3 papers
cs.LG2026
FlowMPC: Improving Flow Matching policies with World Models
Chandon Hamel
Flow Matching (FM) is a powerful approach for behavior cloning in multimodal action spaces [Jiang et al., 2025], but because it is not trained to directly maximize expected return,…
cs.CV2025
Analysis of Bias in Deep Learning Facial Beauty Regressors
Chandon Hamel, Mike Busch
Bias can be introduced to AI systems even from seemingly balanced sources, and AI facial beauty prediction is subject to ethnicity-based bias. This work sounds warnings about AI's…
cs.CV2025
GANji: A Framework for Introductory AI Image Generation
Chandon Hamel, Mike Busch
The comparative study of generative models often requires significant computational resources, creating a barrier for researchers and practitioners. This paper introduces GANji, a…