Tag
JEPA-Anything presents a domain-agnostic framework based on orthogonal predictive factorization for learning predictive models across diverse systems like vision, biology, and control, with demonstrated improvements and experimental validation.
This paper presents a goal-agnostic control framework for partial differential equations using a joint-embedding predictive architecture (JEPA) with a lightweight 2D ViT encoder and action-conditioned latent dynamics, showing that using a learned physical observable probe outperforms raw latent distance for control tasks.
Introduces STST-JEPA, a self-supervised transformer for EEG that predicts masked-token representations, pretrained on 47,703 sessions for brain age regression across ages 5–81.
Introduces DLLM-JEPA, a JEPA formulation for masked diffusion language models that constructs two views from a single input via the diffusion noise schedule, reducing training FLOPs by 33% relative to LLM-JEPA and improving fine-tuning performance on tasks like GSM8K.