Enxin Song

According to our database1, Enxin Song authored at least 8 papers between 2023 and 2025.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2025
AuroraLong: Bringing RNNs Back to Efficient Open-Ended Video Understanding.
CoRR, July, 2025

Video-MMLU: A Massive Multi-Discipline Lecture Understanding Benchmark.
CoRR, April, 2025

AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024
MovieChat+: Question-aware Sparse Memory for Long Video Question Answering.
CoRR, 2024

MovieChat: From Dense Token to Sparse Memory for Long Video Understanding.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

2023
Devil in the Number: Towards Robust Multi-modality Data Filter.
CoRR, 2023

MovieChat: From Dense Token to Sparse Memory for Long Video Understanding.
CoRR, 2023


  Loading...