{"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/beyond-any-shot-adaptation-predicting","title":"Beyond Any-Shot Adaptation: Predicting Optimization Outcome for Robustness Gains without Extra Pay","arxiv_id":"2501.11039","date":"2025-01-19","proceeding":null,"authors":["Qi Cheems Wang","Zehao Xiao","Yixiu Mao","Yun Qu","Jiayi Shen","Yiqin Lv","Xiangyang Ji"],"abstract":"The foundation model enables fast problem-solving without learning from scratch, and such a desirable adaptation property benefits from its adopted cross-task generalization paradigms, e.g., pretraining, meta-training, or finetuning. Recent trends have focused on the curation of task datasets during optimization, which includes task selection as an indispensable consideration for either adaptation robustness or sampling efficiency purposes. Despite some progress, selecting crucial task batches to optimize over iteration mostly exhausts massive task queries and requires intensive evaluation and computations to secure robust adaptation. This work underscores the criticality of both robustness and learning efficiency, especially in scenarios where tasks are risky to collect or costly to evaluate. To this end, we present Model Predictive Task Sampling (MPTS), a novel active task sampling framework to establish connections between the task space and adaptation risk landscape achieve robust adaptation. Technically, MPTS characterizes the task episodic information with a generative model and predicts optimization outcome after adaptation from posterior inference, i.e., forecasting task-specific adaptation risk values. The resulting risk learner amortizes expensive annotation, evaluation, or computation operations in task robust adaptation learning paradigms. Extensive experimental results show that MPTS can be seamlessly integrated into zero-shot, few-shot, and many-shot learning paradigms, increases adaptation robustness, and retains learning efficiency without affording extra cost. The code will be available at the project site https://github.com/thu-rllab/MPTS.","url_abs":"https://arxiv.org/abs/2501.11039v1","url_pdf":"https://arxiv.org/pdf/2501.11039v1.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":"beyond-any-shot-adaptation-predicting","repo_url":"https://github.com/thu-rllab/mpts","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2501.11039","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.11039"}},"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/thu-rllab/mpts","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"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":"900a7b6332276dd7","entry":"get_returns","repo":"thu-rllab/mpts","repo_kind":"official","path":"MetaRL/meta_testing.py","file_url":"https://github.com/thu-rllab/mpts/blob/HEAD/MetaRL/meta_testing.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":"900a7b6332276dd7"}},{"code_sha256_prefix":"2e09fec136475516","entry":"get_task_returns","repo":"thu-rllab/mpts","repo_kind":"official","path":"MetaRL/metalearner.py","file_url":"https://github.com/thu-rllab/mpts/blob/HEAD/MetaRL/metalearner.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":"2e09fec136475516"}},{"code_sha256_prefix":"4246e3602f23a27a","entry":"make_env","repo":"thu-rllab/mpts","repo_kind":"official","path":"MetaRL/sampler.py","file_url":"https://github.com/thu-rllab/mpts/blob/HEAD/MetaRL/sampler.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":"4246e3602f23a27a"}},{"code_sha256_prefix":"0de61eb1c79a8298","entry":"task_get_returns","repo":"thu-rllab/mpts","repo_kind":"official","path":"MetaRL/meta_testing.py","file_url":"https://github.com/thu-rllab/mpts/blob/HEAD/MetaRL/meta_testing.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":"0de61eb1c79a8298"}},{"code_sha256_prefix":"9eb6bc08b78e30be","entry":"total_rewards","repo":"thu-rllab/mpts","repo_kind":"official","path":"MetaRL/meta_testing.py","file_url":"https://github.com/thu-rllab/mpts/blob/HEAD/MetaRL/meta_testing.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":"9eb6bc08b78e30be"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}