VL-JEPA (Vision-Language Joint Embedding Predictive Architecture) in MLX

v-jepa2 开源项目推荐(8 个)
v-jepa2 话题在 GitHub 上没有填写简介,这里按 Star 数汇总最相关的热门仓库。
热门项目 全部 8
GitHub 共 8 个仓库,已全部展示Reproduction of Interpreting Physics in Video World Models (PEZ, arXiv:2602.07050) — layer-wise linear probing of V-JEPA 2 physics representations
Local-first Notion health tracker with TRIBEv2 brain analysis, AI health insights, symptom logging, goals, medications, appointments, and a browser UI
A physics-based video search engine using Meta's V-JEPA 2 world model to find videos with similar motion dynamics.
A quaternion-enhanced Video Joint-Embedding Predictive Architecture with continuous spectral autoencoders, Fourier-domain topology, and a 2D torus latent space for world model learning.
Educational implementation of V-JEPA (Video Joint Embedding Predictive Architecture) in PyTorch. Includes Conv3D tubelet embeddings, Video ViT, EMA target encoder, spatiotemporal masking, linear probing, retrieval evaluation, and effective-rank analysis on Something-Something V2.
Grounding Spatial Representations via Visual World Models for Robust Autoregressive Drift Reduction in Low-Power Robot Telemetry
Real-time Traffic Anomaly Detection With JEPA
关于这个话题
- 清单取自 GitHub 话题页并按 Star 数排序,每次展示前 8 个项目;原始页面见 https://github.com/topics/v-jepa2。
- 该话题在 GitHub 上共有 8 个仓库, 本站收录的是其中最热门的 8 个,不是全量列表。
- Star / Fork 每日自动刷新一次,实时数据以 GitHub 为准。
- 当前 8 个项目累计 114 Star,覆盖 1 种主要语言,数据更新于 2026-11-11。
- 中文介绍来自 GitHub 官方话题说明(github/explore)的机器翻译,可点「查看原文」对照;译文缺失时会先展示原文。