{"task":"Zero-shot Generalization","dataset":"CALVIN","metric_names":["Avg. sequence length"],"rows":[{"id":143369,"task":"Zero-shot Generalization","parent_task":null,"dataset":"CALVIN","model_name":"GR-MG","metrics":{"Avg. sequence length":"4.04"},"paper_url":"https://arxiv.org/abs/2408.14368v2","paper_title":"GR-MG: Leveraging Partially Annotated Data via Multi-Modal Goal-Conditioned Policy","paper_date":"2024-08-26","code_links":[{"title":"bytedance/GR-MG","url":"https://github.com/bytedance/GR-MG"}],"metrics_order":"[\"Avg. sequence length\"]","area":"Methodology","uses_additional_data":1,"source":"archive","tags":[]},{"id":143370,"task":"Zero-shot Generalization","parent_task":null,"dataset":"CALVIN","model_name":"MoDE","metrics":{"Avg. sequence length":"4.01"},"paper_url":"https://arxiv.org/abs/2412.12953v1","paper_title":"Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning","paper_date":"2024-12-17","code_links":[{"title":"intuitive-robots/MoDE_Diffusion_Policy","url":"https://github.com/intuitive-robots/MoDE_Diffusion_Policy"}],"metrics_order":"[\"Avg. sequence length\"]","area":"Methodology","uses_additional_data":1,"source":"archive","tags":[]},{"id":143371,"task":"Zero-shot Generalization","parent_task":null,"dataset":"CALVIN","model_name":"RoboUniView","metrics":{"Avg. sequence length":"3.647"},"paper_url":"https://arxiv.org/abs/2406.18977v3","paper_title":"RoboUniView: Visual-Language Model with Unified View Representation for Robotic Manipulation","paper_date":"2024-06-27","code_links":[{"title":"liufanfanlff/robouniview","url":"https://github.com/liufanfanlff/robouniview"}],"metrics_order":"[\"Avg. sequence length\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":143372,"task":"Zero-shot Generalization","parent_task":null,"dataset":"CALVIN","model_name":"3D Diffuser Actor","metrics":{"Avg. sequence length":"3.27"},"paper_url":"https://arxiv.org/abs/2402.10885","paper_title":"3D Diffuser Actor: Policy Diffusion with 3D Scene Representations","paper_date":"2024-02-18","code_links":[{"title":"nickgkan/3d_diffuser_actor","url":"https://github.com/nickgkan/3d_diffuser_actor"}],"metrics_order":"[\"Avg. sequence length\"]","area":"Methodology","uses_additional_data":0,"source":"archive","tags":[]},{"id":143373,"task":"Zero-shot Generalization","parent_task":null,"dataset":"CALVIN","model_name":"GR-1","metrics":{"Avg. sequence length":"3.06"},"paper_url":"https://arxiv.org/abs/2312.13139v2","paper_title":"Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation","paper_date":"2023-12-20","code_links":[{"title":"bytedance/gr-1","url":"https://github.com/bytedance/gr-1"},{"title":"bytedance/GR-MG","url":"https://github.com/bytedance/GR-MG"},{"title":"GR1-Manipulation/GR-1","url":"https://github.com/GR1-Manipulation/GR-1"}],"metrics_order":"[\"Avg. sequence length\"]","area":"Methodology","uses_additional_data":1,"source":"archive","tags":[]}]}