{"total":68,"rows":[{"id":"2508.04416","title":"Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning","created":"2025-08-06","cited_by_count":91,"area":"lr"},{"id":"2505.04921","title":"Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models","created":"2025-05-08","cited_by_count":90,"area":"lr"},{"id":"2511.20785","title":"LongVT: Incentivizing \"Thinking with Long Videos\" via Native Tool Calling","created":"2025-11-25","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":"2512.02425","title":"WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning","created":"2025-12-02","cited_by_count":53,"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":"2510.20579","title":"Open-o3-Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence","created":"2025-10-23","cited_by_count":49,"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":"2510.23473","title":"Video-Thinker: Sparking \"Thinking with Videos\" via Reinforcement Learning","created":"2025-10-27","cited_by_count":34,"area":"lr"},{"id":"2507.06485","title":"Video-RTS: Rethinking Reinforcement Learning and Test-Time Scaling for Efficient and Enhanced Video Reasoning","created":"2025-07-09","cited_by_count":33,"area":"lr"},{"id":"2506.01725","title":"VideoCap-R1: Enhancing MLLMs for Video Captioning via Structured Thinking","created":"2025-06-02","cited_by_count":30,"area":"lr"},{"id":"2505.19877","title":"Vad-R1: Towards Video Anomaly Reasoning via Perception-to-Cognition Chain-of-Thought","created":"2025-05-26","cited_by_count":24,"area":"lr"},{"id":"2512.16918","title":"AdaTooler-V: Adaptive Tool-Use for Images and Videos","created":"2025-12-18","cited_by_count":21,"area":"lr"},{"id":"2601.05175","title":"VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice","created":"2026-01-08","cited_by_count":21,"area":"lr"},{"id":"2507.18100","title":"Datasets and Recipes for Video Temporal Grounding via Reinforcement Learning","created":"2025-07-24","cited_by_count":19,"area":"lr"},{"id":"2508.05612","title":"Shuffle-R1: Efficient RL framework for Multimodal Large Language Models via Data-centric Dynamic Shuffle","created":"2025-08-07","cited_by_count":19,"area":"lr"},{"id":"2511.13026","title":"REVISOR: Beyond Textual Reflection, Towards Multimodal Introspective Reasoning in Long-Form Video Understanding","created":"2025-11-17","cited_by_count":16,"area":"lr"},{"id":"2508.11538","title":"Reinforcing Video Reasoning Segmentation to Think Before It Segments","created":"2025-08-15","cited_by_count":15,"area":"lr"},{"id":"2512.17436","title":"Xiaomi MiMo-VL-Miloco Technical Report","created":"2025-12-19","cited_by_count":15,"area":"lr"},{"id":"2505.18536","title":"Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models","created":"2025-05-24","cited_by_count":14,"area":"lr"},{"id":"2505.24869","title":"SiLVR: A Simple Language-based Video Reasoning Framework","created":"2025-05-30","cited_by_count":14,"area":"lr"},{"id":"2506.17545","title":"Scene-R1: Video-Grounded Large Language Models for 3D Scene Reasoning without 3D Annotations","created":"2025-06-21","cited_by_count":14,"area":"lr"},{"id":"2511.21375","title":"Thinking With Bounding Boxes: Enhancing Spatio-Temporal Video Grounding via Reinforcement Fine-Tuning","created":"2025-11-26","cited_by_count":12,"area":"lr"},{"id":"2507.00748","title":"Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learning","created":"2025-07-01","cited_by_count":11,"area":"lr"},{"id":"2605.06094","title":"VISD: Enhancing Video Reasoning via Structured Self-Distillation","created":"2026-05-07","cited_by_count":10,"area":"lr"},{"id":"2506.05433","title":"Prefix Grouper: Efficient GRPO Training through Shared-Prefix Forward","created":"2025-06-05","cited_by_count":9,"area":"lr"},{"id":"2602.00181","title":"CamReasoner: Reinforcing Camera Movement Understanding via Structured Spatial Reasoning","created":"2026-01-30","cited_by_count":9,"area":"lr"},{"id":"2509.21113","title":"MOSS-ChatV: Reinforcement Learning with Process Reasoning Reward for Video Temporal Reasoning","created":"2025-09-25","cited_by_count":8,"area":"lr"},{"id":"2510.05034","title":"Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models","created":"2025-10-06","cited_by_count":8,"area":"lr"},{"id":"2511.11113","title":"VIDEOP2R: Video Understanding from Perception to Reasoning","created":"2025-11-14","cited_by_count":8,"area":"lr"},{"id":"2603.28610","title":"ResAdapt: Adaptive Resolution for Efficient Multimodal Reasoning","created":"2026-03-30","cited_by_count":8,"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":"2601.03248","title":"STReasoner: Empowering LLMs for Spatio-Temporal Reasoning in Time Series via Spatial-Aware Reinforcement Learning","created":"2026-01-06","cited_by_count":7,"area":"lr"},{"id":"2602.23306","title":"ThinkOmni: Lifting Textual Reasoning to Omni-modal Scenarios via Guidance Decoding","created":"2026-02-26","cited_by_count":7,"area":"lr"},{"id":"2510.10976","title":"Video-STR: Reinforcing MLLMs in Video Spatio-Temporal Reasoning with Relation Graph","created":"2025-10-13","cited_by_count":6,"area":"lr"},{"id":"2603.15600","title":"From Passive Observer to Active Critic: Reinforcement Learning Elicits Process Reasoning for Robotic Manipulation","created":"2026-03-16","cited_by_count":6,"area":"lr"},{"id":"2508.07683","title":"TAR: Temporal Anchor-Constrained Reasoning for Video Temporal Grounding","created":"2025-08-11","cited_by_count":5,"area":"lr"},{"id":"2602.17555","title":"GraphThinker: Reinforcing Temporally Grounded Video Reasoning with Event Graph Thinking","created":"2026-02-19","cited_by_count":5,"area":"lr"},{"id":"2603.18856","title":"Motion-o: Trajectory-Grounded Video Reasoning","created":"2026-03-19","cited_by_count":4,"area":"lr"},{"id":"2605.14733","title":"Video-Zero: Self-Evolution Video Understanding","created":"2026-05-14","cited_by_count":4,"area":"lr"},{"id":"2606.07433","title":"Watch, Remember, Reason: Human-View Video Understanding with MLLMs","created":"2026-06-05","cited_by_count":4,"area":"lr"},{"id":"2608.20492","title":"Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMs","created":"2026-08-20","cited_by_count":4,"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":"2604.01824","title":"STRIVE: Structured Spatiotemporal Exploration for Reinforcement Learning in Video Question Answering","created":"2026-04-02","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":"2512.00805","title":"Thinking with Drafts: Speculative Temporal Reasoning for Efficient Long Video Understanding","created":"2025-11-30","cited_by_count":2,"area":"lr"},{"id":"2603.10652","title":"Are Video Reasoning Models Ready to Go Outside?","created":"2026-03-11","cited_by_count":2,"area":"lr"},{"id":"2605.01324","title":"Beyond Perceptual Shortcuts: Causal-Inspired Debiasing Optimization for Generalizable Video Reasoning in Lightweight MLLMs","created":"2026-05-02","cited_by_count":2,"area":"lr"},{"id":"2604.20473","title":"Video-ToC: Video Tree-of-Cue Reasoning","created":"2026-04-22","cited_by_count":1,"area":"lr"},{"id":"2604.22226","title":"Towards Temporal Compositional Reasoning in Long-Form Sports Videos","created":"2026-04-24","cited_by_count":1,"area":"lr"},{"id":"2605.26014","title":"STORM: Internalized Modeling for Spatial-Temporal Reasoning in Video-Language Models","created":"2026-05-25","cited_by_count":1,"area":"lr"},{"id":"2608.07417","title":"I Seek You in Videos: Identity-Conditioned Queries for Person-Centric Video Reasoning","created":"2026-08-07","cited_by_count":1,"area":"lr"},{"id":"2511.18463","title":"Decoupling Perception from Reasoning for Hallucination-Resistant Video Understanding","created":"2025-11-23","cited_by_count":0,"area":"lr"},{"id":"2601.10165","title":"Advancing Adaptive Multi-Stage Video Anomaly Reasoning: A Benchmark Dataset and Method","created":"2026-01-15","cited_by_count":0,"area":"lr"},{"id":"2604.00696","title":"TTA-Vid: Generalized Test-Time Adaptation for Video Reasoning","created":"2026-04-01","cited_by_count":0,"area":"lr"},{"id":"2604.04415","title":"STEER: Structured Event Evidence for Video Reasoning via Multi-Objective Reinforcement Learning","created":"2026-04-06","cited_by_count":0,"area":"lr"},{"id":"2604.11283","title":"Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey","created":"2026-04-13","cited_by_count":0,"area":"lr"},{"id":"2605.07334","title":"RCoT-Seg: Reinforced Chain-of-Thought for Video Reasoning and Segmentation","created":"2026-05-08","cited_by_count":0,"area":"lr"},{"id":"2605.23216","title":"CaST-Bench: Benchmarking Causal Chain-Grounded Spatio-Temporal Reasoning for Video Question Answering","created":"2026-05-22","cited_by_count":0,"area":"lr"},{"id":"2606.00775","title":"GIRL-DETR: Gradient-Isolated Reinforcement Learning for Video Moment Retrieval","created":"2026-05-30","cited_by_count":0,"area":"lr"},{"id":"2606.08436","title":"CACR:Reinforcing Temporal Answer Grounding in Instructional Video via Candidate-Aware Causal Reasoning","created":"2026-06-07","cited_by_count":0,"area":"lr"},{"id":"2606.11209","title":"ProcessThinker: Enhancing Multi-modal Large Language Models Reasoning via Rollout-based Process Reward","created":"2026-04-23","cited_by_count":0,"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":"2607.05089","title":"TimeThink: Reasoning with Time for Video LLMs","created":"2026-07-06","cited_by_count":0,"area":"lr"},{"id":"2608.26684","title":"Reason in the Words You Speak: Idiolectal Paraphrasing Off-Policy Traces for Reasoning Distillation in VideoLLMs","created":"2026-08-27","cited_by_count":0,"area":"lr"},{"id":"2610.10893","title":"Less from More: Reinforcing Sparse Video Reasoning from Dense References","created":"2026-10-07","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"},{"id":"2610.17656","title":"Open-o3-Video-v2: Seek, Ground, and Reason with Verifiable Spatio-Temporal Evidence","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}