Portfolio

Selected work from the lab — peer-reviewed research that anchors our applied practice.

Research

CVPR 2026

From Partially to Fully Unmatched Modalities as Negative Samples in Contrastive Learning

We introduce a curriculum for multimodal contrastive learning that treats partially-to-fully unmatched modality pairs as progressively harder negative samples, improving cross-modal representation quality.

IEEE Transactions on Mobile Computing

Toward an Open Ecosystem for Federated Learning Mobile Apps

FLSys is a mobile-cloud federated learning system that supports different FL models and aggregation methods, enabling an open ecosystem of privacy-preserving FL apps on smartphones.

AAAI 2023

Low-Overhead Model Pruning for Federated Learning

Complement Sparsification prunes models through complementary, collaborative sparsification at the server and the clients, cutting communication and computation overhead in federated learning.

Engineering

Applied AI systems delivered for industry. Case studies are available on request.