#大语言模型#LLaVA是一个具有 GPT-4V 级别功能的大语言和视觉模型助手
#自然语言处理#Unilm是一个跨任务、语言和模式的大规模自监督预训练模型
#大语言模型#Janus-Series: Unified Multimodal Understanding and Generation Models
#计算机科学#YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open
DeepSeek-VL: Towards Real-World Vision-Language Understanding
#大语言模型#Code and models for NExT-GPT: Any-to-Any Multimodal Large Language Model
#大语言模型#🦦 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.
#大语言模型#[CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.
#大语言模型#SuperCLUE: 中文通用大模型综合性基准 | A Benchmark for Foundation Models in Chinese
#大语言模型#Chronos: Pretrained Models for Probabilistic Time Series Forecasting
#计算机科学#⚡ TabPFN: Foundation Model for Tabular Data ⚡
EVA Series: Visual Representation Fantasies from BAAI
#计算机科学#Images to inference with no labeling (use foundation models to train supervised models).
#Awesome#Awesome things about LLM-powered agents. Papers / Repos / Blogs / ...
Prompt Learning for Vision-Language Models (IJCV'22, CVPR'22)
[ECCV2024] Video Foundation Models & Data for Multimodal Understanding
Emu Series: Generative Multimodal Models from BAAI
#自然语言处理#An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.
#时序数据库#Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting