Updated 9 months ago

https://github.com/cliangyu/eye_see_you • Science 13%

A face recognition security system

Updated 9 months ago

https://github.com/cliangyu/teebeecee • Science 13%

A repo of pattern recognition data analytics by Team TeeBeeCee.

Updated 9 months ago

https://github.com/cliangyu/llava • Science 10%

Visual Instruction Tuning: Large Language-and-Vision Assistant built towards multimodal GPT-4 level capabilities.

Updated 9 months ago

https://github.com/cliangyu/open_flamingo • Science 23%

An open-source framework for training large multimodal models.

Updated 9 months ago

https://github.com/cliangyu/megatron-deepspeed • Science 10%

Ongoing research training transformer language models at scale, including: BERT & GPT-2

Updated 9 months ago

https://github.com/cliangyu/emu • Science 10%

Emu: An Open Multimodal Generalist

Updated 9 months ago

https://github.com/cliangyu/llmspeculativesampling • Science 10%

Fast inference from large lauguage models via speculative decoding

Updated 9 months ago

https://github.com/cliangyu/slowfast • Science 10%

PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

Updated 9 months ago

https://github.com/cliangyu/qlib • Science 10%

Qlib is an AI-oriented quantitative investment platform, which aims to realize the potential, empower the research, and create the value of AI technologies in quantitative investment. With Qlib, you can easily try your ideas to create better Quant investment strategies. An increasing number of SOTA Quant research works/papers are released in Qlib.

Updated 9 months ago

https://github.com/cliangyu/openpsg • Science 10%

Benchmarking Panoptic Scene Graph Generation (PSG), ECCV'22

Updated 9 months ago

https://github.com/cliangyu/ofa • Science 10%

Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework

Updated 9 months ago

https://github.com/cliangyu/mmaction2 • Science 10%

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark