro; Shimizu, Rina; Hirano, Takato; Matsuda, Nori
      Patent No.: 10,216,959
      Issue Date: Feb 26, 2019
    • Title: "Privacy Preserving Statistical Analysis on Distributed Databases"
      Inventors: Wang, Ye; Lin, Bing-Rong; Rane, Shantanu D.
      Patent No.: 10,146,958
      Issue Date: Dec 4, 2018
    • Title: "Method and System for Determining Hidden States of a Machine using Privacy-Preserving Distributed Data Analytics and a Semi-trusted Server and a Third-Party"
      Inventors: Wang, Ye
      Patent No.: 9,471,810
      Issue Date: Oct 18, 2016
    • Title: "Method for Determining Hidden States of Systems using Privacy-Preserving Distributed Data Analytics"
      Inventors: Wang, Ye; Xie, Qian; Rane, Shantanu D.
      Patent No.: 9,246,978
      Issue Date: Jan 26, 2016
    • Title: "Privacy Preserving Statistical Analysis for Distributed Databases"
      Inventors: Wang, Ye; Lin, Bing-Rong; Rane, Shantanu D.
      Patent No.: 8,893,292
      Issue Date: Nov 18, 2014
    • Title: "Secure Multi-Party Computation of Normalized Sum-Type Functions"
      Inventors: Rane, Shantanu D.; Sun, Wei; Wang, Ye
      Patent No.: 8,473,537
      Issue Date: Jun 25, 2013
    See All Patents for MERL