AV-Reasoner: Improving and Benchmarking Clue-Grounded Audio-Visual Counting for MLLMs May 5, 2026· Lidong Lu , Guo Chen , Zhu Wei , Zhiqi Li , Yicheng Liu Tong Lu · 0 min read Cite URL Type Conference paper Publication Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Last updated on May 5, 2026 Authors Tong Lu Nanjing University ← Understanding New-Knowledge-Induced Factual Hallucinations in LLMs: Analysis and Interpretation May 8, 2026 Bayesian Decomposition and Semantic Completion for Few-shot Semantic Segmentation May 5, 2026 →
