A legible monospace font for playful professionals. Comic Sans for hackers

a classy font

Writing a compiler in a week-end

The Ipe extensible drawing editor

Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks

[CVPR 2024 Highlight] Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding

An LLM-free Multi-dimensional Benchmark for Multi-modal Hallucination Evaluation

Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning

Official PyTorch implementation for "Large Language Diffusion Models"

Code and weights for the paper "Cluster and Predict Latents Patches for Improved Masked Image Modeling"

🪄 Create rich visualizations with AI

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Development tool to measure, monitor and analyze the memory behavior of Python objects in a running Python application.

Democratizing Reinforcement Learning for LLMs

Hypersubatomic is a high contrast UI and syntax theme for VSCode

A minimal GPU design in Verilog to learn how GPUs work from the ground up

A repository that contains all the Data Structures and Algorithms concepts and their implementation in several ways, programming questions and Interview questions. The main aim of this repository i…

Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.

🌾 OAT: A research-friendly framework for LLM online alignment, including preference learning, reinforcement learning, etc.

CeTZ: ein Typst Zeichenpaket - A library for drawing stuff with Typst.

"Deep Generative Modeling": Introductory Examples

Awesome resources for GPUs

The book "Performance Analysis and Tuning on Modern CPU"

A Framework of Small-scale Large Multimodal Models

Original implementation of "Radiant Foam: Real-Time Differentiable Ray Tracing"

s1: Simple test-time scaling

Collection of resources for RL and Reasoning

Witness the aha moment of VLM with less than $3.