{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:03:49Z","timestamp":1791911029546,"version":"4.3.4"},"publisher-location":"Cham","reference-count":53,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032375766","type":"print"},{"value":"9783032375773","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-37577-3_34","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T23:01:13Z","timestamp":1788994873000},"page":"623-640","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Reinforcing Video Reasoning with\u00a0Focused Thinking"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-0082-1935","authenticated-orcid":false,"given":"Jisheng","family":"Dang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0354-9093","authenticated-orcid":false,"given":"Jingze","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2331-3619","authenticated-orcid":false,"given":"Teng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2139-1274","authenticated-orcid":false,"given":"Xuanhui","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4038-3053","authenticated-orcid":false,"given":"Nannan","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1071-4966","authenticated-orcid":false,"given":"Hongbo","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8327-0003","authenticated-orcid":false,"given":"Wei-Shi","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3094-7735","authenticated-orcid":false,"given":"Meng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6097-7807","authenticated-orcid":false,"given":"Tat-Seng","family":"Chua","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"34_CR1","doi-asserted-by":"crossref","unstructured":"Agarwal, S., Zhang, Z., Yuan, L., Han, J., Peng, H.: The unreasonable effectiveness of entropy minimization in LLM reasoning. NeurIPS 38, 107150\u2013107180 (2025)","DOI":"10.52202\/085713-3573"},{"key":"34_CR2","unstructured":"Bai, S., et\u00a0al.: Qwen3-vl technical report. arXiv preprint arXiv:2511.21631 (2025)"},{"key":"34_CR3","unstructured":"Bai, S., et\u00a0al.: Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"34_CR4","unstructured":"Bigelow, E., Holtzman, A., Tanaka, H., Ullman, T.: Forking paths in neural text generation. In: ICLR, vol.\u00a02025, pp. 17134\u201317167 (2025)"},{"key":"34_CR5","unstructured":"Chen, L., Li, L., Zhao, H., Song, Y., Vinci: R1-v: reinforcing super generalization ability in vision-language models with less than \\$3 (2025). https:\/\/github.com\/Deep-Agent\/R1-V. Accessed 02 Feb 2025"},{"key":"34_CR6","unstructured":"Chen, M., Chen, G., Wang, W., Yang, Y.: Seed-grpo: semantic entropy enhanced grpo for uncertainty-aware policy optimization. arXiv preprint arXiv:2505.12346 (2025)"},{"key":"34_CR7","unstructured":"Cheng, Z., et\u00a0al.: Videollama 2: advancing spatial-temporal modeling and audio understanding in video-llms. arXiv preprint arXiv:2406.07476 (2024)"},{"key":"34_CR8","doi-asserted-by":"crossref","unstructured":"Dai, W., Chen, P., Ekbote, C., Liang, P.P.: Qoq-med: building multimodal clinical foundation models with domain-aware GRPO training. NeurIPS 38, 37406\u201337453 (2025)","DOI":"10.52202\/085713-1256"},{"key":"34_CR9","unstructured":"Du, W., Yang, Y., Welleck, S.: Optimizing temperature for language models with multi-sample inference. In: ICML, vol. 267, pp. 14648\u201314668. PMLR (2025)"},{"key":"34_CR10","unstructured":"Fan, K., Feng, K., Lyu, H., Zhou, D., Yue, X.: Sophiavl-r1: reinforcing mllms reasoning with thinking reward (2025). arXiv preprint arXiv:2505.17018"},{"key":"34_CR11","doi-asserted-by":"crossref","unstructured":"Feng, K., et al.: Video-r1: reinforcing video reasoning in MLLMs. In: NeurIPS, vol.\u00a038, pp. 99114\u201399137 (2025)","DOI":"10.52202\/085713-3310"},{"key":"34_CR12","doi-asserted-by":"crossref","unstructured":"Fu, C., et\u00a0al.: Video-mme: the first-ever comprehensive evaluation benchmark of multi-modal llms in video analysis. In: CVPR, pp. 24108\u201324118 (2025)","DOI":"10.1109\/CVPR52734.2025.02245"},{"issue":"8081","key":"34_CR13","doi-asserted-by":"publisher","first-page":"633","DOI":"10.1038\/s41586-025-09422-z","volume":"645","author":"D Guo","year":"2025","unstructured":"Guo, D., et al.: Deepseek-r1 incentivizes reasoning in llms through reinforcement learning. Nature 645(8081), 633\u2013638 (2025)","journal-title":"Nature"},{"key":"34_CR14","unstructured":"Jiang, D., et al.: MME-CoT: benchmarking chain-of-thought in large multimodal models for reasoning quality, robustness, and efficiency. In: ICML, vol.