aod321
Zi Yin(YinZi), PhD Student, Tsinghua University. Current Research RL, Emboided AI, LLM Agent
Tsinghua UniversityBeijing
Pinned Repositories
AgentEnvCoEvolution
Camera-Tracking
Our project is the system that enables a moving camera to track a moving object in real time. We plan on doing this by having a camera mounted to a swivel using two servo motors to allow for the camera’s direction to be controlled. The camera data will be read into the FPGA board and some basic object recognition algorithm will be used to identify an some object and determine if the camera needs to be moved to keep the object in the field of vision. In addition to the auto tracking mode, we plan on having an IR remote to allow for manual panning, mode selection, and power on and off. If there is additional time we would like to also interface the FPGA to a Raspberry Pi board running a linux web server to allow for email alerts (when object moves) and web based control.
Face-parsing-via-tanh-warping
PyTorch implementations of "Face Parsing via tanh-warping"
icnn-face
Face parsing via Interlinked Convolutional Neural Network(Pytorch reimplement)
jspsych_builder_demo
Kanizsa_illusion
A Python library for simply generating Kanizsa illusion graphics (triangles and rectangles) for Cognitive Psychology Research.
map_human_sorting_jspsych
a behavior exp program base on Jspsych(TypeScript)
ML16SDK_AutoBuild
An SDK for 16-beam LIDAR(Support ARM Cross Compile)
OpenWrt-RM2100
STN-iCNN
End-to-End Face Parsing via Interlinked Convolutional Neural Networks
aod321's Repositories
aod321/Face-parsing-via-tanh-warping
PyTorch implementations of "Face Parsing via tanh-warping"
aod321/jspsych_builder_demo
aod321/map_human_sorting_jspsych
a behavior exp program base on Jspsych(TypeScript)
aod321/Auto-GPT
An experimental open-source attempt to make GPT-4 fully autonomous.
aod321/autocut
用文本编辑器剪视频
aod321/chatgpt_bot
aod321/ChatGPT_wechat
ChatGPT-WechatApp
aod321/cobot_s_sim
aod321/create_embeeding_grid_map
aod321/diffusion_policy_3dpusht
Fork of [RSS 2023] Diffusion Policy Visuomotor Policy Learning via Action Diffusion, Modified for Training 3D PushT Task in Maniskill
aod321/docker-whisperX
Dockerfile for WhisperX: Automatic Speech Recognition with Word-Level Timestamps and Speaker Diarization (Dockerfile, CI image build and test)
aod321/egoego_release
Official Implementation of the Paper: Ego-Body Pose Estimation via Ego-Head Pose Estimation (CVPR 2023)
aod321/fast-wfc
An implementation of Wave Function Collapse with a focus on performance.
aod321/fastapi-gridgame
gridgame backend
aod321/GRPCServer
a implementation of dm_env_rpc Unity3D server for agent-world co-evolution
aod321/happy_walker
aod321/human_emotion_rate
aod321/isaac_coevo_fastwfc
aod321/JinyunBackend
aod321/L3MVN
Leveraging Large Language Models for Visual Target Navigation
aod321/llama2.c
Inference Llama 2 in one file of pure C
aod321/ManiSkill
SAPIEN Manipulation Skill Framework, a GPU parallelized robotics simulator and benchmark
aod321/nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
aod321/OpenImuCameraCalibrator
Camera calibration tool
aod321/pusht_3dsim
aod321/pybind11_fastwfc
aod321/pynecone
Web apps in pure Python.
aod321/visualnav-transformer
Official code and checkpoint release for "ViNT: A Foundation Model for Visual Navigation".
aod321/wfc_unity2
aod321/xland_fastwfc