Stars
This repo is the bundled opensource toolkit for book `Navigate through the Factor Zoo: The Science of Factor Investing`.
Kimi-VL: Mixture-of-Experts Vision-Language Model for Multimodal Reasoning, Long-Context Understanding, and Strong Agent Capabilities
🎉 PILOT: A Pre-trained Model-Based Continual Learning Toolbox
Econometrics AI Agent: A specialized LLM-driven agent for automating complex econometric analysis with zero-shot learning, outperforming general AI in expert tasks. 🚀
verl: Volcano Engine Reinforcement Learning for LLMs
Fully open reproduction of DeepSeek-R1
Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on data and models. We are commi…
DeepRetrieval - 🔥 Training Search Agent with Retrieval Outcomes via Reinforcement Learning
FinMTEB: Finance Massive Text Embedding Benchmark
[ACL 2025 Main] Language Model Fine-Tuning on Scaled Survey Data for Predicting Distributions of Public Opinions
MCP 资源精选， MCP指南，Claude MCP，MCP Servers, MCP Clients
AgentSociety: Large-scale Social Simulation to Understand Human Behaviors and Society through LLM-driven Agents
Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning
Pytorch Library for Relational Table Learning with LLMs.
本项目旨在收集开源的表格智能任务数据集（比如表格问答、表格-文本生成等），将原始数据整理为指令微调格式的数据并微调LLM，进而增强LLM对于表格数据的理解，最终构建出专门面向表格智能任务的大型语言模型。
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
A Python library for dynamic classifier and ensemble selection
(AAAI' 20) A Python Toolbox for Machine Learning Model Combination
Official implementation for "TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables" (NeurIPS 2024)
An offical implementation of "TimeKAN: KAN-based Frequency Decomposition Learning Architecture for Long-term Time Series Forecasting" (ICLR 2025)
Q-Star Agent Code: A reinforcement learning-based framework for intelligent agents using Microsoft AutoGen. It leverages Q-Star, a Q-learning variant, for dynamic decision-making. Ideal for develop…
This project is to formalise the iPinYou RTB data into a standard format for further researches.
[AAAI 2022] Seq2Pat: Sequence-to-Pattern Generation Library
[ICLR 2024] Official implementation of "TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting"