Official repo for "Spotlight on Token Perception for Multimodal Reinforcement Learning"

A Survey of Reinforcement Learning for Large Reasoning Models

Official implementation for DenseMixer: Improving MoE Post-Training with Precise Router Gradient

FULL v0, Cursor, Manus, Same.dev, Lovable, Devin, Replit Agent, Windsurf Agent, VSCode Agent, Dia Browser & Trae AI (And other Open Sourced) System Prompts, Tools & AI Models.

paper list, tutorial, and nano code snippet for Diffusion Large Language Models.

[ICML 2025] Official Implementation of GLIDER

[ICML2025] Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignment

OpenThinkIMG is an end-to-end open-source framework that empowers LVLMs to think with images.

This is a replicate of DeepSeek-R1-Zero and DeepSeek-R1 training on small models with limited data

Official implementation of the paper "Attentive Eraser: Unleashing Diffusion Model’s Object Removal Potential via Self-Attention Redirection Guidance" (AAAI 2025)

LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training

Official repository for "Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing". Your efficient and high-quality synthetic data generation pipeline!

The author's implementation for the ICML 2024 paper.

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

😎 up-to-date & curated list of awesome Attacks on Large-Vision-Language-Models papers, methods & resources.

ChatTTS is a generative speech model for daily dialogue.

Xwin-LM: Powerful, Stable, and Reproducible LLM Alignment

Implementation of CALM from the paper "LLM Augmented LLMs: Expanding Capabilities through Composition", out of Google Deepmind

ICLR'2024: Knowledge Fusion of Large Language Models

Tools for merging pretrained large language models.

⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training

List of papers on Hallucination in LMM

为ChatGPT/GLM提供实用化交互界面，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm2等本地模型。兼容文心一言, moss, llama2, rwkv, claude2, 通义千问, 书生, 讯飞星火等。