{"total":16,"rows":[{"id":"2510.25122","title":"NanoVLA: Routing Decoupled Vision-Language Understanding for Nano-sized Generalist Robotic Policies","created":"2025-10-29","cited_by_count":12,"area":"mllm"},{"id":"2512.23562","title":"VL-RouterBench: A Benchmark for Vision-Language Model Routing","created":"2025-12-29","cited_by_count":8,"area":"mllm"},{"id":"2412.18072","title":"MMFactory: A Universal Solution Search Engine for Vision-Language Tasks","created":"2024-12-24","cited_by_count":7,"area":"mllm"},{"id":"2603.09018","title":"Meissa: Multi-modal Medical Agentic Intelligence","created":"2026-03-09","cited_by_count":6,"area":"mllm"},{"id":"2510.27256","title":"ECVL-ROUTER: Scenario-Aware Routing for Vision-Language Models","created":"2025-10-31","cited_by_count":4,"area":"mllm"},{"id":"2601.18735","title":"Why Keep Your Doubts to Yourself? Trading Visual Uncertainties in Multi-Agent Bandit Systems","created":"2026-01-26","cited_by_count":4,"area":"mllm"},{"id":"2605.18853","title":"INAR-VL: Input-Aware Routing for Edge-Cloud Vision-Language Inference","created":"2026-05-13","cited_by_count":2,"area":"mllm"},{"id":"2609.06922","title":"BEFORE THE FLIP: Measuring Hidden Score Shifts In Quantized Vision Language Models Before The Answer Changes for Visual Question Answering","created":"2026-09-07","cited_by_count":1,"area":"mllm"},{"id":"2602.00485","title":"Replacing Parameters with Preferences: Federated Alignment of Heterogeneous Vision-Language Models","created":"2026-01-31","cited_by_count":0,"area":"mllm"},{"id":"2603.17111","title":"Hidden Clones: Exposing and Fixing Family Bias in Vision-Language Model Ensembles","created":"2026-03-17","cited_by_count":0,"area":"mllm"},{"id":"2603.24787","title":"ReLope: KL-Regularized LoRA Probes for Multimodal LLM Routing","created":"2026-03-25","cited_by_count":0,"area":"mllm"},{"id":"2605.03426","title":"Replacing Parameters with Preferences: Federated Alignment of Heterogeneous Vision-Language Models","created":"2026-05-05","cited_by_count":0,"area":"mllm"},{"id":"2605.06339","title":"A Regime Theory of Controller Class Selection for LLM Action Decisions","created":"2026-05-07","cited_by_count":0,"area":"mllm"},{"id":"2606.19646","title":"SAFE-Cascade: Cost-Adaptive Vision-Language Routing for Chart Question Answering","created":"2026-06-17","cited_by_count":0,"area":"mllm"},{"id":"2609.38413","title":"VidHarness: Evolving Agent Harnesses for Cost-Efficient Long Video Understanding","created":"2026-09-29","cited_by_count":0,"area":"mllm"},{"id":"2610.13278","title":"MHR-Router: Multimodal Heterogeneous Retrieval-Enhanced Adaptive Routing for VLM Inference","created":"2026-10-09","cited_by_count":0,"area":"mllm"}],"next_cursor":null}