{"total":31,"rows":[{"id":"2509.25373","title":"From Perception to Cognition: A Survey of Vision-Language Interactive Reasoning in Multimodal Large Language Models","created":"2025-09-29","cited_by_count":26,"area":"lr"},{"id":"2603.22280","title":"DualCoT-VLA: Visual-Linguistic Chain of Thought via Parallel Reasoning for Vision-Language-Action Models","created":"2026-03-23","cited_by_count":20,"area":"lr"},{"id":"2510.09606","title":"SpaceVista: All-Scale Visual Spatial Reasoning from mm to km","created":"2025-10-10","cited_by_count":19,"area":"lr"},{"id":"2602.04476","title":"Vision-aligned Latent Reasoning for Multi-modal Large Language Model","created":"2026-02-04","cited_by_count":18,"area":"lr"},{"id":"2510.11026","title":"GIR-Bench: Versatile Benchmark for Generating Images with Reasoning","created":"2025-10-13","cited_by_count":15,"area":"lr"},{"id":"2608.27549","title":"Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning","created":"2026-08-27","cited_by_count":14,"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":"2511.18833","title":"PrismAudio: Decomposed Chain-of-Thoughts and Multi-dimensional Rewards for Video-to-Audio Generation","created":"2025-11-24","cited_by_count":9,"area":"lr"},{"id":"2603.19235","title":"Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding","created":"2026-03-19","cited_by_count":7,"area":"lr"},{"id":"2602.21186","title":"Spa3R: Predictive Spatial Field Modeling for 3D Visual Reasoning","created":"2026-02-24","cited_by_count":6,"area":"lr"},{"id":"2512.15885","title":"Seeing Beyond Words: Self-Supervised Visual Learning for Multimodal Large Language Models","created":"2025-12-17","cited_by_count":5,"area":"lr"},{"id":"2509.15271","title":"Large Vision Models Can Solve Mental Rotation Problems","created":"2025-09-18","cited_by_count":4,"area":"lr"},{"id":"2603.07530","title":"ICLR: In-Context Imitation Learning with Visual Reasoning","created":"2026-03-08","cited_by_count":4,"area":"lr"},{"id":"2603.07888","title":"VLM-SubtleBench: How Far Are VLMs from Human-Level Subtle Comparative Reasoning?","created":"2026-03-09","cited_by_count":4,"area":"lr"},{"id":"2606.06538","title":"WorldBench: A Challenging and Visually Diverse Multimodal Reasoning Benchmark","created":"2026-06-04","cited_by_count":4,"area":"lr"},{"id":"2603.21526","title":"VIGIL: Part-Grounded Structured Reasoning for Generalizable Deepfake Detection","created":"2026-03-23","cited_by_count":3,"area":"lr"},{"id":"2509.13666","title":"DREAM: Domain-aware Reasoning for Efficient Autonomous Underwater Monitoring","created":"2025-09-17","cited_by_count":2,"area":"lr"},{"id":"2603.22057","title":"SpatialBoost: Enhancing Visual Representation through Language-Guided Reasoning","created":"2026-03-23","cited_by_count":2,"area":"lr"},{"id":"2604.20705","title":"SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models","created":"2026-04-22","cited_by_count":2,"area":"lr"},{"id":"2601.03191","title":"AnatomiX, an Anatomy-Aware Grounded Multimodal Large Language Model for Chest X-Ray Interpretation","created":"2026-01-06","cited_by_count":1,"area":"lr"},{"id":"2601.11729","title":"SpaRRTa: A Synthetic Benchmark for Evaluating Spatial Intelligence in Visual Foundation Models","created":"2026-01-16","cited_by_count":1,"area":"lr"},{"id":"2601.13401","title":"Reasoning with Pixel-level Precision: QVLM Architecture and SQuID Dataset for Quantitative Geospatial Analytics","created":"2026-01-19","cited_by_count":1,"area":"lr"},{"id":"2602.19615","title":"Seeing Clearly, Reasoning Confidently: Plug-and-Play Remedies for Vision Language Model Blindness","created":"2026-02-23","cited_by_count":1,"area":"lr"},{"id":"2604.13268","title":"Indexing Multimodal Language Models for Large-scale Image Retrieval","created":"2026-04-14","cited_by_count":1,"area":"lr"},{"id":"2606.07602","title":"Sample-Efficient Post-Training for LEGO Spatial-Physics Reasoning","created":"2026-05-29","cited_by_count":1,"area":"lr"},{"id":"2601.22231","title":"Geometry without Position? When Positional Embeddings Help and Hurt Spatial Reasoning","created":"2026-01-29","cited_by_count":0,"area":"lr"},{"id":"2604.16587","title":"Real-Time Visual Attribution Streaming in Thinking Model","created":"2026-04-17","cited_by_count":0,"area":"lr"},{"id":"2604.28011","title":"Echo-{\\alpha}: Large Agentic Multimodal Reasoning Model for Ultrasound Interpretation","created":"2026-04-30","cited_by_count":0,"area":"lr"},{"id":"2608.10864","title":"Multi-View Relational Distillation for Spatial Reasoning with Vision-Language Models","created":"2026-08-11","cited_by_count":0,"area":"lr"},{"id":"2610.15403","title":"A Decade of PhotoMappers: A Longitudinal Study of Crowdsourced Disaster Photos Geolocalization with Vision-Language Models and Geospatial Reasoning","created":"2026-10-11","cited_by_count":0,"area":"lr"},{"id":"2610.17844","title":"What Makes a Good Visual Representation for Spatial Understanding in MLLMs?","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}