{"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/reasongen-r1-cot-for-autoregressive-image","title":"ReasonGen-R1: CoT for Autoregressive Image generation models through SFT and RL","arxiv_id":"2505.24875","date":"2025-05-30","proceeding":null,"authors":["Yu Zhang","Yunqi Li","Yifan Yang","Rui Wang","Yuqing Yang","Dai Qi","Jianmin Bao","Dongdong Chen","Chong Luo","Lili Qiu"],"abstract":"Although chain-of-thought reasoning and reinforcement learning (RL) have driven breakthroughs in NLP, their integration into generative vision models remains underexplored. We introduce ReasonGen-R1, a two-stage framework that first imbues an autoregressive image generator with explicit text-based \"thinking\" skills via supervised fine-tuning on a newly generated reasoning dataset of written rationales, and then refines its outputs using Group Relative Policy Optimization. To enable the model to reason through text before generating images, We automatically generate and release a corpus of model crafted rationales paired with visual prompts, enabling controlled planning of object layouts, styles, and scene compositions. Our GRPO algorithm uses reward signals from a pretrained vision language model to assess overall visual quality, optimizing the policy in each update. Evaluations on GenEval, DPG, and the T2I benchmark demonstrate that ReasonGen-R1 consistently outperforms strong baselines and prior state-of-the-art models. More: aka.ms/reasongen.","url_abs":"https://arxiv.org/abs/2505.24875v2","url_pdf":"https://arxiv.org/pdf/2505.24875v2.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":"reasongen-r1-cot-for-autoregressive-image","repo_url":"https://github.com/Franklin-Zhang0/ReasonGen-R1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[{"method_slug":"dpg","method_name":"DPG"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2505.24875","atlas_url":"https://app.syntology.ai/?focus=2505.24875","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.24875"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/Franklin-Zhang0/ReasonGen-R1","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":2,"ran":3,"ran_fixture":1,"unverified":7},"by_repo_kind":{"listed":{"samples":13,"ran":6,"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":"592b3c1a88f93d7c","entry":"expand2square","repo":"Franklin-Zhang0/ReasonGen-R1","repo_kind":"listed","path":"Janus/janus/models/image_processing_vlm.py","file_url":"https://github.com/Franklin-Zhang0/ReasonGen-R1/blob/HEAD/Janus/janus/models/image_processing_vlm.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"592b3c1a88f93d7c"}},{"code_sha256_prefix":"fe79c459a3e4cc64","entry":"get_huggingface_actor_config","repo":"Franklin-Zhang0/ReasonGen-R1","repo_kind":"listed","path":"verl/utils/model.py","file_url":"https://github.com/Franklin-Zhang0/ReasonGen-R1/blob/HEAD/verl/utils/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":"fe79c459a3e4cc64"}},{"code_sha256_prefix":"556a917293596716","entry":"make_plural","repo":"Franklin-Zhang0/ReasonGen-R1","repo_kind":"listed","path":"gen_prompt/create_prompts.py","file_url":"https://github.com/Franklin-Zhang0/ReasonGen-R1/blob/HEAD/gen_prompt/create_prompts.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"556a917293596716"}},{"code_sha256_prefix":"21331a58f93375e4","entry":"union_tensor_dict","repo":"Franklin-Zhang0/ReasonGen-R1","repo_kind":"listed","path":"verl/protocol.py","file_url":"https://github.com/Franklin-Zhang0/ReasonGen-R1/blob/HEAD/verl/protocol.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"21331a58f93375e4"}},{"code_sha256_prefix":"25f0ea3f460f6ce1","entry":"unpad_dataproto","repo":"Franklin-Zhang0/ReasonGen-R1","repo_kind":"listed","path":"verl/protocol.py","file_url":"https://github.com/Franklin-Zhang0/ReasonGen-R1/blob/HEAD/verl/protocol.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"25f0ea3f460f6ce1"}},{"code_sha256_prefix":"e56c199fc836a44e","entry":"with_article","repo":"Franklin-Zhang0/ReasonGen-R1","repo_kind":"listed","path":"gen_prompt/create_prompts.py","file_url":"https://github.com/Franklin-Zhang0/ReasonGen-R1/blob/HEAD/gen_prompt/create_prompts.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e56c199fc836a44e"}},{"code_sha256_prefix":"3130a89440c64972","entry":"checkpoint_wrapper","repo":"Franklin-Zhang0/ReasonGen-R1","repo_kind":"listed","path":"Janus/janus/models/modeling_vlm.py","file_url":"https://github.com/Franklin-Zhang0/ReasonGen-R1/blob/HEAD/Janus/janus/models/modeling_vlm.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":"3130a89440c64972"}},{"code_sha256_prefix":"601de58a282ecb25","entry":"generate_single_object_sample","repo":"Franklin-Zhang0/ReasonGen-R1","repo_kind":"listed","path":"gen_prompt/create_prompts.py","file_url":"https://github.com/Franklin-Zhang0/ReasonGen-R1/blob/HEAD/gen_prompt/create_prompts.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":"601de58a282ecb25"}},{"code_sha256_prefix":"660713a8fa047736","entry":"get_generation_config","repo":"Franklin-Zhang0/ReasonGen-R1","repo_kind":"listed","path":"verl/utils/model.py","file_url":"https://github.com/Franklin-Zhang0/ReasonGen-R1/blob/HEAD/verl/utils/model.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":"660713a8fa047736"}},{"code_sha256_prefix":"0b420baae60fbb33","entry":"get_prompt","repo":"Franklin-Zhang0/ReasonGen-R1","repo_kind":"listed","path":"benchmark/generate_inference_dpg.py","file_url":"https://github.com/Franklin-Zhang0/ReasonGen-R1/blob/HEAD/benchmark/generate_inference_dpg.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":"0b420baae60fbb33"}},{"code_sha256_prefix":"af005d03c2088909","entry":"get_weight_loader","repo":"Franklin-Zhang0/ReasonGen-R1","repo_kind":"listed","path":"verl/models/weight_loader_registry.py","file_url":"https://github.com/Franklin-Zhang0/ReasonGen-R1/blob/HEAD/verl/models/weight_loader_registry.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":"af005d03c2088909"}},{"code_sha256_prefix":"0cc9aa000ef7d88e","entry":"get_weight_saver","repo":"Franklin-Zhang0/ReasonGen-R1","repo_kind":"listed","path":"verl/models/weight_loader_registry.py","file_url":"https://github.com/Franklin-Zhang0/ReasonGen-R1/blob/HEAD/verl/models/weight_loader_registry.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":"0cc9aa000ef7d88e"}},{"code_sha256_prefix":"3b15e2ac7497c441","entry":"squeeze","repo":"Franklin-Zhang0/ReasonGen-R1","repo_kind":"listed","path":"verl/utils/model.py","file_url":"https://github.com/Franklin-Zhang0/ReasonGen-R1/blob/HEAD/verl/utils/model.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":"3b15e2ac7497c441"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}