[ICML 2026 AIWILD] Official implementation of TurnGate, "One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue".

Forge wonderful chat messages in typst

code for paper Query-Dependent Prompt Evaluation and Optimization with Offline Inverse Reinforcement Learning

Spirit-v1.5: A Robotic Foundation Model by Spirit AI

Protein stability prediction using rewired protein generative models

A scriptable Dropbox CLI for files, shared links, teams, and automation workflows

Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"

Fully automatic censorship removal for language models

Removing safety / refusal behaviour from GPT-OSS.

Training Proactive and Personalized LLM Agents

Official Repository for "Glyph: Scaling Context Windows via Visual-Text Compression"

🚀 大语言模型高效转发服务 · An efficient forwarding service designed for LLMs. · OpenAI API Reverse Proxy

Implements harmful/harmless refusal removal using pure HF Transformers

Learn to resolve ambiguity for Question Answering through RL

Scaling Agentic Reinforcement Learning with a Multi-Turn, Multi-Task Framework

🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN

A cross-platform manga app made for e-hentai & exhentai by Flutter

Repo housing the open sourced code for the ai2 scholar qa app and also the corresponding library

[ICLR26] EAPrivacy - Measuring Physical-World Privacy Awareness of Large Language Models: An Evaluation Benchmark

EAPrivacy - Measuring Physical-World Privacy Awareness of Large Language Models: An Evaluation Benchmark

🔍 网易云音乐 Node.js API Services (Half Refactor & Enhanced) 全网最全的网易云音乐API接口

frozen-in-time version of our Paper Finder agent for reproducing evaluation results

💖🧸 Self hosted, you-owned Grok Companion, a container of souls of waifu, cyber livings to bring them into our worlds, wishing to achieve Neuro-sama's altitude. Capable of realtime voice chat, Minec…

interactive & hardware agnostic SDK for lab automation

[ACL 2026] LLM-Based Human-Agent Collaboration and Interaction Systems: A Survey | Awesome Human-Agent Collaboration | Human-AI Collaboration

Unofficial Python API for character.ai

众多优秀广告规则的上游、开源社区中最棒的广告过滤器之一。适配AdGuard/Home/DNS、AdAway、hosts、Mosdns、ClashMeta、QuantumultX等主流广告拦截工具/代理工具。