a hidden state is worth a thousand words.
Hi! I am Bokai Xu, I received my bachelor degree at The Chinese University of Hong Kong, Shenzhen. Currently I am working as an engineer at ModelBest.
My passion is understanding the connection between deep neural networks and biological brain, and the training dynamics in deep neural networks.
About my current research:
At THUNLP@THU aka ModelBest Inc (Jun 2022 - ), I worked on various topics with large language models.
-
contributed to language model alignment UltraChat: Enhancing Chat Language Models by Scaling High-quality Instructional Conversations, the dataset were widely used by community, including Falcon, Zephyr and others.
-
contributed to Tool Learning with Foundation Models & BMTools for LLM to use tools, we thoroughly investigated the LLM’s ability to sequentially use tools for completing various tasks.
-
contributed to MiniCPM-V-2.6, in OCR capability and multi-image understanding capability.
-
contributed to multimodal information retrieval VisRAG & VisRAG-Ret, in training and evaluation of VLM-based dense retrieval models, training data synthesis, and data filtering. VisRAG enables VLM to read and comprehend with vision and retrieve multimodal information, in a way like human.
-
contributed to MiniCPM-Embedding in training and evaluation infrastructure of dense retrieval models.
At ICBI@SIAT (Apr 2023 - ), I worked on brain reconstruction infrastructures. I work closely with Dr.Chaoyu Yang and Prof.Pengcheng Zhou.
- led foundation model pretraining Masked Autoencoders with large-scale microscopic images then aligned pretrained model for trustful brain reconstruction task: Brain Reconstruction by Self Supervised Semantic Stitching of Non-overlapping 3D Microscopic Image .