https://avocado-captioner.github.io/

Ming-UniAudio: Speech LLM for Joint Understanding, Generation and Editing with Unified Representation

Tongyi Deep Research, the Leading Open-source Deep Research Agent

🥢像老乡鸡🐔那样做饭。主要部分于2024年完工，非老乡鸡官方仓库。文字来自《老乡鸡菜品溯源报告》，并做归纳、编辑与整理。CookLikeHOC.

Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.

A benchmark for LLMs on complicated tasks in the terminal

MindVL: Towards Efficient and Effective Training of Multimodal Large Language Models on Ascend NPUs

A simple, elegant, and fast workflow to write resumes and CVs in Markdown.

A Fully Self-Hosted Solution for Full-Duplex Voice Interaction

Repo-level benchmark for real-world Code Agents: from repo understanding → env setup → incremental dev/bug-fixing → task delivery, with cost-aware α metric.

[ICCV 2025] Explore the Limits of Omni-modal Pretraining at Scale

🤗 R1-AQA Model: mispeech/r1-aqa

ICML 2025 Papers: Dive into cutting-edge research from the premier machine learning conference. Stay current with breakthroughs in deep learning, generative AI, optimization, reinforcement learning…

诺亚盘古大模型研发背后的真正的心酸与黑暗的故事。

🛠Awesome Tools，程序员常用高效实用工具、软件资源精选，办公效率提升利器（A Curated Collection of High-Efficiency and Practical Tools and Software Resources for Programmers to Boost Office Productivity）。

主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题

Latest Advances on System-2 Reasoning

MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources

The first Large Audio Language Model that enables native in-depth thinking, which is trained on large-scale audio Chain-of-Thought data.

Visual R1: Trasfer Reasoning Ability from R1 to Visual R1

Latest Advances on Reasoning of Multimodal Large Language Models (Multimodal R1 \ Visual R1) ) 🍓