🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

dLLM: Simple Diffusion Language Modeling

Simple, unified interface to multiple Generative AI providers

Simple, safe way to store and distribute tensors

Tile primitives for speedy kernels

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs

Awesome LLM Jailbreak academic papers

Autoresearch for LLM adversarial attacks

Light, fluffy, and always free - The AWS Local Emulator alternative

Lightweight, useful implementation of conformal prediction on real data.

AI safety course at the University of Tübingen (Summer Semester 2026)

🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models

AI-powered job search system built on Claude Code. 14 skill modes, Go dashboard, PDF generation, batch processing.

A feed-forward 3D foundation model for reconstructing scenes from streaming data

A powerful Telegram bot that provides remote access to Claude Code, enabling developers to interact with their projects from anywhere with full AI assistance and session persistence.

Open-source macOS display manager. DDC brightness/contrast/volume, resolution switching, window tiling, night shift, HDR, profiles, CLI. Free alternative to BetterDisplay.

Strategic research thinking agents for Claude Code — idea evaluation, project triage, and structured brainstorming. Helps you decide which papers to write, not just how to write them.

[EMNLP'23] The official GitHub page for ''Evaluating Object Hallucination in Large Vision-Language Models''

[TACL'23] VSR: A probing benchmark for spatial undersranding of vision-language models.

The official GitHub page for ''Evaluating Object Hallucination in Large Vision-Language Models''

[CVPR'24] HallusionBench: You See What You Think? Or You Think What You See? An Image-Context Reasoning Benchmark Challenging for GPT-4V(ision), LLaVA-1.5, and Other Multi-modality Models

Train the smallest LM you can that fits in 16MB. Best model wins!

Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