Reliable, minimal and scalable library for pretraining foundation and world models
-
Updated
Sep 29, 2026 - Python
Reliable, minimal and scalable library for pretraining foundation and world models
Official code for the paper Graph-level Representation Learning with Joint-Embedding Predictive Architectures published in Transactions on Machine Learning Research (TMLR)
Curated papers, code, datasets, and benchmarks for medical world models in imaging, EHR trajectories, treatment planning, surgical AI, robotics, and virtual-cell simulation.
A PyTorch implementation of a Hierarchical Joint-Embedding Predictive Language Model (H-JEPA-LM) featuring action conditioning and latent-space world model planning.
Reusable world-model-based domain-gap quantification — for perception pipelines and actuator/mechanism models — before any hardware is touched.
Official codebase for TI-JEPA, the Text-Image Joint-Embedding Predictive Architecture. First outlined in our Capstone Project Defense, got 9.9/10
a controlled comparison study of SSL masked-modeling objectives where masked spectrograms reconstruction MAE, masked latent prediction M2D, and joint-embedding prediction Audio-JEPA are pretrained on 52h corpus of Indic speech across 12 languages, all sharing an identical ViT-S/16 encoder and evaluated on the LID & SID tasks of IndicSUPERB
A practical explainer of JEPA, Meta AI’s Joint Embedding Predictive Architecture, with diagrams and insights comparing JEPA and Transformers.
Onramp Sequence Cross-Distillation
PyTorch implementation of "From nucleotides to semantics: genomic representation learning via joint-embedding predictive architecture"
To associate your repository with the joint-embedding-predictive-architecture topic, visit your repo's landing page and select "manage topics."