Stars
微舆：人人可用的多Agent舆情分析助手，打破信息茧房，还原舆情原貌，预测未来走向，辅助决策！从0实现，不依赖任何框架。
This is a repo with links to everything you'd ever want to learn about data engineering
DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
Examining how large language models (LLMs) perform across various synthetic regression tasks when given (input, output) examples in their context, without any parameter update
A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3, Qwen3-MoE, DeepSeek-R1, GLM4.5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Llava, …
Code for the paper "Deep Entity Matching with Pre-trained Language Models"
[NeurIPS 2024] OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI
This repository contains code and extensive prompt examples to reproduce and extend the experiments in our papers "Using ChatGPT for Entity Matching" and "Entity Matching using Large Language Models".
Awesome Pretrained Chinese NLP Models，高质量中文预训练模型&大模型&多模态模型&大语言模型集合
Pre-Training with Whole Word Masking for Chinese BERT（中文BERT-wwm系列模型）
A Survey on Text-to-Video Generation/Synthesis.
Mora: More like Sora for Generalist Video Generation
Open-Sora: Democratizing Efficient Video Production for All
Emote Portrait Alive: Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions
[CVPR 2024] EditGuard: Versatile Image Watermarking for Tamper Localization and Copyright Protection
Set of tools to assess and improve LLM security.
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）
[ECCV2024] VideoMamba: State Space Model for Efficient Video Understanding
Paper list about multimodal and large language models, only used to record papers I read in the daily arxiv for personal needs.
Large World Model -- Modeling Text and Video with Millions Context
MiniCPM4 & MiniCPM4.1: Ultra-Efficient LLMs on End Devices, achieving 3+ generation speedup on reasoning tasks
InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