{"total":32,"rows":[{"id":"2605.02881","title":"MolmoAct2: Action Reasoning Models for Real-world Deployment","created":"2026-05-04","cited_by_count":50,"area":"lr"},{"id":"2605.09874","title":"EgoMemReason: A Memory-Driven Reasoning Benchmark for Long-Horizon Egocentric Video Understanding","created":"2026-05-11","cited_by_count":13,"area":"lr"},{"id":"2602.08828","title":"VideoVeritas: AI-Generated Video Detection via Perception Pretext Reinforcement Learning","created":"2026-02-09","cited_by_count":11,"area":"lr"},{"id":"2604.04917","title":"Vero: An Open RL Recipe for General Visual Reasoning","created":"2026-04-06","cited_by_count":11,"area":"lr"},{"id":"2607.24904","title":"Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model","created":"2026-07-27","cited_by_count":10,"area":"lr"},{"id":"2602.06566","title":"SPARC: Separating Perception And Reasoning Circuits for Test-time Scaling of VLMs","created":"2026-02-06","cited_by_count":7,"area":"lr"},{"id":"2606.11324","title":"Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models","created":"2026-06-09","cited_by_count":6,"area":"lr"},{"id":"2603.26653","title":"PerceptionComp: A Video Benchmark for Complex Perception-Centric Reasoning","created":"2026-03-27","cited_by_count":4,"area":"lr"},{"id":"2606.28864","title":"On Test-Time Scaling for Vision-Language Models","created":"2026-06-27","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":"2603.16506","title":"VIEW2SPACE: Studying Multi-View Visual Reasoning from Sparse Observations","created":"2026-03-17","cited_by_count":3,"area":"lr"},{"id":"2603.18892","title":"MultihopSpatial: Multi-hop Compositional Spatial Reasoning Benchmark for Vision-Language Model","created":"2026-03-19","cited_by_count":3,"area":"lr"},{"id":"2603.25021","title":"VideoTIR: Accurate Understanding for Long Videos with Efficient Tool-Integrated Reasoning","created":"2026-03-26","cited_by_count":3,"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":"2605.07415","title":"ChartREG++: Towards Benchmarking and Improving Chart Referring Expression Grounding under Diverse referring clues and Multi-Target Referring","created":"2026-05-08","cited_by_count":2,"area":"lr"},{"id":"2606.22694","title":"SATURN: Symbolic Spatial Reasoning for Multi-Perspective Grounding","created":"2026-06-21","cited_by_count":2,"area":"lr"},{"id":"2607.00115","title":"PixelEyes: Decoupling Perception and Reasoning for Pinpoint Visual Evidence Seeking","created":"2026-06-30","cited_by_count":2,"area":"lr"},{"id":"2603.10978","title":"GroundCount: Grounding Vision-Language Models with Object Detection for Mitigating Counting Hallucinations","created":"2026-03-11","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":"2606.03988","title":"Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models","created":"2026-06-02","cited_by_count":1,"area":"lr"},{"id":"2607.12711","title":"MaxSAT-Based Feedback for Guiding Vision-Language Models in Sudoku","created":"2026-07-14","cited_by_count":1,"area":"lr"},{"id":"2607.13454","title":"GeoAnchor: Collaborative Reasoning via Latent Decomposition for 3D Spatial Understanding","created":"2026-07-15","cited_by_count":1,"area":"lr"},{"id":"2609.00746","title":"Text Capability Loss in Vision-Language Adaptation: An Attention-Sink Diagnosis","created":"2026-09-01","cited_by_count":1,"area":"lr"},{"id":"2603.21746","title":"Getting to the Point: Pointing Improves LVLMs at Counting","created":"2026-03-23","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":"2605.08452","title":"NICE FACT: Diagnosing and Calibrating VLMs in Quantitative Reasoning for Kinematic Physics","created":"2026-05-08","cited_by_count":0,"area":"lr"},{"id":"2606.12047","title":"Metadata-Aware Multi-Prompt Reasoning for Zero-Shot Accident Understanding","created":"2026-06-10","cited_by_count":0,"area":"lr"},{"id":"2608.24439","title":"DoublesEval: Diagnosing Multi-Agent Tactical Reasoning in Vision-Language Models via Professional Doubles Badminton","created":"2026-08-25","cited_by_count":0,"area":"lr"},{"id":"2608.28144","title":"The Shape of Power: A Multilingual Framework for Social Power Reasoning in Dialogues","created":"2026-08-28","cited_by_count":0,"area":"lr"},{"id":"2609.01515","title":"TempCloze: Can Video-LLMs Identify the Missing Middle?","created":"2026-09-01","cited_by_count":0,"area":"lr"},{"id":"2610.02091","title":"GeoLatent: Geometry-Guided Latent Structuring with Routed Optimization for 3D Reasoning","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.04469","title":"Trinity: Self-Evolving Vision-Language Models with a Self-Verifier","created":"2026-10-03","cited_by_count":0,"area":"lr"}],"next_cursor":null}