Ximeng Sun

3
Papers
94
Total Citations

Papers (3)

Koala: Key Frame-Conditioned Long Video-LLM

CVPR 2024arXiv
62
citations

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer

CVPR 2025
32
citations

Unleashing Hour-Scale Video Training for Long Video-Language Understanding

NeurIPS 2025arXiv
0
citations