{"url":"/task/robot-manipulation-generalization","name":"Robot Manipulation Generalization","slug":"robot-manipulation-generalization","description_markdown":null,"categories":[{"name":"Robots","url":"/area/robots"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":19,"papers_with_code":17,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/robot-manipulation-generalization-on-the","slug":"robot-manipulation-generalization-on-the","dataset":"The COLOSSEUM","dataset_url":"/dataset/the-colosseum","rows_in_archive":9,"metrics":["Average decrease average across all perturbations"],"first_row_in_archive_order":{"model":"RVT","paper_title":"0/1 Deep Neural Networks via Block Coordinate Descent","paper_url":"/paper/0-1-deep-neural-networks-via-block-coordinate","paper_date":"2022-06-19","arxiv_id":"2206.09379","code_links":[],"syntology":null}},{"leaderboard":"/sota/robot-manipulation-generalization-on-gembench","slug":"robot-manipulation-generalization-on-gembench","dataset":"GEMBench","dataset_url":"/dataset/rlbench","rows_in_archive":6,"metrics":["Average Success Rate","Average Success Rate (L1)","Average Success Rate (L2)","Average Success Rate (L3)","Average Success Rate (L4)"],"first_row_in_archive_order":{"model":"3D-LOTUS++","paper_title":"Towards Generalizable Vision-Language Robotic Manipulation: A Benchmark and LLM-guided 3D Policy","paper_url":"/paper/towards-generalizable-vision-language-robotic","paper_date":"2024-10-02","arxiv_id":"2410.01345","code_links":[{"title":"vlc-robot/robot-3dlotus","url":"https://github.com/vlc-robot/robot-3dlotus"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}}}],"datasets":[{"url":"/dataset/rlbench","name":"RLBench","full_name":"","num_papers_in_archive":167},{"url":"/dataset/the-colosseum","name":"The COLOSSEUM","full_name":"The COLOSSEUM: A Benchmark for Evaluating Generalization for Robotic Manipulation","num_papers_in_archive":13}],"subtasks":[],"parent_tasks":[{"url":"/task/robot-manipulation","name":"Robot Manipulation"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":17,"of":17,"tagged_in_all":19,"items":[{"url":"/paper/segment-anything","title":"Segment Anything","date":"2023-04-05","arxiv_id":"2304.02643","repositories_listed":32,"syntology":{"n":23,"n_ran":8,"n_unverified":15,"n_pointer_only":0}},{"url":"/paper/2408-00714","title":"SAM 2: Segment Anything in Images and Videos","date":"2024-08-01","arxiv_id":"2408.00714","repositories_listed":11,"syntology":{"n":49,"n_ran":28,"n_unverified":21,"n_pointer_only":0}},{"url":"/paper/sam2rad-a-segmentation-model-for-medical","title":"Sam2Rad: A Segmentation Model for Medical Images with Learnable Prompts","date":"2024-09-10","arxiv_id":"2409.06821","repositories_listed":2,"syntology":null},{"url":"/paper/segment-anything-for-videos-a-systematic","title":"Segment Anything for Videos: A Systematic Survey","date":"2024-07-31","arxiv_id":"2408.08315","repositories_listed":2,"syntology":null},{"url":"/paper/instruction-driven-history-aware-policies-for","title":"Instruction-driven history-aware policies for robotic manipulations","date":"2022-09-11","arxiv_id":"2209.04899","repositories_listed":2,"syntology":{"n":11,"n_ran":0,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/towards-generalizable-vision-language-robotic","title":"Towards Generalizable Vision-Language Robotic Manipulation: A Benchmark and LLM-guided 3D Policy","date":"2024-10-02","arxiv_id":"2410.01345","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/sam2-adapter-evaluating-adapting-segment","title":"SAM2-Adapter: Evaluating & Adapting Segment Anything 2 in Downstream Tasks: Camouflage, Shadow, Medical Image Segmentation, and More","date":"2024-08-08","arxiv_id":"2408.04579","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/generative-image-as-action-models","title":"Generative Image as Action Models","date":"2024-07-10","arxiv_id":"2407.07875","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/rvt-2-learning-precise-manipulation-from-few","title":"RVT-2: Learning Precise Manipulation from Few Demonstrations","date":"2024-06-12","arxiv_id":"2406.08545","repositories_listed":1,"syntology":{"n":15,"n_ran":15,"n_unverified":0,"n_pointer_only":15}},{"url":"/paper/evaluating-real-world-robot-manipulation","title":"Evaluating Real-World Robot Manipulation Policies in Simulation","date":"2024-05-09","arxiv_id":"2405.05941","repositories_listed":1,"syntology":null},{"url":"/paper/3d-diffuser-actor-policy-diffusion-with-3d","title":"3D Diffuser Actor: Policy Diffusion with 3D Scene Representations","date":"2024-02-18","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/the-colosseum-a-benchmark-for-evaluating","title":"THE COLOSSEUM: A Benchmark for Evaluating Generalization for Robotic Manipulation","date":"2024-02-13","arxiv_id":"2402.08191","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":3}},{"url":"/paper/polarnet-3d-point-clouds-for-language-guided","title":"PolarNet: 3D Point Clouds for Language-Guided Robotic Manipulation","date":"2023-09-27","arxiv_id":"2309.15596","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/rvt-robotic-view-transformer-for-3d-object","title":"RVT: Robotic View Transformer for 3D Object Manipulation","date":"2023-06-26","arxiv_id":"2306.14896","repositories_listed":1,"syntology":null},{"url":"/paper/perceiver-actor-a-multi-task-transformer-for","title":"Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation","date":"2022-09-12","arxiv_id":"2209.05451","repositories_listed":1,"syntology":null},{"url":"/paper/r3m-a-universal-visual-representation-for","title":"R3M: A Universal Visual Representation for Robot Manipulation","date":"2022-03-23","arxiv_id":"2203.12601","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_unverified":3,"n_pointer_only":6}},{"url":"/paper/masked-visual-pre-training-for-motor-control","title":"Masked Visual Pre-training for Motor Control","date":"2022-03-11","arxiv_id":"2203.06173","repositories_listed":1,"syntology":null}],"syntology_records":10,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}