Jinhe Bi
- Papers
- 5
Cite
Notes
Only stored in your browser.
5papers
Authored papers
5Can Visual Input Be Compressed? A Visual Token Compression Benchmark for Large Multimodal Models
arXiv 2025
KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Augmentations and Constraints
arXiv 2025
Loong: Synthesize Long Chain-of-Thoughts at Scale through Verifiers
arXiv 2025
Reinforcement Mid-Training
arXiv 2025
Backdoor Cleaning without External Guidance in MLLM Fine-tuning
arXiv 2025
Affiliations
No known affiliations.
Frequent co-authors
10from 5 papers