{"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/visionreward-fine-grained-multi-dimensional","title":"VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation","arxiv_id":"2412.21059","date":"2024-12-30","proceeding":null,"authors":["Jiazheng Xu","Yu Huang","Jiale Cheng","Yuanming Yang","Jiajun Xu","YuAn Wang","Wenbo Duan","Shen Yang","Qunlin Jin","Shurun Li","Jiayan Teng","Zhuoyi Yang","Wendi Zheng","Xiao Liu","Ming Ding","Xiaohan Zhang","Xiaotao Gu","Shiyu Huang","Minlie Huang","Jie Tang","Yuxiao Dong"],"abstract":"We present a general strategy to aligning visual generation models -- both image and video generation -- with human preference. To start with, we build VisionReward -- a fine-grained and multi-dimensional reward model. We decompose human preferences in images and videos into multiple dimensions, each represented by a series of judgment questions, linearly weighted and summed to an interpretable and accurate score. To address the challenges of video quality assessment, we systematically analyze various dynamic features of videos, which helps VisionReward surpass VideoScore by 17.2% and achieve top performance for video preference prediction. Based on VisionReward, we develop a multi-objective preference learning algorithm that effectively addresses the issue of confounding factors within preference data. Our approach significantly outperforms existing image and video scoring methods on both machine metrics and human evaluation. All code and datasets are provided at https://github.com/THUDM/VisionReward.","url_abs":"https://arxiv.org/abs/2412.21059v1","url_pdf":"https://arxiv.org/pdf/2412.21059v1.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":"visionreward-fine-grained-multi-dimensional","repo_url":"https://github.com/thudm/visionreward","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"video-generation","task_name":"Video Generation"},{"task_slug":"video-quality-assessment","task_name":"Video Quality Assessment"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2412.21059","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.21059"}},"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/thudm/visionreward","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":"f13b1160fd3554a8","entry":"image_loader","repo":"thudm/visionreward","repo_kind":"official","path":"VisionReward_Image/t2v_metrics/models/model.py","file_url":"https://github.com/thudm/visionreward/blob/HEAD/VisionReward_Image/t2v_metrics/models/model.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f13b1160fd3554a8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}