Projectsedit

Research project clustersedit

AI and networksedit

AI and Networks is the current primary project cluster. It includes AI for Networks, Networks for AI, data pruning for decentralized learning, communication-aware evaluation, cross-silo reliability, and distributed computation for Wasserstein-style distributional references.

Distributed Wasserstein barycentersedit

Distributed Wasserstein barycenter is a technical project within the AI-and-networks cluster. It asks how multiple parties can compute or approximate a shared distributional reference from local empirical measures, with applications to collaborative evaluation, sample scoring, and synthetic-data verification.

Machine unlearningedit

Machine Unlearning includes both approximate certified unlearning for differentiable models and exact or efficient unlearning for tree ensembles. Project pages include Hessian-Free Online Certified Unlearning, Beyond Binary Erasure: Soft-Weighted Unlearning for Fairness and Robustness, and DynFrs: An Efficient Framework for Machine Unlearning in Random Forest.

Collaborative evaluationedit

Collaborative Evaluation studies verification without raw-data exchange. It is used in the ICML 2026 model-collapse work to replace a single low-resource, biased verifier with multi-party Wasserstein-geometry proxies.

Synthetic dataedit

Synthetic Data asks when generated data can safely replace or augment real data, and when recursive training amplifies bias or erodes diversity. The current emphasis is low-resource communities, where fragmented real-data coverage makes local filtering more likely to prune valid tail modes. The main paper page is When Sample Selection Bias Precipitates Model Collapse.