{"total":21,"rows":[{"id":"2510.10991","title":"A Survey on Agentic Multimodal Large Language Models","created":"2025-10-13","cited_by_count":23,"area":"mllm"},{"id":"2510.11341","title":"InternSVG: Towards Unified SVG Tasks with Multimodal Large Language Models","created":"2025-10-13","cited_by_count":14,"area":"mllm"},{"id":"2602.01816","title":"Seeing Is Believing? A Benchmark for Multimodal Large Language Models on Visual Illusions and Anomalies","created":"2026-02-02","cited_by_count":8,"area":"mllm"},{"id":"2603.06569","title":"Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders","created":"2026-03-06","cited_by_count":7,"area":"mllm"},{"id":"2606.03890","title":"OVO-S-Bench: A Hierarchical Benchmark for Streaming Spatial Intelligence in Multimodal LLMs","created":"2026-06-02","cited_by_count":6,"area":"mllm"},{"id":"2603.25804","title":"RealChart2Code: Advancing Chart-to-Code Generation with Real Data and Multi-Task Evaluation","created":"2026-03-26","cited_by_count":4,"area":"mllm"},{"id":"2604.08014","title":"Bridging Time and Space: Decoupled Spatio-Temporal Alignment for Video Grounding","created":"2026-04-09","cited_by_count":3,"area":"mllm"},{"id":"2510.25867","title":"Synthesizing High-Quality Visual Question Answering from Medical Documents with Generator-Verifier LMMs","created":"2025-10-29","cited_by_count":2,"area":"mllm"},{"id":"2606.28551","title":"DataComp-VLM: Improved Open Datasets for Vision-Language Models","created":"2026-06-26","cited_by_count":2,"area":"mllm"},{"id":"2602.13650","title":"KorMedMCQA-V: A Multimodal Benchmark for Evaluating Vision-Language Models on the Korean Medical Licensing Examination","created":"2026-02-14","cited_by_count":1,"area":"mllm"},{"id":"2602.22426","title":"SimpleOCR: Rendering Visualized Questions to Teach MLLMs to Read","created":"2026-02-25","cited_by_count":1,"area":"mllm"},{"id":"2605.30911","title":"What Makes LVLMs Hallucinate Less? Unveiling the Architectural Factors Behind Hallucination Robustness","created":"2026-05-29","cited_by_count":1,"area":"mllm"},{"id":"2608.03471","title":"Hi-Token: Hierarchical Coordinate Tokenization for Generative Visual Grounding","created":"2026-08-04","cited_by_count":1,"area":"mllm"},{"id":"2511.22943","title":"Visual Puns from Idioms: An Iterative LLM-T2IM-MLLM Framework","created":"2025-11-28","cited_by_count":0,"area":"mllm"},{"id":"2601.19613","title":"Up to 36x Speedup: Mask-based Parallel Inference Paradigm for Key Information Extraction in MLLMs","created":"2026-01-27","cited_by_count":0,"area":"mllm"},{"id":"2602.06402","title":"MeDocVL: A Visual Language Model for Medical Document Understanding and Parsing","created":"2026-02-06","cited_by_count":0,"area":"mllm"},{"id":"2603.20148","title":"Can Large Multimodal Models Inspect Buildings? A Hierarchical Benchmark for Structural Pathology Reasoning","created":"2026-03-20","cited_by_count":0,"area":"mllm"},{"id":"2603.28387","title":"Prompts Without Evidence: How Neuroimaging Mentions Shift Clinical Vision-Language Model Predictions","created":"2026-03-30","cited_by_count":0,"area":"mllm"},{"id":"2606.04433","title":"Stateful Visual Encoders for Vision-Language Models","created":"2026-06-03","cited_by_count":0,"area":"mllm"},{"id":"2607.02680","title":"K9-Bench: Evaluating Multimodal LLMs on Canine-Centric Videos","created":"2026-07-02","cited_by_count":0,"area":"mllm"},{"id":"2607.15732","title":"IoU-PD: IoU-Aware Privileged Distillation for Visual Grounding with Multimodal Large Language Models","created":"2026-07-17","cited_by_count":0,"area":"mllm"}],"next_cursor":null}