Yiran Zhong

7

Papers

38

Total Citations

Papers (7)

CO2: Efficient Distributed Training with Full Communication-Computation Overlap

Exploring Transformer Extrapolation

Tri-Ergon: Fine-Grained Video-to-Audio Generation with Multi-Modal Conditions and LUFS Control

Various Lengths, Constant Speed: Efficient Language Modeling with Lightning Attention

Improving Audio-Visual Segmentation with Bidirectional Generation

Deep Non-Rigid Structure-from-Motion Revisited: Canonicalization and Sequence Modeling

Towards Open-Vocabulary Audio-Visual Event Localization