{"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/perception-r1-pioneering-perception-policy","title":"Perception-R1: Pioneering Perception Policy with Reinforcement Learning","arxiv_id":"2504.07954","date":"2025-04-10","proceeding":null,"authors":["En Yu","Kangheng Lin","Liang Zhao","Jisheng Yin","Yana Wei","Yuang Peng","Haoran Wei","Jianjian Sun","Chunrui Han","Zheng Ge","Xiangyu Zhang","Daxin Jiang","Jingyu Wang","Wenbing Tao"],"abstract":"Inspired by the success of DeepSeek-R1, we explore the potential of rule-based reinforcement learning (RL) in MLLM post-training for perception policy learning. While promising, our initial experiments reveal that incorporating a thinking process through RL does not consistently lead to performance gains across all visual perception tasks. This leads us to delve into the essential role of RL in the context of visual perception. In this work, we return to the fundamentals and explore the effects of RL on different perception tasks. We observe that the perceptual complexity is a major factor in determining the effectiveness of RL. We also observe that reward design plays a crucial role in further approching the upper limit of model perception. To leverage these findings, we propose Perception-R1, a scalable RL framework using GRPO during MLLM post-training. With a standard Qwen2.5-VL-3B-Instruct, Perception-R1 achieves +4.2% on RefCOCO+, +17.9% on PixMo-Count, +4.2% on PageOCR, and notably, 31.9% AP on COCO2017 val for the first time, establishing a strong baseline for perception policy learning.","url_abs":"https://arxiv.org/abs/2504.07954v1","url_pdf":"https://arxiv.org/pdf/2504.07954v1.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":"perception-r1-pioneering-perception-policy","repo_url":"https://github.com/linkangheng/pr1","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2504.07954","atlas_url":"https://app.syntology.ai/?focus=2504.07954","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.07954"}},"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/linkangheng/pr1","reach":null}],"summary":{"ran_fixture":1,"ran_draft_wrong":2,"ran_honours":2},"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":0,"samples":[{"code_sha256_prefix":"96d8ce55eedcc334","entry":"compute_iou","repo":"linkangheng/pr1","repo_kind":"official","path":"eval/evaluate_grounding.py","file_url":"https://github.com/linkangheng/pr1/blob/HEAD/eval/evaluate_grounding.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"96d8ce55eedcc334"}},{"code_sha256_prefix":"a64d39c4fd2ee2dc","entry":"extract_bbox_answer","repo":"linkangheng/pr1","repo_kind":"official","path":"eval/evaluate_grounding.py","file_url":"https://github.com/linkangheng/pr1/blob/HEAD/eval/evaluate_grounding.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a64d39c4fd2ee2dc"}},{"code_sha256_prefix":"d5d2cbcc026b705c","entry":"extract_boxes","repo":"linkangheng/pr1","repo_kind":"official","path":"eval/evaluate_counting.py","file_url":"https://github.com/linkangheng/pr1/blob/HEAD/eval/evaluate_counting.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d5d2cbcc026b705c"}},{"code_sha256_prefix":"a00db88497f19ef2","entry":"parse_float_sequence_within","repo":"linkangheng/pr1","repo_kind":"official","path":"eval/evaluate_grounding.py","file_url":"https://github.com/linkangheng/pr1/blob/HEAD/eval/evaluate_grounding.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a00db88497f19ef2"}},{"code_sha256_prefix":"779b00437fd21789","entry":"parse_output","repo":"linkangheng/pr1","repo_kind":"official","path":"eval/evaluate_counting.py","file_url":"https://github.com/linkangheng/pr1/blob/HEAD/eval/evaluate_counting.py","link_basis":"first_harvest_node","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":"779b00437fd21789"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}