{"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/simplear-pushing-the-frontier-of","title":"SimpleAR: Pushing the Frontier of Autoregressive Visual Generation through Pretraining, SFT, and RL","arxiv_id":"2504.11455","date":"2025-04-15","proceeding":null,"authors":["Junke Wang","Zhi Tian","Xun Wang","Xinyu Zhang","Weilin Huang","Zuxuan Wu","Yu-Gang Jiang"],"abstract":"This work presents SimpleAR, a vanilla autoregressive visual generation framework without complex architecure modifications. Through careful exploration of training and inference optimization, we demonstrate that: 1) with only 0.5B parameters, our model can generate 1024x1024 resolution images with high fidelity, and achieve competitive results on challenging text-to-image benchmarks, e.g., 0.59 on GenEval and 79.66 on DPG; 2) both supervised fine-tuning (SFT) and Group Relative Policy Optimization (GRPO) training could lead to significant improvements on generation aesthectics and prompt alignment; and 3) when optimized with inference acceleraton techniques like vLLM, the time for SimpleAR to generate an 1024x1024 image could be reduced to around 14 seconds. By sharing these findings and open-sourcing the code, we hope to reveal the potential of autoregressive visual generation and encourage more participation in this research field. Code is available at https://github.com/wdrink/SimpleAR.","url_abs":"https://arxiv.org/abs/2504.11455v1","url_pdf":"https://arxiv.org/pdf/2504.11455v1.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":"simplear-pushing-the-frontier-of","repo_url":"https://github.com/wdrink/simplear","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"inference-optimization","task_name":"Inference Optimization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2504.11455","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.11455"}},"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/wdrink/simplear","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"ran_fixture":1,"unverified":9},"by_repo_kind":{"official":{"samples":11,"ran":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,"samples":[{"code_sha256_prefix":"05feab6a291f31ce","entry":"collate_eval","repo":"wdrink/simplear","repo_kind":"official","path":"hpsv2/evaluation.py","file_url":"https://github.com/wdrink/simplear/blob/HEAD/hpsv2/evaluation.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"05feab6a291f31ce"}},{"code_sha256_prefix":"b0a851cae92754ff","entry":"extract_patches","repo":"wdrink/simplear","repo_kind":"official","path":"simpar/mm_utils.py","file_url":"https://github.com/wdrink/simplear/blob/HEAD/simpar/mm_utils.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b0a851cae92754ff"}},{"code_sha256_prefix":"3c8823948724e269","entry":"auto_pad_images","repo":"wdrink/simplear","repo_kind":"official","path":"simpar/mm_utils.py","file_url":"https://github.com/wdrink/simplear/blob/HEAD/simpar/mm_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3c8823948724e269"}},{"code_sha256_prefix":"4b120d52e38841a1","entry":"load_models","repo":"wdrink/simplear","repo_kind":"official","path":"hpsv2/utils.py","file_url":"https://github.com/wdrink/simplear/blob/HEAD/hpsv2/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4b120d52e38841a1"}},{"code_sha256_prefix":"fb651d0a97fd4d3f","entry":"prepare_inputs_for_generation","repo":"wdrink/simplear","repo_kind":"official","path":"hpsv2/src/open_clip/coca_model.py","file_url":"https://github.com/wdrink/simplear/blob/HEAD/hpsv2/src/open_clip/coca_model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fb651d0a97fd4d3f"}},{"code_sha256_prefix":"7d0ceb9bee72c22d","entry":"process_video_with_decord","repo":"wdrink/simplear","repo_kind":"official","path":"simpar/utils.py","file_url":"https://github.com/wdrink/simplear/blob/HEAD/simpar/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7d0ceb9bee72c22d"}},{"code_sha256_prefix":"5bd0aa0a6397c421","entry":"process_video_with_pyav","repo":"wdrink/simplear","repo_kind":"official","path":"simpar/utils.py","file_url":"https://github.com/wdrink/simplear/blob/HEAD/simpar/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5bd0aa0a6397c421"}},{"code_sha256_prefix":"c80358dff96c25ce","entry":"resize_and_center_crop","repo":"wdrink/simplear","repo_kind":"official","path":"simpar/mm_utils.py","file_url":"https://github.com/wdrink/simplear/blob/HEAD/simpar/mm_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c80358dff96c25ce"}},{"code_sha256_prefix":"c061cfab2678fcdf","entry":"run","repo":"wdrink/simplear","repo_kind":"official","path":"hpsv2/utils.py","file_url":"https://github.com/wdrink/simplear/blob/HEAD/hpsv2/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c061cfab2678fcdf"}},{"code_sha256_prefix":"b20705b0dfd77ffc","entry":"safe_load_tokenizer","repo":"wdrink/simplear","repo_kind":"official","path":"simpar/conversation.py","file_url":"https://github.com/wdrink/simplear/blob/HEAD/simpar/conversation.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b20705b0dfd77ffc"}},{"code_sha256_prefix":"dd437677b4dc71f9","entry":"vllm_t2i","repo":"wdrink/simplear","repo_kind":"official","path":"simpar/model/builder.py","file_url":"https://github.com/wdrink/simplear/blob/HEAD/simpar/model/builder.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dd437677b4dc71f9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}