{"url":"/task/zero-shot-generalization","name":"Zero-shot Generalization","slug":"zero-shot-generalization","description_markdown":null,"categories":[{"name":"Methodology","url":"/area/methodology"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":572,"papers_with_code":301,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"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":1,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/zero-shot-generalization-on-calvin","slug":"zero-shot-generalization-on-calvin","dataset":"CALVIN","dataset_url":"/dataset/calvin-composing-actions-from-language-and","rows_in_archive":5,"metrics":["Avg. sequence length"],"first_row_in_archive_order":{"model":"GR-MG","paper_title":"GR-MG: Leveraging Partially Annotated Data via Multi-Modal Goal-Conditioned Policy","paper_url":"/paper/gr-mg-leveraging-partially-annotated-data-via","paper_date":"2024-08-26","arxiv_id":"2408.14368","code_links":[{"title":"bytedance/GR-MG","url":"https://github.com/bytedance/GR-MG"}],"syntology":{"n":10,"n_ran":8,"n_unverified":2,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/calvin-composing-actions-from-language-and","name":"CALVIN","full_name":"Composing Actions from Language and Vision","num_papers_in_archive":65}],"subtasks":[],"parent_tasks":[],"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":30,"of":301,"tagged_in_all":572,"items":[{"url":"/paper/multitask-prompted-training-enables-zero-shot-1","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","date":"2021-10-15","arxiv_id":"2110.08207","repositories_listed":8,"syntology":{"n":15,"n_ran":8,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/generalization-without-systematicity-on-the","title":"Generalization without systematicity: On the compositional skills of sequence-to-sequence recurrent networks","date":"2017-10-31","arxiv_id":"1711.00350","repositories_listed":7,"syntology":null},{"url":"/paper/zoedepth-zero-shot-transfer-by-combining","title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","date":"2023-02-23","arxiv_id":"2302.12288","repositories_listed":6,"syntology":{"n":16,"n_ran":10,"n_unverified":6,"n_pointer_only":1}},{"url":"/paper/repurposing-diffusion-based-image-generators","title":"Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation","date":"2023-12-04","arxiv_id":"2312.02145","repositories_listed":4,"syntology":{"n":26,"n_ran":14,"n_unverified":12,"n_pointer_only":0}},{"url":"/paper/learning-tsp-requires-rethinking","title":"Learning the Travelling Salesperson Problem Requires Rethinking Generalization","date":"2020-06-12","arxiv_id":"2006.07054","repositories_listed":4,"syntology":{"n":7,"n_ran":3,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/towards-scalable-multi-domain-conversational","title":"Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset","date":"2019-09-12","arxiv_id":"1909.05855","repositories_listed":4,"syntology":null},{"url":"/paper/learning-transferable-cooperative-behavior-in","title":"Learning Transferable Cooperative Behavior in Multi-Agent Teams","date":"2019-06-04","arxiv_id":"1906.01202","repositories_listed":4,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/seg-zero-reasoning-chain-guided-segmentation","title":"Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement","date":"2025-03-09","arxiv_id":"2503.06520","repositories_listed":3,"syntology":null},{"url":"/paper/visual-autoregressive-modeling-scalable-image","title":"Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction","date":"2024-04-03","arxiv_id":"2404.02905","repositories_listed":3,"syntology":{"n":11,"n_ran":5,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/learning-to-route-among-specialized-experts","title":"Learning to Route Among Specialized Experts for Zero-Shot Generalization","date":"2024-02-08","arxiv_id":"2402.05859","repositories_listed":3,"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/unleashing-large-scale-video-generative-pre","title":"Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation","date":"2023-12-20","arxiv_id":"2312.13139","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/promptunet-toward-interactive-medical-image","title":"One-Prompt to Segment All Medical