vjepa

High-throughput, resume-safe vision and video embedding pipelines for VLM datasets—26 pinned encoders, streaming Hugging Face ingestion, and Safetensors shard commits.

Open-source vision stack with stereo camera hardware, GPU processing, and AI agent for training video classifiers.

vjepa / vjepa2 / vjepa2.1 PCA visualization utility for dense features and world model inspection.

Assess Data Quality Before Annotation or Labelled Data Quality after Annotation (Txt files/Yolo Format). Visualise the patterns covered by each class/activity.

Can the V-JEPA2 model be used as a world model?

Masked Multi-Component Gated Decomposition Architecture

V-JEPA for Gray-Scott dynamics. Initial work produced during the 24-hour Hack the World(s) hackathon. 1st place 🏆

A physics-based video search engine using Meta's V-JEPA 2 world model to find videos with similar motion dynamics.

Patch-level predictive surprise from video foundation model embeddings. The embedding delta is the attention signal.

End-to-end engineering of a V-JEPA-style video world-model trainer: data curation at scale, distributed (FSDP) training, and inference optimization. From-scratch JEPA + SIGReg.

GranularVAR: Multi-scale video understanding with augmentation-graded contrastive learning and calibrated uncertainty. V-JEPA 2 encoder + granularity-conditioned decoder. GWU MS Data Science Capstone, Spring 2026.

SCOUT: frozen-encoder embedding-space prediction for sim-to-real text-based person retrieval. ECCV 2026 Workshop (AI City Challenge Track 4), accepted as a poster.

Locally-Hosted Media Gallery App with AI Similarity Search