{"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/visually-grounded-planning-without-vision","title":"Visually-Grounded Planning without Vision: Language Models Infer Detailed Plans from High-level Instructions","arxiv_id":"2009.14259","date":"2020-09-29","proceeding":null,"authors":["Peter A. Jansen"],"abstract":"The recently proposed ALFRED challenge task aims for a virtual robotic agent to complete complex multi-step everyday tasks in a virtual home environment from high-level natural language directives, such as \"put a hot piece of bread on a plate\". Currently, the best-performing models are able to complete less than 5% of these tasks successfully. In this work we focus on modeling the translation problem of converting natural language directives into detailed multi-step sequences of actions that accomplish those goals in the virtual environment. We empirically demonstrate that it is possible to generate gold multi-step plans from language directives alone without any visual input in 26% of unseen cases. When a small amount of visual information is incorporated, namely the starting location in the virtual environment, our best-performing GPT-2 model successfully generates gold command sequences in 58% of cases. Our results suggest that contextualized language models may provide strong visual semantic planning modules for grounded virtual agents.","url_abs":"https://arxiv.org/abs/2009.14259v2","url_pdf":"https://arxiv.org/pdf/2009.14259v2.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":"visually-grounded-planning-without-vision","repo_url":"https://github.com/cognitiveailab/alfred-gpt2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"discriminative-fine-tuning","method_name":"Discriminative Fine-Tuning"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-2","method_name":"GPT-2"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2009.14259","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.14259"}},"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/cognitiveailab/alfred-gpt2","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"a766a95b9fd5ee9c","entry":"prepare_ctrl_input","repo":"cognitiveailab/alfred-gpt2","repo_kind":"official","path":"code/evaluation/run_evaluation1.py","file_url":"https://github.com/cognitiveailab/alfred-gpt2/blob/HEAD/code/evaluation/run_evaluation1.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a766a95b9fd5ee9c"}},{"code_sha256_prefix":"b7bf53f6b6b11a4b","entry":"prepare_xlm_input","repo":"cognitiveailab/alfred-gpt2","repo_kind":"official","path":"code/evaluation/run_evaluation1.py","file_url":"https://github.com/cognitiveailab/alfred-gpt2/blob/HEAD/code/evaluation/run_evaluation1.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b7bf53f6b6b11a4b"}},{"code_sha256_prefix":"605ecfdd68892238","entry":"prepare_xlnet_input","repo":"cognitiveailab/alfred-gpt2","repo_kind":"official","path":"code/evaluation/run_evaluation1.py","file_url":"https://github.com/cognitiveailab/alfred-gpt2/blob/HEAD/code/evaluation/run_evaluation1.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"605ecfdd68892238"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}