🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.
- alignment
- dpo
- llm
- llm-aligment
132,241 visible repositories in the index
121–144 of 145 · Most stars
🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.
This is the official github repo of Think-on-Graph (ICLR 2024). If you are interested in our work or willing to join our research team in Shenzhen, please feel free to contact us by email ([email protected])
Open-source, self-hosted alternative to NotebookLM. Chat with your documents, generate audio summaries, and ground AI in your own sources—built with Supabase and N8N on a React frontend.
A curated collection of research papers exploring the utilization of LLMs for graph-related tasks.
A Hub/research area, for jailbreaking LLM's, and breaking their safety filters.
xLAM: A Family of Large Action Models to Empower AI Agent Systems
本教程将全面指导你如何快速搭建自己的AI应用环境,从Docker桌面版的安装与配置开始,到本地部署Dify并自定义AI助手功能,让你轻松实现“猜病例”、“甜蜜哄人”、“新生入学指南”、“小红书读书卡片”与“面试宝典”等多种特色AI应用。并教会你从基础智能体到使用工作流,再到知识库、DeepResearch、数据库、MCP、复杂任务编排等高阶任务,由浅到深的学习掌握基于dify的大模型应用开发。
Best static AI text humanizer. Two research-grounded LLM-agnostic skills that make AI writing sound human and relatable. Nine levers, 50+ peer-reviewed sources, 2024-2026 detection literature.
Measuring how well CLI agents like Claude Code or Codex CLI can post-train base LLMs on a single H100 GPU in 10 hours
:sunrise: A comprehensive, cutting-edge open-source framework for next-generation Transformers/LLM, with compute-matched benchmarking and a platform for autonomous architecture research.
An agent that compiles git maintenance chores into reusable programs, then decides whether to replay them by running checks rather than by guessing the task looks familiar
AI jailbreaks: 35 paste-ready AI jailbreak prompts for 25+ frontier and open-weight models - system prompts, AGENTS.md specs, and Ollama Modelfiles. Built for AI security research and red-team testing.
Dyno Lab — an AI safety, alignment and interpretability research workbench for Apple Silicon. Explore activations, probes, SAEs and interventions with local inference, a Python SDK, APIs and MCP.
A Unified Framework for Efficient RSI Research
A team of Hermes agents you chat with, each with its own screen on one Orgo computer. Composio apps, xAI voice and X research.
CaseCite is an open-source, self-hosted legal RAG caselaw research & document analysis platform.
Translateddsh jailbreak - DeepSeek Assistant jailbreak plugin (DSH jailbreak / jailbreak / jailbreak prompts): request boundary injection, so the model no longer starts with "I can't" right away. Combined ASR across 20 categories 45.0%, coverage 19/20, benign capability Δ=0.0pt (24/24 graded); 0 host patches, off by default, off passes through verbatim, every rewrite is recorded in a manifest and promptSha256 for auditing. Former name dsh-jalibreak
How many bugs can LMs find & fix in large codebases?
TranslatedAcademic research library for DSH — search, cite, approve imports, hand off notes. Also: a research literature library plugin for DeepSeek Harness: search papers, include sources, approve imports into the library, and hand off note leads to other plugins in the same session.
This is the official repo for paper InteractiveWorld A Verifiable Human-Centric Environment for Building Better Interactive MLLM Assistants
A Long-Horizon Benchmark for Self-Improving Inference Systems
Research experiments exploring uncommon quant techniques.
Deterministic quality scorer for AI agent instruction files — 8-dimension scoring with security, multi-format (SKILL.md, CLAUDE.md, .cursorrules, AGENTS.md), anti-gaming detection, zero dependencies
AI-Driven Full-Text Screening and Data Extraction for Systematic Reviews and Evidence Synthesis