Scholar
Zejun Ma
Google Scholar ID: XwY9LXoAAAAJ
Bytedance
machine learning
deep learning
multimodal
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
3,721
H-index
29
i10-index
57
Publications
20
Co-authors
0
Publications
16 items
video-SALMONN-R$^3$: Learning to ReWatch, ReAsk, and ReAnswer for Efficient Video Understanding
2026
Cited
0
video-SALMONN S: Streaming Audio-Visual LLMs Beyond Length Limits via Memory
2025
Cited
0
SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning
2025
Cited
0
SWE-Perf: Can Language Models Optimize Code Performance on Real-World Repositories?
2025
Cited
0
First Return, Entropy-Eliciting Explore
2025
Cited
0
ZeCO: Zero Communication Overhead Sequence Parallelism for Linear Attention
2025
Cited
0
MMSearch-R1: Incentivizing LMMs to Search
2025
Cited
0
video-SALMONN 2: Captioning-Enhanced Audio-Visual Large Language Models
2025
Cited
0
Load more
