Showing 2026Show all
2 papers · 1 filter
cs.LG2026
Sub-JEPA: Subspace Gaussian Regularization for Stable End-to-End World Models
Kai Zhao, Dongliang Nie, Yuchen Lin +4
Joint-Embedding Predictive Architectures (JEPAs) provide a simpleframework for learning world models by predicting future latent representations.However, JEPA training is subject t…
cs.LG2026
Learning to Select Visual In-Context Demonstrations
Eugene Lee, Yu-Chi Lin, Jiajie Diao
Multimodal Large Language Models (MLLMs) adapt to visual tasks via in-context learning (ICL), which relies heavily on demonstration quality. The dominant demonstration selection st…