{"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/a-dense-reward-view-on-aligning-text-to-image","title":"A Dense Reward View on Aligning Text-to-Image Diffusion with Preference","arxiv_id":"2402.08265","date":"2024-02-13","proceeding":null,"authors":["Shentao Yang","Tianqi Chen","Mingyuan Zhou"],"abstract":"Aligning text-to-image diffusion model (T2I) with preference has been gaining increasing research attention. While prior works exist on directly optimizing T2I by preference data, these methods are developed under the bandit assumption of a latent reward on the entire diffusion reverse chain, while ignoring the sequential nature of the generation process. This may harm the efficacy and efficiency of preference alignment. In this paper, we take on a finer dense reward perspective and derive a tractable alignment objective that emphasizes the initial steps of the T2I reverse chain. In particular, we introduce temporal discounting into DPO-style explicit-reward-free objectives, to break the temporal symmetry therein and suit the T2I generation hierarchy. In experiments on single and multiple prompt generation, our method is competitive with strong relevant baselines, both quantitatively and qualitatively. Further investigations are conducted to illustrate the insight of our approach.","url_abs":"https://arxiv.org/abs/2402.08265v2","url_pdf":"https://arxiv.org/pdf/2402.08265v2.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":"a-dense-reward-view-on-aligning-text-to-image","repo_url":"https://github.com/shentao-yang/dense_reward_t2i","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.08265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.08265"}},"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/shentao-yang/dense_reward_t2i","reach":{"status":"ok"}}],"summary":{"ran":5},"by_repo_kind":{"official":{"samples":5,"ran":5,"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":5,"samples":[{"code_sha256_prefix":"c489bb9ff3f10f97","entry":"concat_imgs","repo":"shentao-yang/dense_reward_t2i","repo_kind":"official","path":"eval_ckpts/stable_diffusion_pipeline_traj.py","file_url":"https://github.com/shentao-yang/dense_reward_t2i/blob/HEAD/eval_ckpts/stable_diffusion_pipeline_traj.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c489bb9ff3f10f97"}},{"code_sha256_prefix":"244e50dfe922e639","entry":"get_snr_schedule","repo":"shentao-yang/dense_reward_t2i","repo_kind":"official","path":"utils.py","file_url":"https://github.com/shentao-yang/dense_reward_t2i/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"244e50dfe922e639"}},{"code_sha256_prefix":"6ab46c06e144019b","entry":"listMLELoss","repo":"shentao-yang/dense_reward_t2i","repo_kind":"official","path":"reward_loss.py","file_url":"https://github.com/shentao-yang/dense_reward_t2i/blob/HEAD/reward_loss.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":"6ab46c06e144019b"}},{"code_sha256_prefix":"88fc4c03f1a33d44","entry":"make_banner","repo":"shentao-yang/dense_reward_t2i","repo_kind":"official","path":"utils.py","file_url":"https://github.com/shentao-yang/dense_reward_t2i/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"88fc4c03f1a33d44"}},{"code_sha256_prefix":"4bd02a478fc9cfdf","entry":"register_score","repo":"shentao-yang/dense_reward_t2i","repo_kind":"official","path":"scorer_ensemble.py","file_url":"https://github.com/shentao-yang/dense_reward_t2i/blob/HEAD/scorer_ensemble.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4bd02a478fc9cfdf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}