Luodian
❤️ Feeling the AGI/Sincerely love coding/Huge interests in large-scale systems. Prev: Berkeley AI Research/MSR Asia, Redmond/ByteDance Research
Nanyang Technological UniversitySingapore
Pinned Repositories
CVinW_Readings
A collection of papers on the topic of ``Computer Vision in the Wild (CVinW)''
lmms-eval
Accelerating the development of large multimodal models (LMMs) with lmms-eval
LLaVA-NeXT
GenBench
Benchmarking and Analyzing Generative Data for Visual Recognition
Generalizable-Mixture-of-Experts
GMoE could be the next backbone model for many kinds of generalization task.
Learning-Invariant-Representations-and-Risks
Pytorch code release of CVPR 21 Paper: Learning Invariant Representations and Risks
MADAN
Pytorch Code release for our NeurIPS paper "Multi-source Domain Adaptation for Semantic Segmentation"
Mapillary2COCO
Transfer Mapillary Vistas Dataset to Coco format
Otter
🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.
RelateAnything
Relate Anything Model is capable of taking an image as input and utilizing SAM to identify the corresponding mask within the image.
Luodian's Repositories
Luodian/Otter
🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.
Luodian/RelateAnything
Relate Anything Model is capable of taking an image as input and utilizing SAM to identify the corresponding mask within the image.
Luodian/Generalizable-Mixture-of-Experts
GMoE could be the next backbone model for many kinds of generalization task.
Luodian/GenBench
Benchmarking and Analyzing Generative Data for Visual Recognition
Luodian/IIB
Luodian/mmc4
MultimodalC4 is a multimodal extension of c4 that interleaves millions of images with text.
Luodian/Awesome-Anything
General AI methods for Anything: AnyObject, AnyGeneration, AnyModel, AnyTask, AnyX
Luodian/langchain_semantic_search
Luodian/open_flamingo
An open-source framework for training large multimodal models.
Luodian/opencompass
OpenCompass is an LLM evaluation platform, supporting a wide range of models (LLaMA, LLaMa2, ChatGLM2, ChatGPT, Claude, etc) over 50+ datasets.
Luodian/sglang
SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with models faster and more controllable.
Luodian/uncertainty-baselines
High-quality implementations of standard and SOTA methods on a variety of tasks.
Luodian/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
Luodian/zsh_codex
This is a ZSH plugin that enables you to use OpenAI's Codex AI in the command line.
Luodian/3detr
Code & Models for 3DETR - an End-to-end transformer model for 3D object detection
Luodian/awesome-mixture-of-experts
A collection of AWESOME things about mixture-of-experts
Luodian/blog
Luodian/CLIP
Contrastive Language-Image Pretraining
Luodian/codespace
Luodian/commands_history
Luodian/CVinW_Readings
A collection of papers on the topic of ``Computer Vision in the Wild (CVinW)''
Luodian/detectron2
Detectron2 is FAIR's next-generation platform for object detection, segmentation and other visual recognition tasks.
Luodian/GPT-4-LLM
Luodian/LAVIS
LAVIS - A One-stop Library for Language-Vision Intelligence
Luodian/llama_index
LlamaIndex (GPT Index) is a project that provides a central interface to connect your LLM's with external data.
Luodian/luodian.github.io
Luodian/miro
Official PyTorch implementation of MIRO
Luodian/openclip
An open source implementation of CLIP with DeepSpeed
Luodian/OpenPSG
Benchmarking Panoptic Scene Graph Generation (PSG), ECCV'22
Luodian/stablediffusion
High-Resolution Image Synthesis with Latent Diffusion Models