Stars
📨 The ultimate agentic social media scheduling tool 🤖
Bringing BERT into modernity via both architecture changes and scaling
A plugin for Apple Mail to compose answers with different AI models with your own key.
Universal SEO skill for Claude Code. 19 sub-skills, 12 subagents, 3 extensions (DataForSEO, Firecrawl, Banana). Technical SEO, E-E-A-T, schema, GEO/AEO, backlinks, local SEO, maps intelligence, Goo…
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…
This work systematically evaluates the impact of decision protocols in multi-agent debates, showing that voting improves reasoning tasks, consensus benefits knowledge tasks, and introducing new met…
AI agents running research on single-GPU nanochat training automatically
Uptime tracker for endpoints of the cs-insights project.
Citation helper to display stats from Google Scholar on webpage.
The main frontend and backend of the cs-insights project.
The official code to generate the dataset of the paper "Affect, Body, Cognition, Demographics, and Emotion: The ABCDE of Text Features for Computational Affective Science"
A modernized, complete, self-contained TeX/LaTeX engine, powered by XeTeX and TeXLive.
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
[ICLR'24 Spotlight] A language model (LM)-based emulation framework for identifying the risks of LM agents with tool use
Web interface for browsing, search and filtering recent arxiv submissions
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
An open-source AI agent that brings the power of Gemini directly into your terminal.
news-please - an integrated web crawler and information extractor for news that just works
Repository for the LREC 2022 submission on Emotion Word Dynamics in Geolocated Tweet data.
Röttger et al. (2024): "IssueBench: Millions of Realistic Prompts for Measuring Issue Bias in LLM Writing Assistance"
The official evaluation implementation of the paper "BRIGHTER: BRIdging the Gap in Human-Annotated Textual Emotion Recognition Datasets for 28 Languages"