Taian Guo

large language models

large vison-language models

reinforcement learning

llm agent

retrieval-augmented generation

complex instruction following

multi-label classification

label relevance ranking

reinforcement learning

open-vocabulary

zero-shot learning

multi-modal

vision language pre-training

large language models

object detection

semantic segmentation

deep learning

computer vision

CNNs

video super-resolution

image de-raining