{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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 (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":40,"of":40,"of_with_code":14,"tagged_in_all":40,"counts":{"archive_papers_tagged":40,"with_a_code_link":14,"where_syntology_ran_a_sample":6,"not_listed_spam_title":0,"listed":40,"listed_where_code_ran":6,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":5,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":5,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/embodied-question-answering","slug":"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","slug":"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_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/cityeqa-a-hierarchical-llm-agent-on-embodied#ran","syntology_url":"https://syntology.ai/paper/2502.12532","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.12532"}},"official":{"repos":["biluyong/cityeqa","tsinghua-fib-lab/CityEQA"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-learning-a-generalist-model-for","slug":"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_constructed":0,"n_ran_checked":4,"n_instrument":6,"n_unverified":5,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/towards-learning-a-generalist-model-for#ran","syntology_url":"https://syntology.ai/paper/2312.02010","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02010"}},"official":{"repos":["lavi-lab/navillm","zd11024/NaviLLM"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/neural-modular-control-for-embodied-question","slug":"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":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":11,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/neural-modular-control-for-embodied-question#ran","syntology_url":"https://syntology.ai/paper/1810.11181","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.11181"}},"official":null}},{"url":"/paper/tarsier2-advancing-large-vision-language","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tarsier2-advancing-large-vision-language#ran","syntology_url":"https://syntology.ai/paper/2501.07888","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.07888"}},"official":{"repos":["bytedance/tarsier"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/lscenellm-enhancing-large-3d-scene","slug":"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":10,"n_constructed":0,"n_ran_checked":2,"n_instrument":8,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":11,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 8 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/lscenellm-enhancing-large-3d-scene#ran","syntology_url":"https://syntology.ai/paper/2412.01292","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.01292"}},"official":{"repos":["Hoyyyaard/LSceneLLM"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/mfe-etp-a-comprehensive-evaluation-benchmark","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/videonavqa-bridging-the-gap-between-visual#ran","syntology_url":"https://syntology.ai/paper/1908.04950","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.04950"}},"official":{"repos":["catalina17/VideoNavQA"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/multi-target-embodied-question-answering","slug":"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","slug":"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":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/blindfold-baselines-for-embodied-qa#ran","syntology_url":"https://syntology.ai/paper/1811.05013","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.05013"}},"official":{"repos":["ankeshanand/blindfold-baselines-eqa"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":null,"slug":"enter-the-mind-palace-reasoning-and-planning","title":"Enter the Mind Palace: Reasoning and Planning for Long-term Active Embodied Question Answering","date":"2025-07-17","arxiv_id":"2507.12846","repositories_listed":0,"syntology":null},{"url":null,"slug":"tosa-token-merging-with-spatial-awareness","title":"ToSA: Token Merging with Spatial Awareness","date":"2025-06-24","arxiv_id":"2506.20066","repositories_listed":0,"syntology":null},{"url":null,"slug":"general-purpose-robotic-navigation-via-lvlm","title":"General-Purpose Robotic Navigation via LVLM-Orchestrated Perception, Reasoning, and Acting","date":"2025-06-20","arxiv_id":"2506.17462","repositories_listed":0,"syntology":null},{"url":null,"slug":"eqa-rm-a-generative-embodied-reward-model","title":"EQA-RM: A Generative Embodied Reward Model with Test-time Scaling","date":"2025-06-12","arxiv_id":"2506.10389","repositories_listed":0,"syntology":null},{"url":null,"slug":"memory-centric-embodied-question-answer","title":"Memory-Centric Embodied Question Answer","date":"2025-05-20","arxiv_id":"2505.13948","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-the-destination-a-novel-benchmark-for","title":"Beyond the Destination: A Novel Benchmark for Exploration-Aware Embodied Question