Xiaoxing Hu
- Papers
- 5
Cite
Notes
Only stored in your browser.
5papers
Authored papers
5Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding
arXiv 2026
Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models
arXiv 2026
Decoupled Global-Local Alignment for Improving Compositional Understanding
arXiv 2025
ProCLIP: Progressive Vision-Language Alignment via LLM-based Embedder
arXiv 2025
Earth-Adapter: Bridge the Geospatial Domain Gaps with Mixture of Frequency Adaptation
arXiv 2025
Affiliations
No known affiliations.
Frequent co-authors
10from 5 papers