{"id":19704629,"url":"https://github.com/higgsfield/interaction_network_pytorch","last_synced_at":"2025-10-02T19:31:33.052Z","repository":{"id":49983116,"uuid":"115491152","full_name":"higgsfield/interaction_network_pytorch","owner":"higgsfield","description":"Pytorch Implementation of Interaction Networks for Learning about Objects, Relations and Physics","archived":false,"fork":false,"pushed_at":"2017-12-27T09:51:53.000Z","size":668,"stargazers_count":130,"open_issues_count":2,"forks_count":16,"subscribers_count":6,"default_branch":"master","last_synced_at":"2025-04-05T17:51:11.938Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/higgsfield.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2017-12-27T06:49:32.000Z","updated_at":"2025-03-26T15:49:15.000Z","dependencies_parsed_at":"2022-09-19T07:40:57.949Z","dependency_job_id":null,"html_url":"https://github.com/higgsfield/interaction_network_pytorch","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/higgsfield/interaction_network_pytorch","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/higgsfield%2Finteraction_network_pytorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/higgsfield%2Finteraction_network_pytorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/higgsfield%2Finteraction_network_pytorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/higgsfield%2Finteraction_network_pytorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/higgsfield","download_url":"https://codeload.github.com/higgsfield/interaction_network_pytorch/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/higgsfield%2Finteraction_network_pytorch/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":278061384,"owners_count":25923503,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-10-02T02:00:08.890Z","response_time":67,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-11-11T21:23:39.451Z","updated_at":"2025-10-02T19:31:32.738Z","avatar_url":"https://github.com/higgsfield.png","language":"Jupyter Notebook","funding_links":[],"categories":["Paper implementations｜论文实现","Paper implementations"],"sub_categories":["Other libraries｜其他库:","Other libraries:"],"readme":"# Interaction-Network-Pytorch\nPytorch Implementraion of [Interaction Networks for Learning about Objects, Relations and Physics](https://arxiv.org/abs/1612.00222).\n\nInteraction Network is a powerful graph based framework for dynamic systems. It is able to simulate the physical trajectories of n-body, bouncing ball, and non-rigid string systems accurately over thousands of time steps, after training only on single step predictions.\n\n*Our results provide surprisingly strong evidence of IN’s ability to learn accurate physical simulations and generalize their training to novel systems with different numbers and configurations of objects and relations… Our interaction network implementation is the first learnable physics engine than can scale up to real-world problems, and is a promising template for new AI approaches to reasoning about other physical and mechanical systems, scene understanding, social perception, hierarchical planning, and analogical reasoning.* \n\nAlso see nice [blog post](https://blog.acolyer.org/2017/01/02/interaction-networks-for-learning-about-objects-relations-and-physics/) and [keynote](https://www.slideshare.net/KenKuroki/interaction-networks-for-learning-about-objects-relations-and-physics).\n\nThanks to [jaesik817 tensorflow implementation](https://github.com/jaesik817/Interaction-networks_tensorflow) for Physics Engine. \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhiggsfield%2Finteraction_network_pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhiggsfield%2Finteraction_network_pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhiggsfield%2Finteraction_network_pytorch/lists"}