{"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/instruction-following-agents-with-jointly-pre","title":"Instruction-Following Agents with Multimodal Transformer","arxiv_id":"2210.13431","date":"2022-10-24","proceeding":null,"authors":["Hao liu","Lisa Lee","Kimin Lee","Pieter Abbeel"],"abstract":"Humans are excellent at understanding language and vision to accomplish a wide range of tasks. In contrast, creating general instruction-following embodied agents remains a difficult challenge. Prior work that uses pure language-only models lack visual grounding, making it difficult to connect language instructions with visual observations. On the other hand, methods that use pre-trained multimodal models typically come with divided language and visual representations, requiring designing specialized network architecture to fuse them together. We propose a simple yet effective model for robots to solve instruction-following tasks in vision-based environments. Our \\ours method consists of a multimodal transformer that encodes visual observations and language instructions, and a transformer-based policy that predicts actions based on encoded representations. The multimodal transformer is pre-trained on millions of image-text pairs and natural language text, thereby producing generic cross-modal representations of observations and instructions. The transformer-based policy keeps track of the full history of observations and actions, and predicts actions autoregressively. Despite its simplicity, we show that this unified transformer model outperforms all state-of-the-art pre-trained or trained-from-scratch methods in both single-task and multi-task settings. Our model also shows better model scalability and generalization ability than prior work.","url_abs":"https://arxiv.org/abs/2210.13431v4","url_pdf":"https://arxiv.org/pdf/2210.13431v4.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":"instruction-following-agents-with-jointly-pre","repo_url":"https://github.com/lhao499/instructrl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"instruction-following","task_name":"Instruction Following"},{"task_slug":"visual-grounding","task_name":"Visual Grounding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.13431","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.13431"}},"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/lhao499/instructrl","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":6,"unverified":14},"by_repo_kind":{"official":{"samples":20,"ran":6,"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":"ef0abd7fbdc81c5e","entry":"cross_entropy","repo":"lhao499/instructrl","repo_kind":"official","path":"instructrl/model.py","file_url":"https://github.com/lhao499/instructrl/blob/HEAD/instructrl/model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ef0abd7fbdc81c5e"}},{"code_sha256_prefix":"d2f199c948f2a9ed","entry":"extend_and_repeat","repo":"lhao499/instructrl","repo_kind":"official","path":"instructrl/utils.py","file_url":"https://github.com/lhao499/instructrl/blob/HEAD/instructrl/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d2f199c948f2a9ed"}},{"code_sha256_prefix":"f051af6f08e6125a","entry":"get_metrics","repo":"lhao499/instructrl","repo_kind":"official","path":"instructrl/utils.py","file_url":"https://github.com/lhao499/instructrl/blob/HEAD/instructrl/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f051af6f08e6125a"}},{"code_sha256_prefix":"a94b14df1af9126d","entry":"get_pos_embed","repo":"lhao499/instructrl","repo_kind":"official","path":"instructrl/model.py","file_url":"https://github.com/lhao499/instructrl/blob/HEAD/instructrl/model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a94b14df1af9126d"}},{"code_sha256_prefix":"cc35af8b18b7dc58","entry":"mse_loss","repo":"lhao499/instructrl","repo_kind":"official","path":"instructrl/model.py","file_url":"https://github.com/lhao499/instructrl/blob/HEAD/instructrl/model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cc35af8b18b7dc58"}},{"code_sha256_prefix":"1e6123c693775a38","entry":"wrap_function_with_rng","repo":"lhao499/instructrl","repo_kind":"official","path":"instructrl/utils.py","file_url":"https://github.com/lhao499/instructrl/blob/HEAD/instructrl/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1e6123c693775a38"}},{"code_sha256_prefix":"c16d1755d384c81b","entry":"batch_rollout","repo":"lhao499/instructrl","repo_kind":"official","path":"instructrl/envs/rollout.py","file_url":"https://github.com/lhao499/instructrl/blob/HEAD/instructrl/envs/rollout.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":"c16d1755d384c81b"}},{"code_sha256_prefix":"600b55b260ebe0ff","entry":"build_env_fn","repo":"lhao499/instructrl","repo_kind":"official","path":"instructrl/instructrl_main.py","file_url":"https://github.com/lhao499/instructrl/blob/HEAD/instructrl/instructrl_main.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":"600b55b260ebe0ff"}},{"code_sha256_prefix":"dc4f5bae4c75e9c4","entry":"build_env_fn","repo":"lhao499/instructrl","repo_kind":"official","path":"instructrl/local_run.py","file_url":"https://github.com/lhao499/instructrl/blob/HEAD/instructrl/local_run.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":"dc4f5bae4c75e9c4"}},{"code_sha256_prefix":"1189ccb694f97474","entry":"create_test_step","repo":"lhao499/instructrl","repo_kind":"official","path":"instructrl/local_run.py","file_url":"https://github.com/lhao499/instructrl/blob/HEAD/instructrl/local_run.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":"1189ccb694f97474"}},{"code_sha256_prefix":"06f8960d0fb5a580","entry":"create_train_step","repo":"lhao499/instructrl","repo_kind":"official","path":"instructrl/instructrl_main.py","file_url":"https://github.com/lhao499/instructrl/blob/HEAD/instructrl/instructrl_main.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":"06f8960d0fb5a580"}},{"code_sha256_prefix":"6f7c29d589a38d3b","entry":"discrete_euler_to_quaternion","repo":"lhao499/instructrl","repo_kind":"official","path":"instructrl/data.py","file_url":"https://github.com/lhao499/instructrl/blob/HEAD/instructrl/data.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":"6f7c29d589a38d3b"}},{"code_sha256_prefix":"a18a67bfbd7246bb","entry":"download","repo":"lhao499/instructrl","repo_kind":"official","path":"instructrl/models/openai/download.py","file_url":"https://github.com/lhao499/instructrl/blob/HEAD/instructrl/models/openai/download.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":"a18a67bfbd7246bb"}},{"code_sha256_prefix":"913edd29987265fa","entry":"get_cont_action","repo":"lhao499/instructrl","repo_kind":"official","path":"instructrl/data.py","file_url":"https://github.com/lhao499/instructrl/blob/HEAD/instructrl/data.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":"913edd29987265fa"}},{"code_sha256_prefix":"15ba5cffc310ab9f","entry":"hash_file","repo":"lhao499/instructrl","repo_kind":"official","path":"instructrl/models/openai/download.py","file_url":"https://github.com/lhao499/instructrl/blob/HEAD/instructrl/models/openai/download.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":"15ba5cffc310ab9f"}},{"code_sha256_prefix":"cd63725ed150c8be","entry":"mask_intersection","repo":"lhao499/instructrl","repo_kind":"official","path":"instructrl/models/m3ae/model.py","file_url":"https://github.com/lhao499/instructrl/blob/HEAD/instructrl/models/m3ae/model.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":"cd63725ed150c8be"}},{"code_sha256_prefix":"e0f860b8706ea27b","entry":"mask_not","repo":"lhao499/instructrl","repo_kind":"official","path":"instructrl/models/m3ae/model.py","file_url":"https://github.com/lhao499/instructrl/blob/HEAD/instructrl/models/m3ae/model.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":"e0f860b8706ea27b"}},{"code_sha256_prefix":"d049b3e2054cb151","entry":"mask_union","repo":"lhao499/instructrl","repo_kind":"official","path":"instructrl/models/m3ae/model.py","file_url":"https://github.com/lhao499/instructrl/blob/HEAD/instructrl/models/m3ae/model.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":"d049b3e2054cb151"}},{"code_sha256_prefix":"d97e89c7f1953b3a","entry":"prefix_metrics","repo":"lhao499/instructrl","repo_kind":"official","path":"instructrl/models/m3ae/utils.py","file_url":"https://github.com/lhao499/instructrl/blob/HEAD/instructrl/models/m3ae/utils.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":"d97e89c7f1953b3a"}},{"code_sha256_prefix":"278d0834e4c3f3b4","entry":"sync_state_fn","repo":"lhao499/instructrl","repo_kind":"official","path":"instructrl/instructrl_main.py","file_url":"https://github.com/lhao499/instructrl/blob/HEAD/instructrl/instructrl_main.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":"278d0834e4c3f3b4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}