Xiaojie Jin
- Papers
- 7
Cite
Notes
Only stored in your browser.
7papers
Authored papers
7VideoWorld 2: Learning Transferable Knowledge from Real-world Videos
arXiv 2026
Flash-VStream: Efficient Real-Time Understanding for Long Video Streams
arXiv 2025
IV-Bench: A Benchmark for Image-Grounded Video Perception and Reasoning in Multimodal LLMs
arXiv 2025
ScaleLong: A Multi-Timescale Benchmark for Long Video Understanding
arXiv 2025
Realistic Full-Body Tracking from Sparse Observations via Joint-Level Modeling
ICCV 2023 1
COSA: Concatenated Sample Pretrained Vision-Language Foundation Model
arXiv 2023
Vista-LLaMA: Reliable Video Narrator via Equal Distance to Visual Tokens
arXiv 2023
Affiliations
No known affiliations.
Frequent co-authors
10from 7 papers