Answering","date":"2025-03-14","arxiv_id":"2503.11117","repositories_listed":0,"syntology":null},{"url":null,"slug":"vector-quantized-feature-fields-for-fast-3d","title":"Vector Quantized Feature Fields for Fast 3D Semantic Lifting","date":"2025-03-09","arxiv_id":"2503.06469","repositories_listed":0,"syntology":null},{"url":null,"slug":"grapheqa-using-3d-semantic-scene-graphs-for","title":"GraphEQA: Using 3D Semantic Scene Graphs for Real-time Embodied Question Answering","date":"2024-12-19","arxiv_id":"2412.14480","repositories_listed":0,"syntology":null},{"url":null,"slug":"noisyeqa-benchmarking-embodied-question","title":"NoisyEQA: Benchmarking Embodied Question Answering Against Noisy Queries","date":"2024-12-14","arxiv_id":"2412.10726","repositories_listed":0,"syntology":null},{"url":null,"slug":"tango-training-free-embodied-ai-agents-for","title":"TANGO: Training-free Embodied AI Agents for Open-world Tasks","date":"2024-12-05","arxiv_id":"2412.10402","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficienteqa-an-efficient-approach-for-open","title":"EfficientEQA: An Efficient Approach for Open Vocabulary Embodied Question Answering","date":"2024-10-26","arxiv_id":"2410.20263","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-this-it-towards-ecologically-valid","title":"\"Is This It?\": Towards Ecologically Valid Benchmarks for Situated Collaboration","date":"2024-08-30","arxiv_id":"2409.10525","repositories_listed":0,"syntology":null},{"url":null,"slug":"embodied-question-answering-via-multi-llm","title":"Multi-LLM QA with Embodied Exploration","date":"2024-06-16","arxiv_id":"2406.10918","repositories_listed":0,"syntology":null},{"url":null,"slug":"s-eqa-tackling-situational-queries-in","title":"Is the House Ready For Sleeptime? Generating and Evaluating Situational Queries for Embodied Question Answering","date":"2024-05-08","arxiv_id":"2405.04732","repositories_listed":0,"syntology":null},{"url":null,"slug":"explore-until-confident-efficient-exploration","title":"Explore until Confident: Efficient Exploration for Embodied Question Answering","date":"2024-03-23","arxiv_id":"2403.15941","repositories_listed":0,"syntology":null},{"url":null,"slug":"openeqa-embodied-question-answering-in-the","title":"OpenEQA: Embodied Question Answering in the Era of Foundation Models","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-as-a-robotic-brain-unifying-egocentric","title":"LLM as A Robotic Brain: Unifying Egocentric Memory and Control","date":"2023-04-19","arxiv_id":"2304.09349","repositories_listed":0,"syntology":null},{"url":null,"slug":"explore-before-moving-a-feasible-path","title":"Explore before Moving: A Feasible Path Estimation and Memory Recalling Framework for Embodied Navigation","date":"2021-10-16","arxiv_id":"2110.08571","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-embodied-ai-from-simulator-to","title":"A Survey of Embodied AI: From Simulators to Research Tasks","date":"2021-03-08","arxiv_id":"2103.04918","repositories_listed":0,"syntology":null},{"url":null,"slug":"counterfactual-vision-and-language-navigation-2","title":"Counterfactual Vision-and-Language Navigation: Unravelling the Unseen","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-agent-embodied-question-answering-in","title":"Multi-Agent Embodied Question Answering in Interactive Environments","date":"2020-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"segeqa-video-segmentation-based-visual","title":"SegEQA: Video Segmentation Based Visual Attention for Embodied Question Answering","date":"2019-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-task-knowledge-transfer-for-visually","title":"Cross-Task Knowledge Transfer for Visually-Grounded Navigation","date":"2019-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-embodiedqa-a-simple-baseline-and","title":"Revisiting EmbodiedQA: A Simple Baseline and Beyond","date":"2019-04-08","arxiv_id":"1904.04166","repositories_listed":0,"syntology":null},{"url":null,"slug":"embodied-question-answering-in-photorealistic","title":"Embodied Question Answering in Photorealistic Environments with Point Cloud Perception","date":"2019-04-06","arxiv_id":"1904.03461","repositories_listed":0,"syntology":null},{"url":null,"slug":"embodied-multimodal-multitask-learning","title":"Embodied Multimodal Multitask Learning","date":"2019-02-04","arxiv_id":"1902.01385","repositories_listed":0,"syntology":null}],"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"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":6,"papers_where_code_ran_first_page":"/task/embodied-question-answering/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/embodied-question-answering/papers/ran/1","json":"/task/embodied-question-answering/papers/ran/1.json","rows":6}],"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":"2026-10-05T00:36:11+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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"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"},"record_sha256":"c38a5e342a2fbbccabb6aed382f04af0795b86054fcd6ad0268636e608505dff","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}