{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/episodic-transformer-for-vision-and-language","title":"Episodic Transformer for Vision-and-Language Navigation","arxiv_id":"2105.06453","date":"2021-05-13","proceeding":"ICCV 2021 10","authors":["Alexander Pashevich","Cordelia Schmid","Chen Sun"],"abstract":"Interaction and navigation defined by natural language instructions in dynamic environments pose significant challenges for neural agents. This paper focuses on addressing two challenges: handling long sequence of subtasks, and understanding complex human instructions. We propose Episodic Transformer (E.T.), a multimodal transformer that encodes language inputs and the full episode history of visual observations and actions. To improve training, we leverage synthetic instructions as an intermediate representation that decouples understanding the visual appearance of an environment from the variations of natural language instructions. We demonstrate that encoding the history with a transformer is critical to solve compositional tasks, and that pretraining and joint training with synthetic instructions further improve the performance. Our approach sets a new state of the art on the challenging ALFRED benchmark, achieving 38.4% and 8.5% task success rates on seen and unseen test splits.","url_abs":"https://arxiv.org/abs/2105.06453v2","url_pdf":"https://arxiv.org/pdf/2105.06453v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"episodic-transformer-for-vision-and-language","repo_url":"https://github.com/alexpashevich/E.T.","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"vision-and-language-navigation","task_name":"Vision and Language Navigation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2105.06453","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.06453"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alexpashevich/E.T.","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"71f2661ddf223250","entry":"compute_metrics","repo":"alexpashevich/E.T.","repo_kind":"official","path":"alfred/eval/eval_subgoals.py","file_url":"https://github.com/alexpashevich/E.T./blob/HEAD/alfred/eval/eval_subgoals.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"71f2661ddf223250"}},{"code_sha256_prefix":"42214cbf20d06362","entry":"create_optimizer_and_schedulers","repo":"alexpashevich/E.T.","repo_kind":"official","path":"alfred/utils/model_util.py","file_url":"https://github.com/alexpashevich/E.T./blob/HEAD/alfred/utils/model_util.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"42214cbf20d06362"}},{"code_sha256_prefix":"12ba53fedf724ead","entry":"get_action","repo":"alexpashevich/E.T.","repo_kind":"official","path":"alfred/env/reward.py","file_url":"https://github.com/alexpashevich/E.T./blob/HEAD/alfred/env/reward.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"12ba53fedf724ead"}},{"code_sha256_prefix":"d11401259503326f","entry":"get_task","repo":"alexpashevich/E.T.","repo_kind":"official","path":"alfred/env/tasks.py","file_url":"https://github.com/alexpashevich/E.T./blob/HEAD/alfred/env/tasks.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d11401259503326f"}},{"code_sha256_prefix":"026a1fec14fca72d","entry":"load_model","repo":"alexpashevich/E.T.","repo_kind":"official","path":"alfred/utils/model_util.py","file_url":"https://github.com/alexpashevich/E.T./blob/HEAD/alfred/utils/model_util.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"026a1fec14fca72d"}},{"code_sha256_prefix":"d34e3ef19764c321","entry":"load_model_args","repo":"alexpashevich/E.T.","repo_kind":"official","path":"alfred/utils/model_util.py","file_url":"https://github.com/alexpashevich/E.T./blob/HEAD/alfred/utils/model_util.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d34e3ef19764c321"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}