\u00a0267, pp. 27793\u201327830. PMLR (2025)"},{"key":"34_CR15","doi-asserted-by":"crossref","unstructured":"Kang, Z., Zhao, X., Song, D.: Scalable best-of-n selection for large language models via self-certainty. NeurIPS 38, 19720\u201319745 (2025)","DOI":"10.52202\/085713-0663"},{"key":"34_CR16","doi-asserted-by":"crossref","unstructured":"Li, K., et\u00a0al.: Mvbench: a comprehensive multi-modal video understanding benchmark. In: CVPR, pp. 22195\u201322206 (2024)","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"34_CR17","unstructured":"Li, X., et\u00a0al.: Videochat-r1: enhancing spatio-temporal perception via reinforcement fine-tuning. arXiv preprint arXiv:2504.06958 (2025)"},{"key":"34_CR18","doi-asserted-by":"publisher","unstructured":"Li, Y., Wang, C., Jia, J.: LLaMA-VID: an image is worth 2 tokens in large language models. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision \u2013 ECCV 2024. ECCV 2024. LNCS, vol. 15104, pp. 323\u2013340. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-72952-2_19","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"34_CR19","unstructured":"Lin, Z., et al.: Critical tokens matter: token-level contrastive estimation enhances LLM\u2019s reasoning capability. In: ICML, vol. 267, pp. 37906\u201337918. PMLR (2025)"},{"key":"34_CR20","doi-asserted-by":"crossref","unstructured":"Liu, J., et al.: Kangaroo: a powerful video-language model supporting long-context video input: J. liu et al. IJCV 134(3), \u00a0114 (2026)","DOI":"10.1007\/s11263-025-02620-2"},{"key":"34_CR21","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Tempcompass: do video llms really understand videos? In: ACL Findings, pp. 8731\u20138772 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.517"},{"key":"34_CR22","unstructured":"Liu, Z., et al.: Understanding r1-zero-like training: a critical perspective. In: 2nd AI for Math Workshop @ ICML 2025 (2025)"},{"key":"34_CR23","unstructured":"Liu, Z., et al.: Acereason-nemotron 1.1: advancing math and code reasoning through sft and rl synergy (2025). arXiv preprint arXiv:2506.13284"},{"key":"34_CR24","unstructured":"Meng, D., et\u00a0al.: Videocap-r1: enhancing mllms for video captioning via structured thinking. arXiv preprint arXiv:2506.01725 (2025)"},{"key":"34_CR25","unstructured":"Meng, F., et\u00a0al.: Mm-eureka: exploring the frontiers of multimodal reasoning with rule-based reinforcement learning (2025). arXiv preprint arXiv:2503.07365"},{"key":"34_CR26","doi-asserted-by":"crossref","unstructured":"Oh, B.D., Schuler, W.: Token-wise decomposition of autoregressive language model hidden states for analyzing model predictions. In: ACL, vol. 1, pp. 10105\u201310117 (2023)","DOI":"10.18653\/v1\/2023.acl-long.562"},{"key":"34_CR27","unstructured":"Peng, Y., et al.: Lmm-r1: empowering 3b lmms with strong reasoning abilities through two-stage rule-based rl. arXiv preprint arXiv:2503.07536 (2025)"},{"key":"34_CR28","unstructured":"Qin, T., et al.: Decomposing elements of problem solving: what \u201cmath\u201d does rl teach? (2025). arXiv preprint arXiv:2505.22756"},{"key":"34_CR29","unstructured":"Samineni, S.R., Kalwar, D., Valmeekam, K., Stechly, K., Kambhampati, S.: RL in name only? Analyzing the structural assumptions in RL post-training for LLMs. In: NeurIPS 2025 Workshop on Bridging Language, Agent, and World Models for Reasoning and Planning (2025)"},{"key":"34_CR30","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms (2017). arXiv preprint arXiv:1707.06347"},{"key":"34_CR31","unstructured":"Shao, Z., et\u00a0al.: Deepseekmath: pushing the limits of mathematical reasoning in open language models. arXiv preprint arXiv:2402.03300 (2024)"},{"key":"34_CR32","doi-asserted-by":"crossref","unstructured":"Shu, F., Zhang, L., Jiang, H., Xie, C.: Audio-visual llm for video understanding. In: ICCV, pp. 4246\u20134255 (2025)","DOI":"10.1109\/ICCVW69036.2025.00447"},{"key":"34_CR33","unstructured":"Tian, X., et al.: More thought, less accuracy? On the dual nature of reasoning in vision-language models. In: ICLR (2026)"},{"key":"34_CR34","doi-asserted-by":"crossref","unstructured":"Wang, Q., Yu, Y., Yuan, Y., Mao, R., Zhou, T.: VideoRFT: incentivizing video reasoning capability in MLLMs via reinforced fine-tuning. In: NeurIPS, vol.\u00a038, pp. 4350\u20134376 (2025)","DOI":"10.52202\/085713-0155"},{"key":"34_CR35","unstructured":"von Werra, L., et al.: Trl: transformer reinforcement learning (2020). https:\/\/github.com\/huggingface\/trl"},{"key":"34_CR36","unstructured":"Wu, B., Yu, S., Chen, Z., Tenenbaum, J.B., Gan, C.: Star: a benchmark for situated reasoning in real-world videos (2024). arXiv preprint arXiv:2405.09711"},{"key":"34_CR37","doi-asserted-by":"crossref","unstructured":"Xiao, J., Yao, A., Li, Y., Chua, T.S.: Can i trust your answer? Visually grounded video question answering. In: CVPR, pp. 13204\u201313214 (2024)","DOI":"10.1109\/CVPR52733.2024.01254"},{"key":"34_CR38","doi-asserted-by":"publisher","unstructured":"Yan, C., et al.: VISA: reasoning video object segmentation via large language models. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision \u2013 ECCV 2024. ECCV 2024. LNCS, vol. 15073, pp. 98\u2013115. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-72633-0_6","DOI":"10.1007\/978-3-031-72633-0_6"},{"key":"34_CR39","unstructured":"Yi, K., et al.: Clevrer: collision events for video representation and reasoning. In: ICLR (2020)"},{"key":"34_CR40","unstructured":"Yu, E., et\u00a0al.: Unhackable temporal rewarding for scalable video mllms. arXiv preprint arXiv:2502.12081 (2025)"},{"key":"34_CR41","doi-asserted-by":"crossref","unstructured":"Yu, Q., et\u00a0al.: Dapo: an open-source llm reinforcement learning system at scale. In: NeurIPS, vol.\u00a038, pp. 113222\u2013113244 (2025)","DOI":"10.52202\/085713-3775"},{"key":"34_CR42","unstructured":"Yue, Y., et al.: Does reinforcement learning really incentivize reasoning capacity in LLMs beyond the base model? In: NeurIPS, vol.\u00a038, pp. 57654\u201357689 (2025)"},{"key":"34_CR43","unstructured":"Zhan, Y., et al.: Vision-r1: evolving human-free alignment in large vision-language models via vision-guided reinforcement learning. In: CVPR, pp. 5807\u20135817 (2026)"},{"key":"34_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: R1-vl: learning to reason with multimodal large language models via step-wise group relative policy optimization. In: ICCV, pp. 1859\u20131869 (2025)","DOI":"10.1109\/ICCV51701.2025.00181"},{"key":"34_CR45","unstructured":"Zhang, P., et al.: Long context transfer from language to vision. TMLR (2025)"},{"key":"34_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Wu, H., Zhang, C., Zhao, P., Bian, Y.: Right question is already half the answer: fully unsupervised llm reasoning incentivization. In: NeurIPS, vol.\u00a038, pp. 67345\u201367372 (2025)","DOI":"10.52202\/085713-2259"},{"key":"34_CR47","unstructured":"Zhang, T., et al.: TokUR: token-level uncertainty estimation for large language mode reasoning. In: First Workshop on Foundations of Reasoning in Language Models (2025)"},{"key":"34_CR48","unstructured":"Zhang, X., et al.: Towards self-improving systematic cognition for next-generation foundation mllms. arXiv preprint arXiv:2503.12303 (2025)"},{"key":"34_CR49","unstructured":"Zhang, Y., et\u00a0al.: Llava-uhd v2: an mllm integrating high-resolution feature pyramid via hierarchical window transformer. arXiv preprint arXiv:2412.13871 (2024)"},{"key":"34_CR50","unstructured":"Zhao, X., Kang, Z., Feng, A., Levine, S., Song, D.: Learning to reason without external rewards. In: 2nd AI for Math Workshop @ ICML 2025 (2025)"},{"key":"34_CR51","doi-asserted-by":"crossref","unstructured":"Zhao, Y., et\u00a0al.: Mmvu: measuring expert-level multi-discipline video understanding. In: CVPR, pp. 8475\u20138489 (2025)","DOI":"10.1109\/CVPR52734.2025.00793"},{"key":"34_CR52","unstructured":"Zheng, R., et\u00a0al.: Secrets of rlhf in large language models part i: ppo. arXiv preprint arXiv:2307.04964 (2023)"},{"key":"34_CR53","unstructured":"Zhou, H., Li, X., Wang, R., Cheng, M., Zhou, T., Hsieh, C.J.: R1-zero\u2019s aha moment in visual reasoning on a 2b non-sft model. arXiv preprint arXiv:2503.05132 (2025)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37577-3_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T23:01:24Z","timestamp":1788994884000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37577-3_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032375766","9783032375773"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37577-3_34","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"10 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}