[NIPS 2025 DB Oral] Official Repository of paper: Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing

Official implementation for "TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables" (NeurIPS 2024)

A Library for Advanced Deep Time Series Models for General Time Series Analysis.

Python 3 support for the MS COCO caption evaluation tools

Zhejiang University Graduation Thesis LaTeX Template

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

Official implementation of paper "GoViG: Goal-Conditioned Visual Navigation Instruction Generation"

Official implementation of the paper: "StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling"

Frontier Multimodal Foundation Models for Image and Video Understanding

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

本项目设计了一个基于 RAG 与大模型技术的医疗问答系统，利用 DiseaseKG 数据集与 Neo4j 构 建知识图谱，结合 BERT 的命名实体识别和 34b 大模型的意图识别，通过精确的知识检索和问答生成， 提升系统在医疗咨询中的性能，解决大模型在医疗领域应用的可靠性问题。

[NAACL 2025 Main] DTELS: Towards Dynamic Granularity of Timeline Summarization

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and cont…

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

DropMicroFluidAgents (DMFAs): Autonomous Droplet Microfluidic Research Framework Through Large Language Model Agents

多智能体强化学习

复现大模型相关算法及一些学习记录

Fully open reproduction of DeepSeek-R1

R1-searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning

PromptCBLUE: a large-scale instruction-tuning dataset for multi-task and few-shot learning in the medical domain in Chinese

This project contains derivation of Single Stance and foot-strike leg dynamic equations. Finally, 2D simulation of Biped Robot in MATLAB.

RAG兴趣小组，全手写的一个RAG应用。Langchain的大部分库会很方便，但是你不一定理解其中原理，所以代码尽可能展现基本算法，主打理解RAG的原理

🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!

【三年面试五年模拟】AIGC算法工程师面试秘籍。涵盖AIGC、传统深度学习、自动驾驶、AI Agent、机器学习、计算机视觉、自然语言处理、强化学习、大数据挖掘、具身智能、元宇宙、AGI等AI行业面试笔试干货经验与核心知识。

LLM-A*: Large Language Model Enhanced Incremental Heuristic Search on Path Planning