MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix Paper • 2505.13032 • Published May 19 • 2
CMI-Bench: A Comprehensive Benchmark for Evaluating Music Instruction Following Paper • 2506.12285 • Published 24 days ago • 54
$μ^2$Tokenizer: Differentiable Multi-Scale Multi-Modal Tokenizer for Radiology Report Generation Paper • 2507.00316 • Published 7 days ago • 15