{"total":16,"rows":[{"id":"2504.09724","title":"A Survey on Efficient Vision-Language Models","created":"2025-04-13","cited_by_count":19,"area":"mllm"},{"id":"2408.02454","title":"VL-TGS: Trajectory Generation and Selection using Vision Language Models in Mapless Outdoor Environments","created":"2024-08-05","cited_by_count":11,"area":"mllm"},{"id":"2410.05191","title":"LADEV: A Language-Driven Testing and Evaluation Platform for Vision-Language-Action Models in Robotic Manipulation","created":"2024-10-07","cited_by_count":9,"area":"mllm"},{"id":"2502.10636","title":"USER-VLM 360: Personalized Vision Language Models with User-aware Tuning for Social Human-Robot Interactions","created":"2025-02-15","cited_by_count":6,"area":"mllm"},{"id":"2409.12842","title":"Vision Language Models Can Parse Floor Plan Maps","created":"2024-09-19","cited_by_count":5,"area":"mllm"},{"id":"2512.14757","title":"SocialNav-MoE: A Mixture-of-Experts Vision Language Model for Socially Compliant Navigation with Reinforcement Fine-Tuning","created":"2025-12-15","cited_by_count":5,"area":"mllm"},{"id":"2405.20795","title":"InsightSee: Advancing Multi-agent Vision-Language Models for Enhanced Visual Understanding","created":"2024-05-31","cited_by_count":3,"area":"mllm"},{"id":"2505.20503","title":"Embodied AI with Foundation Models for Mobile Service Robots: A Systematic Review","created":"2025-05-26","cited_by_count":3,"area":"mllm"},{"id":"2601.14622","title":"Probing Prompt Design for Socially Compliant Robot Navigation with Vision Language Models","created":"2026-01-21","cited_by_count":1,"area":"mllm"},{"id":"2504.05477","title":"Trust Through Transparency: Explainable Social Navigation for Autonomous Mobile Robots via Vision-Language Models","created":"2025-04-07","cited_by_count":0,"area":"mllm"},{"id":"2506.20373","title":"CARMA: Context-Aware Situational Grounding of Human-Robot Group Interactions by Combining Vision-Language Models with Object and Action Recognition","created":"2025-06-25","cited_by_count":0,"area":"mllm"},{"id":"2507.11079","title":"Tactical Decision for Multi-UGV Confrontation with a Vision-Language Model-Based Commander","created":"2025-07-15","cited_by_count":0,"area":"mllm"},{"id":"2603.11447","title":"Enhancing Lightweight Vision Language Models through Group Competitive Learning for Socially Compliant Navigation","created":"2026-03-12","cited_by_count":0,"area":"mllm"},{"id":"2607.16318","title":"The World According to a Social Robot -- Augmenting Human-Robot Dialogue With Vision Language Models","created":"2026-07-15","cited_by_count":0,"area":"mllm"},{"id":"2608.06154","title":"Visual Grounding in Zero-Shot Vision-Language Control","created":"2026-08-06","cited_by_count":0,"area":"mllm"},{"id":"2609.22925","title":"\"Dear LLaVA, Please Drive\": A Depth-Aware Vision-Language Agent for Closed-Loop Robotic Control","created":"2026-09-19","cited_by_count":0,"area":"mllm"}],"next_cursor":null}