{"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/videochat-r1-enhancing-spatio-temporal","title":"VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning","arxiv_id":"2504.06958","date":"2025-04-09","proceeding":null,"authors":["Xinhao Li","Ziang Yan","Desen Meng","Lu Dong","Xiangyu Zeng","Yinan He","Yali Wang","Yu Qiao","Yi Wang","LiMin Wang"],"abstract":"Recent advancements in reinforcement learning have significantly advanced the reasoning capabilities of multimodal large language models (MLLMs). While approaches such as Group Relative Policy Optimization (GRPO) and rule-based reward mechanisms demonstrate promise in text and image domains, their application to video understanding remains limited. This paper presents a systematic exploration of Reinforcement Fine-Tuning (RFT) with GRPO for video MLLMs, aiming to enhance spatio-temporal perception while maintaining general capabilities. Our experiments reveal that RFT is highly data-efficient for task-specific improvements. Through multi-task RFT on spatio-temporal perception objectives with limited samples, we develop VideoChat-R1, a powerful video MLLM that achieves state-of-the-art performance on spatio-temporal perception tasks without sacrificing chat ability, while exhibiting emerging spatio-temporal reasoning abilities. Compared to Qwen2.5-VL-7B, VideoChat-R1 boosts performance several-fold in tasks like temporal grounding (+31.8) and object tracking (+31.2). Additionally, it significantly improves on general QA benchmarks such as VideoMME (+0.9), MVBench (+1.0), and Perception Test (+0.9). Our findings underscore the potential of RFT for specialized task enhancement of Video MLLMs. We hope our work offers valuable insights for future RL research in video MLLMs.","url_abs":"https://arxiv.org/abs/2504.06958v2","url_pdf":"https://arxiv.org/pdf/2504.06958v2.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":"videochat-r1-enhancing-spatio-temporal","repo_url":"https://github.com/opengvlab/videochat-r1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"MVBench"},{"task_slug":"object-tracking","task_name":"Object Tracking"},{"task_slug":"video-understanding","task_name":"Video Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2504.06958","atlas_url":"https://app.syntology.ai/?focus=2504.06958","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.06958"}},"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/opengvlab/videochat-r1","reach":null}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"ea06eaae4fc1eaf0","entry":"hash_args","repo":"opengvlab/videochat-r1","repo_kind":"listed","path":"Videochat-R1/lmms-eval_videochat/lmms_eval/api/model.py","file_url":"https://github.com/opengvlab/videochat-r1/blob/HEAD/Videochat-R1/lmms-eval_videochat/lmms_eval/api/model.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ea06eaae4fc1eaf0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}