Mustafa Chasmai

CICS at UMass Amherst, Massachusetts, USA.

dp.jpg

I am a PhD Student at UMass Amherst, working broadly in Computer Vision under Prof. Subhransu Maji. My research focuses on AI applied for multimodal ecological applications such as bioacoustics, geolocalization, and morphometrics.

Prior to this, I completed my Bachelors degree in Computer Science from IIT Delhi.

News

Apr 30, 2026 Bioacoustic Geolocation and MetaPerch accepted at ICML 2026!
Oct 31, 2025 Wrapped up my internship (student researcher) at Google Deepmind
Sep 1, 2024 iNatSounds accepted at NeurIPS 2024 (D&B)!
Aug 30, 2024 Wrapped up my internship at Dolby
Sep 1, 2023 Started my PhD at UMass Amherst

Selected Publications see all

  1. ICML

    Bioacoustic Geolocation: Species Sounds as Geographic Signals
    Mustafa Chasmai, Wuao Liu, Subhransu Maji, and Grant Van Horn
    In The Forty-third International Conference on Machine Learning 2026
  2. ICML

    MetaPerch: Learning from metadata for bioacoustics foundation models
    Mustafa Chasmai, Vincent Dumoulin, and Jenny Hamer
    In The Forty-third International Conference on Machine Learning 2026
  3. CVPR

    RealBirdID: Benchmarking Bird Species Identification in the Era of MLLMs
    Logan Lawrence, Oindrila Saha, Rangel Daroya, Mustafa Chasmai, Wuao Liu, and 6 more authors
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2026
  4. CVPR-W

    Masked Autoencoders with Limited Data: Does It Work? A Fine-Grained Bioacoustics Case Study
    Wuao Liu, Mustafa Chasmai, Subhransu Maji, and Grant Van Horn
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2026
  5. NeurIPS

    The iNaturalist Sounds Dataset
    Mustafa Chasmai, Alexander Shepard, Subhransu Maji, and Grant Van Horn
    In The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track 2024