Lists (2)
Starred repositories
🎓从0开始训练一个大模型Minimind项目的超详细解析，包括但不限于用到的架构，算法，以及大模型面试经验
Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.
Qwen-AgentWorld: Language World Models for General Agents
[ACL 2026 Oral] From Word to World: Can Large Language Models be Implicit Text-based World Models?
LeetCode Hot 100 自用刷题辅助：纯本地静态网页，核心代码/ACM 双模式判题（Python + JavaScript）、错题复习、知识补充、按难度折叠分组、OpenAI 兼容 AI 助手（悬浮窗，支持本地 CORS 代理）。零依赖零构建，一键启动。
macOS Adobe apps download & installer
[NeurIPS 2025 Spotlight] StreamForest: Efficient Online Video Understanding with Persistent Event Memory
The official repository for paper "FlexSelect: Flexible Token Selection for Efficient Long Video Understanding".
**Deep Video Discovery (DVD)** is a deep-research style question answering agent designed for understanding extra-long videos.
⏰ Agenticly track worldwide conference deadlines (Website, Python Cli, Wechat Applet)
OmniVideo-100K: A Dataset for Audio-Visual Reasoning through Structured Scripts and Evidence Chains
MathScale 🚀 - A development framework for generating and solving math problems using large language models (LLMs). 📚✏️ It processes the MATH seed dataset, constructs knowledge graphs, and leverages…
[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
This is the official code repository for the paper: Towards General Continuous Memory for Vision-Language Models.
One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks
A collection of AI Agents papers (Updated biweekly)
Generate editable PPT decks from paper PDFs or LaTeX sources
💻 A curated list of papers and resources for multi-modal Graphical User Interface (GUI) agents.
Awesome GUI Agent Paper List
A hand-picked collection of the finest of resources for the most awesome of agents, Claude Code, the undisputed champion of coding companions, from the unstoppable team at Anthropic PBC. A delectab…
We propose a pioneering benchmark to evaluate LLM agents' ability to improve over time in streaming scenarios