FaceCat-Kronos是由 花卷猫量化研究团队 打造的一款金融量化工具。本项目基于清华大学最新开源的K线预测模型 Kronos，融合了前沿的人工智能技术，旨在为金融市场提供科学的分析与预测能力。 本工具能够对股票历史数据进行深度预训练，实现精准的做市商K线规划，并对未来市场走势进行科学推演，适用于量化研究、策略研发、交易决策支持、投研汇报、教学演示、二次开发。无论是基金、私募、荐股机构…

Kronos: A Foundation Model for the Language of Financial Markets

"DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)"

Sample application to demonstrate Google ADK and A2A interoperability. For informational purposes only.

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Transformer: PyTorch Implementation of "Attention Is All You Need"

Time-R1: Framework and resources for endowing LLMs with comprehensive temporal reasoning (understanding, prediction, creative generation) using a novel three-stage RL curriculum. Includes the Time-…

Time-R1 is a two-stage reinforcement fine-tuning framework that trains large language models to perform slow-thinking, step-by-step reasoning for accurate and explainable time series forecasting.

TradingAgents: Multi-Agents LLM Financial Trading Framework

《动手学大模型Dive into LLMs》系列编程实践教程

Implementation of "AlphaQCM: Alpha Discovery in Finance with Distributional Reinforcement Learning"

This repository contains code and notebooks for a project focused on cryptocurrency price prediction. The project aims to explore and compare different machine learning approaches, including graph …

The code Implementation of the paper “KAA: Kolmogorov-Arnold Attention for Enhancing Attentive Graph Neural Networks".

The sample codes for our ICLR18 paper "FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling""

Bayesian Neural Network in PyTorch

Using a GNN to predict future extreme weather events

A python package for reconstructing causal connection using Gaussian Causal Network

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Easily build AI systems with Evals, RAG, Agents, fine-tuning, synthetic data, and more.

Framework for autonomous learning of explainable graph neural networks

Code for IoTJ 2024 paper "SageFormer: Series-Aware Framework for Long-Term Multivariate Time-Series Forecasting".

The code for FilterTS: Comprehensive Frequency Filtering for Multivariate Time Series Forecasting

The development and future prospects of large multimodal reasoning models.

Code and datasets for paper "Spatiotemporal convolutional network for time-series prediction with causal-factor inference"