{"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/decisionnce-embodied-multimodal","title":"DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning","arxiv_id":"2402.18137","date":"2024-02-28","proceeding":null,"authors":["Jianxiong Li","Jinliang Zheng","Yinan Zheng","Liyuan Mao","Xiao Hu","Sijie Cheng","Haoyi Niu","Jihao Liu","Yu Liu","Jingjing Liu","Ya-Qin Zhang","Xianyuan Zhan"],"abstract":"Multimodal pretraining is an effective strategy for the trinity of goals of representation learning in autonomous robots: 1) extracting both local and global task progressions; 2) enforcing temporal consistency of visual representation; 3) capturing trajectory-level language grounding. Most existing methods approach these via separate objectives, which often reach sub-optimal solutions. In this paper, we propose a universal unified objective that can simultaneously extract meaningful task progression information from image sequences and seamlessly align them with language instructions. We discover that via implicit preferences, where a visual trajectory inherently aligns better with its corresponding language instruction than mismatched pairs, the popular Bradley-Terry model can transform into representation learning through proper reward reparameterizations. The resulted framework, DecisionNCE, mirrors an InfoNCE-style objective but is distinctively tailored for decision-making tasks, providing an embodied representation learning framework that elegantly extracts both local and global task progression features, with temporal consistency enforced through implicit time contrastive learning, while ensuring trajectory-level instruction grounding via multimodal joint encoding. Evaluation on both simulated and real robots demonstrates that DecisionNCE effectively facilitates diverse downstream policy learning tasks, offering a versatile solution for unified representation and reward learning. Project Page: https://2toinf.github.io/DecisionNCE/","url_abs":"https://arxiv.org/abs/2402.18137v2","url_pdf":"https://arxiv.org/pdf/2402.18137v2.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":"decisionnce-embodied-multimodal","repo_url":"https://github.com/2toinf/DecisionNCE","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[{"method_slug":"align","method_name":"ALIGN"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/contrastive-learning-on-10000-people-human","task":"Contrastive Learning","dataset":"10,000 People - Human Pose Recognition Data","model":"1","rank_in_archive_order":1,"of":1,"metrics":{"0..5sec":"1"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.18137","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.18137"}},"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/2toinf/DecisionNCE","reach":null}],"summary":{"ran":1,"ran_draft_wrong":2},"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":0,"samples":[{"code_sha256_prefix":"5cb20bf7ea19ead0","entry":"DecisionNCELoss","repo":"2toinf/DecisionNCE","repo_kind":"official","path":"DecisionNCE/losses.py","file_url":"https://github.com/2toinf/DecisionNCE/blob/HEAD/DecisionNCE/losses.py","link_basis":"first_harvest_node","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":"5cb20bf7ea19ead0"}},{"code_sha256_prefix":"1a95e67d3a627b8a","entry":"get_reward_matrix_P","repo":"2toinf/DecisionNCE","repo_kind":"official","path":"DecisionNCE/losses.py","file_url":"https://github.com/2toinf/DecisionNCE/blob/HEAD/DecisionNCE/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1a95e67d3a627b8a"}},{"code_sha256_prefix":"520ff973e7deca7e","entry":"get_reward_matrix_T","repo":"2toinf/DecisionNCE","repo_kind":"official","path":"DecisionNCE/losses.py","file_url":"https://github.com/2toinf/DecisionNCE/blob/HEAD/DecisionNCE/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"520ff973e7deca7e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}