Images","date":"2023-05-17","arxiv_id":"2305.10300","repositories_listed":3,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/from-images-to-textual-prompts-zero-shot-vqa","title":"From Images to Textual Prompts: Zero-shot VQA with Frozen Large Language Models","date":"2022-12-21","arxiv_id":"2212.10846","repositories_listed":3,"syntology":null},{"url":"/paper/metamorph-learning-universal-controllers-with-1","title":"MetaMorph: Learning Universal Controllers with Transformers","date":"2022-03-22","arxiv_id":"2203.11931","repositories_listed":3,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/the-scattering-compositional-learner","title":"The Scattering Compositional Learner: Discovering Objects, Attributes, Relationships in Analogical Reasoning","date":"2020-07-08","arxiv_id":"2007.04212","repositories_listed":3,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/memory-augmented-recursive-neural-networks","title":"Compositional Generalization with Tree Stack Memory Units","date":"2019-11-05","arxiv_id":"1911.01545","repositories_listed":3,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/convolutional-conditional-neural-processes-1","title":"Convolutional Conditional Neural Processes","date":"2019-10-29","arxiv_id":"1910.13556","repositories_listed":3,"syntology":null},{"url":"/paper/desta2-5-audio-toward-general-purpose-large","title":"DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment","date":"2025-07-03","arxiv_id":"2507.02768","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/zero-shot-whole-body-humanoid-control-via","title":"Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation Models","date":"2025-04-15","arxiv_id":"2504.11054","repositories_listed":2,"syntology":{"n":31,"n_ran":16,"n_unverified":15,"n_pointer_only":31}},{"url":"/paper/efficient-alignment-of-unconditioned-action","title":"Efficient Alignment of Unconditioned Action Prior for Language-conditioned Pick and Place in Clutter","date":"2025-03-12","arxiv_id":"2503.09423","repositories_listed":2,"syntology":null},{"url":"/paper/foundationstereo-zero-shot-stereo-matching","title":"FoundationStereo: Zero-Shot Stereo Matching","date":"2025-01-17","arxiv_id":"2501.09898","repositories_listed":2,"syntology":{"n":46,"n_ran":36,"n_unverified":10,"n_pointer_only":46}},{"url":"/paper/improving-zero-shot-object-level-change","title":"Improving Zero-Shot Object-Level Change Detection by Incorporating Visual Correspondence","date":"2025-01-09","arxiv_id":"2501.05555","repositories_listed":2,"syntology":null},{"url":"/paper/madation-face-morphing-attack-detection-with","title":"MADation: Face Morphing Attack Detection with Foundation Models","date":"2025-01-07","arxiv_id":"2501.03800","repositories_listed":2,"syntology":null},{"url":"/paper/clear-conv-like-linearization-revs-pre","title":"CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up","date":"2024-12-20","arxiv_id":"2412.16112","repositories_listed":2,"syntology":{"n":13,"n_ran":2,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/mmpt-multimodal-prompt-tuning-for-zero-shot","title":"M$^2$PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning","date":"2024-09-24","arxiv_id":"2409.15657","repositories_listed":2,"syntology":{"n":26,"n_ran":16,"n_unverified":10,"n_pointer_only":26}},{"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/gomaa-geo-goal-modality-agnostic-active-geo","title":"GOMAA-Geo: GOal Modality Agnostic Active Geo-localization","date":"2024-06-04","arxiv_id":"2406.01917","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/mvmoe-multi-task-vehicle-routing-solver-with","title":"MVMoE: Multi-Task Vehicle Routing Solver with Mixture-of-Experts","date":"2024-05-02","arxiv_id":"2405.01029","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/fastsam3d-an-efficient-segment-anything-model","title":"FastSAM3D: An Efficient Segment Anything Model for 3D Volumetric Medical Images","date":"2024-03-14","arxiv_id":"2403.09827","repositories_listed":2,"syntology":{"n":12,"n_ran":5,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/rsbuilding-towards-general-remote-sensing","title":"RSBuilding: Towards General Remote Sensing Image Building Extraction and Change Detection with Foundation Model","date":"2024-03-12","arxiv_id":"2403.07564","repositories_listed":2,"syntology":null}],"syntology_records":20,"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"}}