yinpeidai Goto Github PK

act-plus-plus

Imitation learning algorithms with Co-training for Mobile ALOHA: ACT, Diffusion Policy, VINN

algorithm_interview_notes-chinese

2018/2019/校招/春招/秋招/算法/机器学习(Machine Learning)/深度学习(Deep Learning)/自然语言处理(NLP)/C/C++/Python/面试笔记

bert-bilstm-crf-pytorch

使用谷歌预训练bert做字嵌入的BiLSTM-CRF序列标注模型

bert-use-demo

the demo for bert

depth-anything

Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data

foolnotes

useful notes for programming skills

grounded-segment-anything

Marrying Grounding DINO with Segment Anything & Stable Diffusion & Tag2Text & BLIP & Whisper & ChatBot - Automatically Detect , Segment and Generate Anything with Image, Text, and Audio Inputs

habitat-lab

A modular high-level library to train embodied AI agents across a variety of tasks and environments.

home-robot

Mobile manipulation research tools for roboticists

iqiyiproject

Iqiyi movie dialog system

jiant

The jiant toolkit for general-purpose text understanding models

llava

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

llava-next

lseg-module

Adapted from Habitat home-robot code base

minicpm-v

MiniCPM-Llama3-V 2.5: A GPT-4V Level Multimodal LLM on Your Phone

mmcoref

Code for DSTC 10: SIMMC 2.0 track: Multimodal Coreference Resolution subtask.

multiwoz

Source code for end-to-end dialogue model from the MultiWOZ paper (Budzianowski et al. 2018, EMNLP)

naum

Code for NAUM project paper

nerf-navigation

Code for the Nerf Navigation Paper. Implements a trajectory optimiser and state estimator which use NeRFs as an environment representation

neural-episodic-control

Implementation of Deepmind's Neural Episodic Control

olmo

Modeling, training, eval, and inference code for OLMo

open-llava-next

An open-source implementation of LLaVA-NeXT.

orb_slam2

Real-Time SLAM for Monocular, Stereo and RGB-D Cameras, with Loop Detection and Relocalization Capabilities

orb_slam3

ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM

orion

Orion-14B is a family of models includes a 14B foundation LLM, and a series of models: a chat model, a long context model, a quantized model, a RAG fine-tuned model, and an Agent fine-tuned model. Orion-14B 系列模型包括一个具有140亿参数的多语言基座大模型以及一系列相关的衍生模型，包括对话模型，长文本模型，量化模型，RAG微调模型，Agent微调模型等。

peract

Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation

peract_colab

Annotated Tutorial for PerAct

pirlnav

Code for training embodied agents using IL and RL finetuning at scale for ObjectNav

pytorch-nec

PyTorch Implementation of Neural Episodic Control (NEC)

rlbench

A large-scale benchmark and learning environment.