Making Dialogue Grounding Data Rich: A Three-Tier Data Synthesis Framework for Generalized Referring Expression Comprehension Paper • 2512.02791 • Published 7 days ago • 1
Seeing the Forest and the Trees: Query-Aware Tokenizer for Long-Video Multimodal Language Models Paper • 2511.11910 • Published 25 days ago • 35
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 Jun 14 • 53
$μ^2$Tokenizer: Differentiable Multi-Scale Multi-Modal Tokenizer for Radiology Report Generation Paper • 2507.00316 • Published Jun 30 • 15