Showing 2026Show all
2 papers · 1 filter
stat.ME2026
MediEncoder: Nonlinear Representation Learning for High-Dimensional Causal Mediation Analysis
Shi Bo, Debarghya Mukherjee, AmirEmad Ghassami
Causal mediation analysis decomposes a treatment effect into indirect pathways through mediators and direct pathways not operating through them. Modern biomedical studies often inv…
cs.LG2026
Towards General Preference Alignment: Diffusion Models at Nash Equilibrium
Jiaming Hu, Jiamu Bai, Haoyu Wang +2
Reinforcement learning from human feedback (RLHF) has been popular for aligning text-to-image (T2I) diffusion models with human preferences. As a mainstream branch of RLHF, Direct…