Blog

Writing about my research in computer vision, multi-agent systems, and AI for social good to make the research more accessible.

Research Multi-Agent Diffusion Models

Diffusion Forcing for Multi-Agent Interaction

One autoregressive diffusion model that generates coordinated human motion — for any task, any group size, any duration. We introduce MAGNet, a unified framework tackling the full spectrum of multi-person motion generation.

2025 · 10 min read
Research Computer Vision Motion Prediction

It Takes Two: How We Taught AI to Predict Dance Through Social Interaction

Does knowing your partner's movements help predict your own future motion? We tackle this question using 30 hours of swing dancing data and show that social conditioning cuts prediction error by 52%.

2024 · 8 min read
Research GANs Fairness

When GANs See Race: How Training Data Shapes Who Gets Generated

A deep dive into how racial composition of datasets impacts generative image models — from truncation tricks that erase minority representation to annotator biases that distort quality metrics.

2022 · 6 min read