Pytorch implementation of "Genie: Generative Interactive Environments", Bruce et al. (2024).
☆267Aug 21, 2024Updated last year
Alternatives and similar repositories for open-genie
Users that are interested in open-genie are comparing it to the libraries listed below
Sorting:
- JAX reimplementation of the DeepMind paper "Genie: Generative Interactive Environments"☆101Jan 23, 2025Updated last year
- A framework for training world models with virtual environments, complete with annotated environment dataset (RetroAct), exploration agen…☆71Oct 25, 2025Updated 4 months ago
- Official repository of Learning to Act from Actionless Videos through Dense Correspondences.☆248Apr 25, 2024Updated last year
- world modeling challenge for humanoid robots☆554Nov 8, 2024Updated last year
- [ICLR 2025] LAPA: Latent Action Pretraining from Videos☆472Jan 22, 2025Updated last year
- Code for the ICLR 2024 spotlight paper: "Learning to Act without Actions" (introducing Latent Action Policies)☆134Jul 31, 2024Updated last year
- ☆142Jul 8, 2025Updated 7 months ago
- code for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"☆1,169Nov 9, 2025Updated 3 months ago
- Official repository for "iVideoGPT: Interactive VideoGPTs are Scalable World Models" (NeurIPS 2024), https://arxiv.org/abs/2405.15223☆167Sep 23, 2025Updated 5 months ago
- Evaluating and reproducing real-world robot manipulation policies (e.g., RT-1, RT-1-X, Octo) in simulation under common setups (e.g., Goo…☆980Dec 20, 2025Updated 2 months ago
- ☆94Sep 4, 2024Updated last year
- [NeurIPS 2024] CLOVER: Closed-Loop Visuomotor Control with Generative Expectation for Robotic Manipulation☆133Sep 8, 2025Updated 5 months ago
- Code for "Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation"☆300Apr 22, 2024Updated last year
- Official code for "Behavior Generation with Latent Actions" (ICML 2024 Spotlight)☆197Feb 28, 2024Updated 2 years ago
- [ICML 2025] Official PyTorch Implementation of "History-Guided Video Diffusion"☆630Jul 1, 2025Updated 8 months ago
- [ICCV2025 Oral] Latent Motion Token as the Bridging Language for Learning Robot Manipulation from Videos☆164Oct 1, 2025Updated 5 months ago
- [RSS 2024] Learning Manipulation by Predicting Interaction☆120Jul 2, 2025Updated 8 months ago
- Official implementation of GR-MG☆93Jan 12, 2025Updated last year
- Cosmos-Predict1 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world m…☆414Jan 6, 2026Updated last month
- dataloading is my passion☆75May 2, 2024Updated last year
- ☆443Nov 29, 2025Updated 3 months ago
- Heterogeneous Pre-trained Transformer (HPT) as Scalable Policy Learner.☆529Dec 6, 2024Updated last year
- ElasticTok: Adaptive Tokenization for Image and Video☆88Nov 4, 2024Updated last year
- Official Code Repo for GENIMA☆77Oct 29, 2025Updated 4 months ago
- Pandora: Towards General World Model with Natural Language Actions and Video States☆532Sep 23, 2024Updated last year
- OpenVLA: An open-source vision-language-action model for robotic manipulation.☆5,383Mar 23, 2025Updated 11 months ago
- (CVPR 2025) A Data-Centric Revisit of Pre-Trained Vision Models for Robot Learning☆24Mar 11, 2025Updated 11 months ago
- [TMLR 2024] Official PyTorch Implementation of Deep Dynamic Latent Particles☆16Feb 8, 2024Updated 2 years ago
- ☆19Jun 26, 2024Updated last year
- List of papers on video-centric robot learning☆22Nov 16, 2024Updated last year
- SEED-Voken: A Series of Powerful Visual Tokenizers☆996Nov 25, 2025Updated 3 months ago
- Octo is a transformer-based robot policy trained on a diverse mix of 800k robot trajectories.☆1,552Jul 31, 2024Updated last year
- The official codebase for running the experiments described in the AVDC paper.☆20Oct 2, 2024Updated last year
- DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Control☆117Oct 27, 2024Updated last year
- Re-implementation of pi0 vision-language-action (VLA) model from Physical Intelligence☆1,397Jan 31, 2025Updated last year
- ☆323May 22, 2025Updated 9 months ago
- [CVPR 2025] The offical Implementation of "Universal Actions for Enhanced Embodied Foundation Models"☆232Nov 6, 2025Updated 3 months ago
- MAPLE infuses dexterous manipulation priors from egocentric videos into vision encoders, making their features well-suited for downstream…☆29Dec 9, 2025Updated 2 months ago
- A Video Tokenizer Evaluation Dataset☆151Jan 13, 2025Updated last year