Pinned Repositories
baseline_AppAgent
AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.
BulletArm
BulletArm is a benchmark and learning-environment for robotic manipulation.
clip_search
database_utils
galera_data_generation
mobile_game_compatibility_study
open_flamingo
An open-source framework for training large multimodal models.
themis_rr
txtParser
52书库小说txt下载的爬虫一只
videoFrame
zihesong's Repositories
zihesong/videoFrame
zihesong/baseline_AppAgent
AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.
zihesong/BulletArm
BulletArm is a benchmark and learning-environment for robotic manipulation.
zihesong/clip_search
zihesong/database_utils
zihesong/galera_data_generation
zihesong/mobile_game_compatibility_study
zihesong/open_flamingo
An open-source framework for training large multimodal models.
zihesong/themis_rr
zihesong/txtParser
52书库小说txt下载的爬虫一只
zihesong/ui_access
zihesong/ui_access_scripts
zihesong/zihesong.github.io
Resume