基本信息
浏览量:2
职业迁徙
个人简介
My research aim to build up unified AI system capable of simultaneously processing information from multiple modalities and addressing various downstream tasks. With this goal, I have explored following topics:
alignment, debiasing and uncertainty calibration: alignment for large language models (LLMs) and diffusion models, RLAIF, LLMs uncertainty confidence calibration.
language-based multi-modal intelligence: multi-modal learning (acoustic, vision, language and point clouds modalities, etc.), multi-modal retrieval and summarization, downstream adaption (zero-shot learning, parameter-efficient fine-tuning), superalignment, confidence calibration methods and LLM hallucination.
visual representation learning: unified vision model for diverse tasks (object detection, segmentation and reconstruction, etc.)
alignment, debiasing and uncertainty calibration: alignment for large language models (LLMs) and diffusion models, RLAIF, LLMs uncertainty confidence calibration.
language-based multi-modal intelligence: multi-modal learning (acoustic, vision, language and point clouds modalities, etc.), multi-modal retrieval and summarization, downstream adaption (zero-shot learning, parameter-efficient fine-tuning), superalignment, confidence calibration methods and LLM hallucination.
visual representation learning: unified vision model for diverse tasks (object detection, segmentation and reconstruction, etc.)
研究兴趣
论文共 4 篇作者统计合作学者相似作者
按年份排序按引用量排序主题筛选期刊级别筛选合作者筛选合作机构筛选
时间
引用量
主题
期刊级别
合作者
合作机构
INFORMATION SCIENCES (2024): 119888-119888
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)pp.1-5, (2023)
引用0浏览0EIWOS引用
0
0
作者统计
合作学者
合作机构
D-Core
- 合作者
- 学生
- 导师
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn