{"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/policy-contrastive-decoding-for-robotic","title":"Policy Contrastive Decoding for Robotic Foundation Models","arxiv_id":"2505.13255","date":"2025-05-19","proceeding":null,"authors":["Shihan Wu","Xu Luo","Ji Zhang","Junlin Xie","Jingkuan Song","Heng Tao Shen","Lianli Gao"],"abstract":"Robotic foundation models, or generalist robot policies, hold immense potential to enable flexible, general-purpose and dexterous robotic systems. Despite their advancements, our empirical experiments reveal that existing robot policies are prone to learning spurious correlations from pre-training trajectories, adversely affecting their generalization capabilities beyond the training data. To tackle this, we propose a novel Policy Contrastive Decoding (PCD) approach, which redirects the robot policy's focus toward object-relevant visual clues by contrasting action probability distributions derived from original and object-masked visual inputs. As a training-free method, our PCD can be used as a plugin to improve different types of robot policies without needing to finetune or access model weights. We conduct extensive experiments on top of three open-source robot policies, including the autoregressive policy OpenVLA and the diffusion-based policies Octo and $\\pi_0$. The obtained results in both simulation and real-world environments prove PCD's flexibility and effectiveness, e.g., PCD enhances the state-of-the-art policy $\\pi_0$ by 8.9% in the simulation environment and by 108% in the real-world environment. Code and demos are publicly available at: https://koorye.github.io/PCD.","url_abs":"https://arxiv.org/abs/2505.13255v2","url_pdf":"https://arxiv.org/pdf/2505.13255v2.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":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"policy-contrastive-decoding-for-robotic","repo_url":"https://github.com/Koorye/PCD","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.13255","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.13255"}},"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/Koorye/PCD","reach":null}],"summary":{"ran":1,"ran_violates":1,"ran_draft_wrong":3,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":7,"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":7,"samples":[{"code_sha256_prefix":"16b617e7398be201","entry":"ContrastDecoding","repo":"Koorye/PCD","repo_kind":"official","path":"contrast_policies/kde_contrast_decoding.py","file_url":"https://github.com/Koorye/PCD/blob/HEAD/contrast_policies/kde_contrast_decoding.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"16b617e7398be201"}},{"code_sha256_prefix":"7362d2cd65a04fcd","entry":"gaussian_kernel_jax","repo":"Koorye/PCD","repo_kind":"official","path":"contrast_policies/kde_contrast_decoding.py","file_url":"https://github.com/Koorye/PCD/blob/HEAD/contrast_policies/kde_contrast_decoding.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7362d2cd65a04fcd"}},{"code_sha256_prefix":"6339fc0334074ade","entry":"gaussian_kernel_torch","repo":"Koorye/PCD","repo_kind":"official","path":"contrast_policies/kde_contrast_decoding.py","file_url":"https://github.com/Koorye/PCD/blob/HEAD/contrast_policies/kde_contrast_decoding.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6339fc0334074ade"}},{"code_sha256_prefix":"0c11f3cc247a64c3","entry":"kde_jax","repo":"Koorye/PCD","repo_kind":"official","path":"contrast_policies/kde_contrast_decoding.py","file_url":"https://github.com/Koorye/PCD/blob/HEAD/contrast_policies/kde_contrast_decoding.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0c11f3cc247a64c3"}},{"code_sha256_prefix":"56b6d6f2824f2e67","entry":"scott_rule_jax","repo":"Koorye/PCD","repo_kind":"official","path":"contrast_policies/kde_contrast_decoding.py","file_url":"https://github.com/Koorye/PCD/blob/HEAD/contrast_policies/kde_contrast_decoding.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"56b6d6f2824f2e67"}},{"code_sha256_prefix":"a3de7f0ab75c0d42","entry":"scott_rule_torch","repo":"Koorye/PCD","repo_kind":"official","path":"contrast_policies/kde_contrast_decoding.py","file_url":"https://github.com/Koorye/PCD/blob/HEAD/contrast_policies/kde_contrast_decoding.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a3de7f0ab75c0d42"}},{"code_sha256_prefix":"bed476f89908de30","entry":"kde_torch","repo":"Koorye/PCD","repo_kind":"official","path":"contrast_policies/kde_contrast_decoding.py","file_url":"https://github.com/Koorye/PCD/blob/HEAD/contrast_policies/kde_contrast_decoding.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bed476f89908de30"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}