{"total":21,"rows":[{"id":"2504.06958","title":"VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning","created":"2025-04-09","cited_by_count":255,"area":"lr"},{"id":"2509.21100","title":"VideoChat-R1.5: Visual Test-Time Scaling to Reinforce Multimodal Reasoning by Iterative Perception","created":"2025-09-25","cited_by_count":65,"area":"lr"},{"id":"2506.07464","title":"DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO","created":"2025-06-09","cited_by_count":61,"area":"lr"},{"id":"2512.03043","title":"OneThinker: All-in-one Reasoning Model for Image and Video","created":"2025-12-02","cited_by_count":56,"area":"lr"},{"id":"2512.14698","title":"TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs","created":"2025-12-16","cited_by_count":50,"area":"lr"},{"id":"2602.02994","title":"Video-OPD: Efficient Post-Training of Multimodal Large Language Models for Temporal Video Grounding via On-Policy Distillation","created":"2026-02-03","cited_by_count":36,"area":"lr"},{"id":"2506.06097","title":"VideoChat-A1: Thinking with Long Videos by Chain-of-Shot Reasoning","created":"2025-06-06","cited_by_count":32,"area":"lr"},{"id":"2506.01908","title":"Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency","created":"2025-06-02","cited_by_count":26,"area":"lr"},{"id":"2509.23652","title":"ReWatch-R1: Boosting Complex Video Reasoning in Large Vision-Language Models through Agentic Data Synthesis","created":"2025-09-28","cited_by_count":26,"area":"lr"},{"id":"2503.16081","title":"OThink-MR1: Stimulating multimodal generalized reasoning capabilities via dynamic reinforcement learning","created":"2025-03-20","cited_by_count":24,"area":"lr"},{"id":"2512.17436","title":"Xiaomi MiMo-VL-Miloco Technical Report","created":"2025-12-19","cited_by_count":15,"area":"lr"},{"id":"2505.01583","title":"TEMPURA: Temporal Event Masked Prediction and Understanding for Reasoning in Action","created":"2025-05-02","cited_by_count":14,"area":"lr"},{"id":"2603.00905","title":"pySpatial: Generating 3D Visual Programs for Zero-Shot Spatial Reasoning","created":"2026-03-01","cited_by_count":14,"area":"lr"},{"id":"2510.23397","title":"VideoTG-R1: Boosting Video Temporal Grounding via Curriculum Reinforcement Learning on Reflected Boundary Annotations","created":"2025-10-27","cited_by_count":7,"area":"lr"},{"id":"2605.14733","title":"Video-Zero: Self-Evolution Video Understanding","created":"2026-05-14","cited_by_count":4,"area":"lr"},{"id":"2510.04428","title":"A.I.R.: Enabling Adaptive, Iterative, and Reasoning-based Frame Selection For Video Question Answering","created":"2025-10-06","cited_by_count":3,"area":"lr"},{"id":"2602.11730","title":"STVG-R1: Incentivizing Instance-Level Reasoning and Grounding in Videos via Reinforcement Learning","created":"2026-02-12","cited_by_count":3,"area":"lr"},{"id":"2606.09248","title":"Temporal-Aware Reasoning Optimization for Video Temporal Grounding","created":"2026-06-08","cited_by_count":3,"area":"lr"},{"id":"2607.01737","title":"ReQuest: Rethinking-based Question-Aware Frame Selection for Long-Form Video QA","created":"2026-07-02","cited_by_count":2,"area":"lr"},{"id":"2606.20561","title":"TimeProVe: Propose, then Verify for Efficient Long Video Temporal Reasoning in Activities of Daily Living","created":"2026-06-18","cited_by_count":0,"area":"lr"},{"id":"2610.16172","title":"EventLens: Event-Structure Reinforcement Learning for Video Understanding","created":"2026-10-12","cited_by_count":0,"area":"lr"}],"next_cursor":null}