{"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/hive-harnessing-human-feedback-for","title":"HIVE: Harnessing Human Feedback for Instructional Visual Editing","arxiv_id":"2303.09618","date":"2023-03-16","proceeding":"CVPR 2024 1","authors":["Shu Zhang","Xinyi Yang","Yihao Feng","Can Qin","Chia-Chih Chen","Ning Yu","Zeyuan Chen","Huan Wang","Silvio Savarese","Stefano Ermon","Caiming Xiong","ran Xu"],"abstract":"Incorporating human feedback has been shown to be crucial to align text generated by large language models to human preferences. We hypothesize that state-of-the-art instructional image editing models, where outputs are generated based on an input image and an editing instruction, could similarly benefit from human feedback, as their outputs may not adhere to the correct instructions and preferences of users. In this paper, we present a novel framework to harness human feedback for instructional visual editing (HIVE). Specifically, we collect human feedback on the edited images and learn a reward function to capture the underlying user preferences. We then introduce scalable diffusion model fine-tuning methods that can incorporate human preferences based on the estimated reward. Besides, to mitigate the bias brought by the limitation of data, we contribute a new 1M training dataset, a 3.6K reward dataset for rewards learning, and a 1K evaluation dataset to boost the performance of instructional image editing. We conduct extensive empirical experiments quantitatively and qualitatively, showing that HIVE is favored over previous state-of-the-art instructional image editing approaches by a large margin.","url_abs":"https://arxiv.org/abs/2303.09618v2","url_pdf":"https://arxiv.org/pdf/2303.09618v2.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":"hive-harnessing-human-feedback-for","repo_url":"https://github.com/salesforce/HIVE","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"text-based-image-editing","task_name":"Text-based Image Editing"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2303.09618","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.09618"}},"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/salesforce/HIVE","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_violates":2,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":4,"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":"424012cb37b31172","entry":"default","repo":"salesforce/HIVE","repo_kind":"official","path":"stable_diffusion/ldm/modules/attention.py","file_url":"https://github.com/salesforce/HIVE/blob/HEAD/stable_diffusion/ldm/modules/attention.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"424012cb37b31172"}},{"code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":"salesforce/HIVE","repo_kind":"official","path":"stable_diffusion/ldm/modules/attention.py","file_url":"https://github.com/salesforce/HIVE/blob/HEAD/stable_diffusion/ldm/modules/attention.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"aa5486a3650902d8"}},{"code_sha256_prefix":"9a299fe5ae09e407","entry":"uniq","repo":"salesforce/HIVE","repo_kind":"official","path":"stable_diffusion/ldm/modules/attention.py","file_url":"https://github.com/salesforce/HIVE/blob/HEAD/stable_diffusion/ldm/modules/attention.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9a299fe5ae09e407"}},{"code_sha256_prefix":"4533e43e06a12dc5","entry":"download_models","repo":"salesforce/HIVE","repo_kind":"official","path":"stable_diffusion/notebook_helpers.py","file_url":"https://github.com/salesforce/HIVE/blob/HEAD/stable_diffusion/notebook_helpers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4533e43e06a12dc5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}