{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/flow-grpo-training-flow-matching-models-via","title":"Flow-GRPO: Training Flow Matching Models via Online RL","arxiv_id":"2505.05470","date":"2025-05-08","proceeding":null,"authors":["Jie Liu","Gongye Liu","Jiajun Liang","Yangguang Li","Jiaheng Liu","Xintao Wang","Pengfei Wan","Di Zhang","Wanli Ouyang"],"abstract":"We propose Flow-GRPO, the first method integrating online reinforcement learning (RL) into flow matching models. Our approach uses two key strategies: (1) an ODE-to-SDE conversion that transforms a deterministic Ordinary Differential Equation (ODE) into an equivalent Stochastic Differential Equation (SDE) that matches the original model's marginal distribution at all timesteps, enabling statistical sampling for RL exploration; and (2) a Denoising Reduction strategy that reduces training denoising steps while retaining the original inference timestep number, significantly improving sampling efficiency without performance degradation. Empirically, Flow-GRPO is effective across multiple text-to-image tasks. For complex compositions, RL-tuned SD3.5 generates nearly perfect object counts, spatial relations, and fine-grained attributes, boosting GenEval accuracy from 63% to 95%. In visual text rendering, its accuracy improves from 59% to 92%, significantly enhancing text generation. Flow-GRPO also achieves substantial gains in human preference alignment. Notably, very little reward hacking occurred, meaning rewards did not increase at the cost of appreciable image quality or diversity degradation.","url_abs":"https://arxiv.org/abs/2505.05470v2","url_pdf":"https://arxiv.org/pdf/2505.05470v2.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":"flow-grpo-training-flow-matching-models-via","repo_url":"https://github.com/yifan123/flow_grpo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"text-to-image-generation","task_name":"Text-to-Image Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/text-to-image-generation-on-geneval","task":"Text-to-Image Generation","dataset":"GenEval","model":"SD3.5-Medium+Flow-GRPO","rank_in_archive_order":1,"of":20,"metrics":{"Overall":"0.95"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2505.05470","atlas_url":"https://app.syntology.ai/?focus=2505.05470","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.05470"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2505.05470"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2505.05470"},"call":"get_harvested_code_for_paper(arxiv_id=\"2505.05470\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2505.05470"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2505.05470\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2505.05470"},"call":"get_concepts_for_paper(arxiv_id=\"2505.05470\")"}],"by_repo":[{"repo":"yifan123/flow_grpo","kind":"official","samples":9,"ran":5,"instrument":2,"unverified":4}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2505.05470.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2505.05470.svg"},"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/yifan123/flow_grpo","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":2,"ran_fixture":1,"ran_draft_wrong":1,"ran":1,"unverified":4},"n_samples":9,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":4,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":9,"ran":5,"n_ran_checked":3,"n_instrument":2,"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,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":5,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-24","last":"2026-09-25","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"aaf3538ea48a524d","code_sha256_prefix":"aaf3538ea48a524d","entry":"extract_scores","repo":"yifan123/flow_grpo","repo_kind":"official","path":"flow_grpo/qwenvl.py","file_url":"https://github.com/yifan123/flow_grpo/blob/HEAD/flow_grpo/qwenvl.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"output_text:list/1/str","fixture_out_type":"list","level_recorded_at":"2026-09-25T22:21:49.183891+00:00","code_page":"/code/extract-scores","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"aaf3538ea48a524d"}},{"code_sha256":"1d0c29e5ba66b093","code_sha256_prefix":"1d0c29e5ba66b093","entry":"get_image_transform","repo":"yifan123/flow_grpo","repo_kind":"official","path":"flow_grpo/clip_scorer.py","file_url":"https://github.com/yifan123/flow_grpo/blob/HEAD/flow_grpo/clip_scorer.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"processor:MockImageProcessor/0/?","fixture_out_type":"Compose","level_recorded_at":"2026-09-25T03:30:08.474462+00:00","code_page":"/code/get-image-transform","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"1d0c29e5ba66b093"}},{"code_sha256":"b4ae73baea6f9f47","code_sha256_prefix":"b4ae73baea6f9f47","entry":"get_size","repo":"yifan123/flow_grpo","repo_kind":"official","path":"flow_grpo/clip_scorer.py","file_url":"https://github.com/yifan123/flow_grpo/blob/HEAD/flow_grpo/clip_scorer.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"size:int/0/int","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","retrieve_with":{"tool":"get_code","code_sha256":"b4ae73baea6f9f47"},"code_page":"/code/get-size","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"b4ae73baea6f9f47"}},{"code_sha256":"679c61d741aabb1d","code_sha256_prefix":"679c61d741aabb1d","entry":"pil_image_to_base64","repo":"yifan123/flow_grpo","repo_kind":"official","path":"flow_grpo/qwenvl.py","file_url":"https://github.com/yifan123/flow_grpo/blob/HEAD/flow_grpo/qwenvl.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"image:Image/0/?","fixture_out_type":"str","level_recorded_at":"2026-09-25T06:02:23.992132+00:00","code_page":"/code/pil-image-to-base64","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"679c61d741aabb1d"}},{"code_sha256":"9f8c8299498f223d","code_sha256_prefix":"9f8c8299498f223d","entry":"register_optimizer_offload_hooks","repo":"yifan123/flow_grpo","repo_kind":"official","path":"flow_grpo/fsdp_utils.py","file_url":"https://github.com/yifan123/flow_grpo/blob/HEAD/flow_grpo/fsdp_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"optimizer:SGD/0/?","fixture_out_type":"tuple","level_recorded_at":"2026-09-25T00:28:05.031210+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"9f8c8299498f223d"}},{"code_sha256":"58a9aa750111b5f3","code_sha256_prefix":"58a9aa750111b5f3","entry":"clip_score","repo":"yifan123/flow_grpo","repo_kind":"official","path":"flow_grpo/rewards.py","file_url":"https://github.com/yifan123/flow_grpo/blob/HEAD/flow_grpo/rewards.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"58a9aa750111b5f3"}},{"code_sha256":"597a05808a506d45","code_sha256_prefix":"597a05808a506d45","entry":"fsdp_wrapper","repo":"yifan123/flow_grpo","repo_kind":"official","path":"flow_grpo/fsdp_utils.py","file_url":"https://github.com/yifan123/flow_grpo/blob/HEAD/flow_grpo/fsdp_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"597a05808a506d45"}},{"code_sha256":"6bfe651b4ae64450","code_sha256_prefix":"6bfe651b4ae64450","entry":"image_similarity_score","repo":"yifan123/flow_grpo","repo_kind":"official","path":"flow_grpo/rewards.py","file_url":"https://github.com/yifan123/flow_grpo/blob/HEAD/flow_grpo/rewards.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"6bfe651b4ae64450"}},{"code_sha256":"667f709586d6128e","code_sha256_prefix":"667f709586d6128e","entry":"pickscore_score","repo":"yifan123/flow_grpo","repo_kind":"official","path":"flow_grpo/rewards.py","file_url":"https://github.com/yifan123/flow_grpo/blob/HEAD/flow_grpo/rewards.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"667f709586d6128e"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"c054a7bf878be934d5a6af68d8e3df378c64e0ebc8df14527ffc37379e52fa72","record_changed_at":"2026-10-04","record_changed_at_basis":"changed"}