We present a comprehensive solution to learn and improve text-to-image models from human
preference feedback. To begin with, we build ImageReward---the first general-purpose text…

People are spending an enormous amount of time on digital devices through graphical user
interfaces (GUIs) eg computer or smartphone screens. Large language models (LLMs) such …

We introduce CogVLM, a powerful open-source visual language foundation model. Different
from the popular shallow alignment method which maps image features into the input space …

We present CogVideoX, a large-scale text-to-video generation model based on diffusion
transformer, which can generate 10-second continuous videos aligned with text prompt, with a …

Objective Robot‐assisted surgery has been promoted worldwide in recent years. The
development of a domestic orthopaedic robot and its clinical application are therefore of great …

… Jiazheng Xu1 … Jiazheng Xu and Xuefeng Wu contributed equally to this work. … Jiazheng
Xu: investigation, visualization, writing – original draft preparation. Xuefeng Wu: investigation, …

We investigate the generalization boundaries of current Multimodal Large Language Models
(MLLMs) via comprehensive evaluation under out-of-distribution scenarios and domain-…

We present a general strategy to aligning visual generation models -- both image and video
generation -- with human preference. To start with, we build VisionReward -- a fine-grained …

Native arbuscular mycorrhizal fungi (AMF) generally provide more effective assistance for
phytoremediation to remove heavy metal (HM) from polluted soils than non-native AMF. …

Succinate dehydrogenase (SDH) is one of the most important molecular targets for the
development of new fungicides. Carboxamide fungicides are a class of SDH inhibitors widely …