{"url":"/task/embodied-question-answering","name":"Embodied Question Answering","slug":"embodied-question-answering","description_markdown":null,"categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":40,"papers_with_code":14,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":[],"datasets":[{"url":"/dataset/eqa","name":"EQA","full_name":"Embodied Question Answering","num_papers_in_archive":87},{"url":"/dataset/openeqa","name":"OpenEQA","full_name":"","num_papers_in_archive":0}],"subtasks":[],"parent_tasks":[{"url":"/task/visual-question-answering","name":"Visual Question Answering (VQA)"}],"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":14,"of":14,"tagged_in_all":40,"items":[{"url":"/paper/embodied-question-answering","title":"Embodied Question Answering","date":"2017-11-30","arxiv_id":"1711.11543","repositories_listed":4,"syntology":null},{"url":"/paper/cityeqa-a-hierarchical-llm-agent-on-embodied","title":"CityEQA: A Hierarchical LLM Agent on Embodied Question Answering Benchmark in City Space","date":"2025-02-18","arxiv_id":"2502.12532","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_unverified":2,"n_pointer_only":4}},{"url":"/paper/towards-learning-a-generalist-model-for","title":"Towards Learning a Generalist Model for Embodied Navigation","date":"2023-12-04","arxiv_id":"2312.02010","repositories_listed":2,"syntology":{"n":15,"n_ran":10,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/neural-modular-control-for-embodied-question","title":"Neural Modular Control for Embodied Question Answering","date":"2018-10-26","arxiv_id":"1810.11181","repositories_listed":2,"syntology":{"n":11,"n_ran":0,"n_unverified":11,"n_pointer_only":11}},{"url":"/paper/tarsier2-advancing-large-vision-language","title":"Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video Understanding","date":"2025-01-14","arxiv_id":"2501.07888","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":4}},{"url":"/paper/lscenellm-enhancing-large-3d-scene","title":"LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual Preferences","date":"2024-12-02","arxiv_id":"2412.01292","repositories_listed":1,"syntology":{"n":11,"n_ran":6,"n_unverified":5,"n_pointer_only":11}},{"url":"/paper/mfe-etp-a-comprehensive-evaluation-benchmark","title":"MFE-ETP: A Comprehensive Evaluation Benchmark for Multi-modal Foundation Models on Embodied Task Planning","date":"2024-07-06","arxiv_id":"2407.05047","repositories_listed":1,"syntology":null},{"url":"/paper/map-based-modular-approach-for-zero-shot","title":"Map-based Modular Approach for Zero-shot Embodied Question Answering","date":"2024-05-26","arxiv_id":"2405.16559","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-embodied-interactive-agent-for","title":"MEIA: Multimodal Embodied Perception and Interaction in Unknown Environments","date":"2024-02-01","arxiv_id":"2402.00290","repositories_listed":1,"syntology":null},{"url":"/paper/synthesizing-event-centric-knowledge-graphs","title":"Synthesizing Event-centric Knowledge Graphs of Daily Activities Using Virtual Space","date":"2023-07-30","arxiv_id":"2307.16206","repositories_listed":1,"syntology":null},{"url":"/paper/allenact-a-framework-for-embodied-ai-research","title":"AllenAct: A Framework for Embodied AI Research","date":"2020-08-28","arxiv_id":"2008.12760","repositories_listed":1,"syntology":null},{"url":"/paper/videonavqa-bridging-the-gap-between-visual","title":"VideoNavQA: Bridging the Gap between Visual and Embodied Question Answering","date":"2019-08-14","arxiv_id":"1908.04950","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/multi-target-embodied-question-answering","title":"Multi-Target Embodied Question Answering","date":"2019-04-09","arxiv_id":"1904.04686","repositories_listed":1,"syntology":null},{"url":"/paper/blindfold-baselines-for-embodied-qa","title":"Blindfold Baselines for Embodied QA","date":"2018-11-12","arxiv_id":"1811.05013","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}}],"syntology_records":7,"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":"2026-09-25T09:33:49+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"}}