Scholar
Kailin Jiang (蒋凯林)
Google Scholar ID: NSHQsrAAAAAJ
BIGAI & USTC
Citations & Impact
Citations
262
H-index
6
i10-index
4
Publications
13
Co-authors
9
list available
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- Published Papers:
- - MMKE-Bench: A Multimodal Editing Benchmark for Diverse Visual Knowledge (ICLR 2025 & ICLR 2025 Workshop SSI-FM)
- - In-Context Editing: Learning Knowledge from Self-Induced Distributions (ICLR 2025)
- Preprints:
- - KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Augmentations and Constraints
- - Can Visual Input Be Compressed? A Visual Token Compression Benchmark for Large Multimodal Models
- - Benchmarking Multimodal Knowledge Conflict for Large Multimodal Models
- - MINED: Probing and Updating with Multimodal Time-Sensitive Knowledge for Large Multimodal Models
- - When Large Multimodal Models Confront Evolving Knowledge: Challenges and Pathways
- Invention Patents:
- - A multimodal evolving knowledge injection method and system
Research Experience
- Internship at the State Key Laboratory of General Artificial Intelligence; Reviewer for ICLR 2025 and ICLR 2026.
Education
- PhD student, jointly supervised by BIGAI and USTC, supervisors are Qing Li (BIGAI), Yuntao Du (SDU), Siyuan Qi (Gyges Labs), Bin Li, and Lei Liu (USTC). Completed undergraduate studies from the College of Science of Sichuan Agricultural University in June 2024.
Background
- Research Interests: knowledge editing, knowledge injection, multimodal learning, continual learning. Currently doing an internship at the State Key Laboratory of General Artificial Intelligence.
Miscellany
- Personal interests not provided
