{"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/can-we-generate-images-with-cot-let-s-verify","title":"Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step","arxiv_id":"2501.13926","date":"2025-01-23","proceeding":null,"authors":["Ziyu Guo","Renrui Zhang","Chengzhuo Tong","Zhizheng Zhao","Peng Gao","Hongsheng Li","Pheng-Ann Heng"],"abstract":"Chain-of-Thought (CoT) reasoning has been extensively explored in large models to tackle complex understanding tasks. However, it still remains an open question whether such strategies can be applied to verifying and reinforcing image generation scenarios. In this paper, we provide the first comprehensive investigation of the potential of CoT reasoning to enhance autoregressive image generation. We focus on three techniques: scaling test-time computation for verification, aligning model preferences with Direct Preference Optimization (DPO), and integrating these techniques for complementary effects. Our results demonstrate that these approaches can be effectively adapted and combined to significantly improve image generation performance. Furthermore, given the pivotal role of reward models in our findings, we propose the Potential Assessment Reward Model (PARM) and PARM++, specialized for autoregressive image generation. PARM adaptively assesses each generation step through a potential assessment approach, merging the strengths of existing reward models, and PARM++ further introduces a reflection mechanism to self-correct the generated unsatisfactory image. Using our investigated reasoning strategies, we enhance a baseline model, Show-o, to achieve superior results, with a significant +24% improvement on the GenEval benchmark, surpassing Stable Diffusion 3 by +15%. We hope our study provides unique insights and paves a new path for integrating CoT reasoning with autoregressive image generation. Code and models are released at https://github.com/ZiyuGuo99/Image-Generation-CoT","url_abs":"https://arxiv.org/abs/2501.13926v1","url_pdf":"https://arxiv.org/pdf/2501.13926v1.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":"can-we-generate-images-with-cot-let-s-verify","repo_url":"https://github.com/ziyuguo99/image-generation-cot","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok"}},{"paper_slug":"can-we-generate-images-with-cot-let-s-verify","repo_url":"https://github.com/caraj7/t2i-r1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"text-to-image-generation","task_name":"Text-to-Image Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/text-to-image-generation-on-geneval","task":"Text-to-Image Generation","dataset":"GenEval","model":"Show-o [xie2024show] PARM It. DPO PARM","rank_in_archive_order":8,"of":20,"metrics":{"Overall":"0.77"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-image-generation-on-geneval","task":"Text-to-Image Generation","dataset":"GenEval","model":"Show-o [xie2024show] Ft. ORM It. DPO Ft. ORM","rank_in_archive_order":9,"of":20,"metrics":{"Overall":"0.75"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2501.13926","atlas_url":"https://app.syntology.ai/?focus=2501.13926","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.13926"}},"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/ziyuguo99/image-generation-cot","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/caraj7/t2i-r1","reach":null}],"summary":{"ran_violates":1,"ran_honours":1,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{},"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":4,"samples":[{"code_sha256_prefix":"7bff6f3b3cb560e7","entry":"convert_to_custom_text_state_dict","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"7bff6f3b3cb560e7"}},{"code_sha256_prefix":"dd52eb593f187038","entry":"get_caption_height","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"dd52eb593f187038"}},{"code_sha256_prefix":"dcd422d66b0581d8","entry":"get_cast_dtype","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"code_sha256_prefix":"275eb8fe6104bf3a","entry":"build_model_from_openai_state_dict","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"275eb8fe6104bf3a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}