{"total":18,"rows":[{"id":"2605.09272","title":"Towards Conversational Medical AI with Eyes, Ears and a Voice","created":"2026-05-10","cited_by_count":4,"area":null},{"id":"2606.14957","title":"Learning Sparse Latent Predictive Foundation Model for Multimodal Neuroimaging","created":"2026-06-12","cited_by_count":4,"area":null},{"id":"2605.23715","title":"NLG Evaluation: Past, Present, Future","created":"2026-05-22","cited_by_count":2,"area":null},{"id":"2607.28516","title":"Beyond Frame Selection: Generative Latent Evidence Aggregation for Long-Video Understanding","created":"2026-07-30","cited_by_count":2,"area":null},{"id":"2605.09693","title":"Do multimodal models imagine electric sheep?","created":"2026-05-10","cited_by_count":1,"area":null},{"id":"2606.30220","title":"From Accuracy to Visual Dependence: Auditing and Filtering Modality Collapse in Traffic VideoQA","created":"2026-06-29","cited_by_count":1,"area":null},{"id":"2608.06564","title":"Which Decisions Low-Bit Quantization Breaks, and How to Predict Them","created":"2026-08-06","cited_by_count":1,"area":null},{"id":"2605.07919","title":"MedVIGIL: Evaluating Trustworthy Medical VLMs Under Broken Visual Evidence","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.14787","title":"Do Composed Image Retrieval Benchmarks Require Multimodal Composition?","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.20525","title":"NeuroQA: A Large-Scale Image-Grounded Benchmark for 3D Brain MRI Understanding","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2606.13441","title":"Why Sampling Is Not Choosing: Intentionality, Agency, and Moral Responsibility in Large Language Models","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2608.00976","title":"Location-Aware Fine-Grained Representation Learning for Medical Vision Foundation Models","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.13210","title":"NARU: A Benchmark for NARrative Evolution and Cultural Nuance Understanding in Japanese Extreme Long Video","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.20069","title":"V-REX: Efficient Specialist VLM Training for Veterinary X-Rays","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2608.26382","title":"VIPER: An Expert-Curated Benchmark for Vision-Language Models in Veterinary Pathology","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.34716","title":"From Pixel Generation to Topological Inference: Structural Dual Super-Resolution for Trustworthy Cross-Physical-Domain Trabecular Morphology Learning","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.06018","title":"Investigating Query-Insensitive Behavior in Spatio-Temporal Video Grounding","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.08365","title":"A Stevens's Power Law Check-up of GPT-5.5's Implicit Reading of Visual Encoding","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}