Presented our PlantCLEF 2025 research on multi-label plant species classification using Vision Transformers at the FGVC12 workshop poster session.
I’m a Machine Learning Engineer at Voxel51, completing a Master’s in Computer Science at Georgia Tech. My research interests lie at the intersection of machine learning and representation learning. I am interested in designing models that learn rich, transferable representations efficiently across domains such as vision, language, audio, and 3D perception.
As the computational demands of AI grow, the era of brute-force scaling is hitting a memory wall — memory bandwidth and energy costs simply don’t scale with compute. My research aims to advance green AI: building efficient systems that achieve state-of-the-art capability without a massive carbon footprint.
I also co-lead DS@GT Applied Research & Competitions (ARC), a student-run group advancing ML research through competitive challenges and peer-reviewed publications.
Recent News
- Feb 2026 Contributed bug fixes to the Adapters open-source library link
- Jan 2026 Honored to receive the Best Poster Award at CRIDC 2026 and $1,500 in travel grants link
- Jan 2026 Started a new position as Machine Learning Engineer at Voxel51 link
- Dec 2025 Updated my website and started organizing publications, news, and blog posts
- Dec 2025 Finished teaching the DS@GT ARC - Fall Interest Group (videos available on YouTube) link
Featured Posts
- Jun 20, 2025 FeaturedPresenting a poster at CVPR 2025
- Jan 25, 2024 FeaturedIntroduction to Image Classification with CNNs and PyTorchA practical guide to understanding Convolutional Neural Networks (CNNs) by building a model to classify clothing items.
- Jan 25, 2023 FeaturedVisualizing Universal Function Approximation with PyTorchA visual guide demonstrating how neural networks leverage non-linearities to approximate continuous functions, comparing linear baselines against deep networks.
Publication Highlights
- Distilling Spectrograms into Tokens: Fast and Lightweight Bioacoustic Classification for BirdCLEF+ 2025
Anthony Miyaguchi, Murilo Gustineli, Adrian Cheungg
LifeCLEF Workshop, Madrid 2025 — Best Working Note Paper Award - Tile-Based ViT Inference with Visual-Cluster Priors for Zero-Shot Multi-Species Plant Identification
Murilo Gustineli, Anthony Miyaguchi, Adrian Cheungg, Divyansh Khattak
LifeCLEF Workshop, Madrid 2025 — CVPR poster - Transfer Learning with Pseudo Multi-Label Birdcall Classification for DS@GT BirdCLEF 2024
Anthony Miyaguchi, Adrian Cheung, Murilo Gustineli, Ashley Kim
LifeCLEF Workshop, Grenoble 2024 — Best Working Note Paper Award