ABadCandy
Follow
Starred repositories
微舆：人人可用的多Agent舆情分析助手，打破信息茧房，还原舆情原貌，预测未来走向，辅助决策！从0实现，不依赖任何框架。
Repo for "Adaptation of Agentic AI"
Skywork-R1V is an advanced multimodal AI model series developed by Skywork AI, specializing in vision-language reasoning.
Kimi K2 is the large language model series developed by Moonshot AI team
[NeurIPS 2025🔥]Main source code of SRPO framework.
OpenAgents - AI Agent Networks for Open Collaboration
Build resilient language agents as graphs.
Tongyi Deep Research, the Leading Open-source Deep Research Agent
A set of LangChain Tutorials from my youtube channel
[ICLR 2026] End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning
A reading list on LLM based Synthetic Data Generation 🔥
Official Code for "Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search"
Trae Agent is an LLM-based agent for general purpose software engineering tasks.
Seed1.5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning, achieving state-of-the-art performance on 38 out of 60 public benchmarks.
GLM-4.6V/4.5V/4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
A paper list of some recent works about Token Compress for Vit and VLM
A paper list about Token Merge, Reduce, Resample, Drop for MLLMs.
84
Updated Oct 26, 2025
[TMLR 25] SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models
Automatically crawl arXiv papers daily and summarize them using AI. Illustrating them using GitHub Pages.
The Entropy Mechanism of Reinforcement Learning for Large Language Model Reasoning.
A visuailzation tool to make deep understaning and easier debugging for RLHF training.