Jian Cong

3
Papers
135
Total Citations

Papers (3)

MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix

NeurIPS 2025arXiv
52
citations

Language Model Can Listen While Speaking

AAAI 2025
47
citations

DiTAR: Diffusion Transformer Autoregressive Modeling for Speech Generation

ICML 2025
36
citations