facebookresearch / IntPhys2Links
This is the code repository for IntPhys 2, a video benchmark designed to evaluate the intuitive physics understanding of deep learning models.
☆62Updated last month
Alternatives and similar repositories for IntPhys2
Users that are interested in IntPhys2 are comparing it to the libraries listed below
Sorting:
- This repo contains the code for the paper "Intuitive physics understanding emerges fromself-supervised pretraining on natural videos"☆172Updated 5 months ago
- Implementation of the Large Behavioral Model architecture for dexterous manipulation from Toyota Research Institute☆45Updated this week
- ☆228Updated 4 months ago
- Theia: Distilling Diverse Vision Foundation Models for Robot Learning☆245Updated 4 months ago
- Nvidia GEAR Lab's initiative to solve the robotics data problem using world models☆258Updated this week
- Implementation of Flow Policy Optimization (FPO)☆188Updated 2 weeks ago
- [ICLR'25] LLaRA: Supercharging Robot Learning Data for Vision-Language Policy☆221Updated 4 months ago
- Official implementation of the paper "EgoPet: Egomotion and Interaction Data from an Animal's Perspective".☆26Updated last year
- Clarity: A Minimalist Website Template for AI Research☆130Updated 7 months ago
- [ICML'25] The PyTorch implementation of paper: "AdaWorld: Learning Adaptable World Models with Latent Actions".☆133Updated last month
- NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Tasks☆161Updated 2 weeks ago
- Pytorch implementation of "Genie: Generative Interactive Environments", Bruce et al. (2024).☆181Updated 11 months ago
- ☆76Updated 2 months ago
- Cosmos-Predict1 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world m…☆309Updated last week
- ☆163Updated 5 months ago
- [ICML 2024] A Touch, Vision, and Language Dataset for Multimodal Alignment☆81Updated 2 months ago
- Cosmos-Predict2 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world m…☆440Updated last week
- [ICLR 2025] LAPA: Latent Action Pretraining from Videos☆348Updated 6 months ago
- OpenVLA: An open-source vision-language-action model for robotic manipulation.☆231Updated 4 months ago
- Official repository for "iVideoGPT: Interactive VideoGPTs are Scalable World Models" (NeurIPS 2024), https://arxiv.org/abs/2405.15223☆137Updated 2 months ago
- Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long c…☆589Updated this week
- ☆121Updated 5 months ago
- Code release for ICLR 2023 paper: SlotFormer on object-centric dynamics models☆112Updated last year
- [ICLR 2025] Official implementation and benchmark evaluation repository of <PhysBench: Benchmarking and Enhancing Vision-Language Models …☆67Updated 2 months ago
- Visualizing the DROID dataset using Rerun☆76Updated 2 months ago
- Benchmarking physical understanding in generative video models☆189Updated 2 months ago
- Official Reporsitory of "RoboEngine: Plug-and-Play Robot Data Augmentation with Semantic Robot Segmentation and Background Generation"☆119Updated 2 months ago
- Embodied Reasoning Question Answer (ERQA) Benchmark☆197Updated 5 months ago
- Generative World Explorer☆153Updated last month
- Official repository of Learning to Act from Actionless Videos through Dense Correspondences.☆225Updated last year