NeurIPS paper: Joint Energy Models show human vision aligns between generative and discriminative

ShahabBakht · x · 2026-11-18

A NeurIPS 2026 paper argues vision is explained by neither purely generative nor discriminative learning. Training a single Joint Energy-based Model (JEM) across the generative↔discriminative continuum via an interpolation parameter α, the authors evaluate human alignment on six tasks (gloss perception, similarity, response distributions, diagnostic features, OOD generalization, shape-texture bias) using ImageNet, synthetic and CIFAR-10 data. Alignment peaks in the middle of the continuum, suggesting human-like vision needs both objectives.

Original post →

More from Research

Research channel →