Starred repositories
The simplest, fastest repository for training/finetuning medium-sized GPTs.
A fully open-source humanoid arm for physical AI research and deployment in contact-rich environments.
The Remdis toolkit: Building advanced real-time multimodal dialogue systems with incremental processing and large language models. This repository provides the English version of Remdis.
Interactive visualizations of the geometric intuition behind diffusion models.
The raw game transcripts, additional materials and processor for the PhotoBook Dataset
An AI cursor for desktop using Gemini 2.0 Flash (Experimental)
HumanEvalComm: Evaluating Communication Skill of Code LLM and LLM Agent
Code and data associated with the AmbiEnt dataset in "We're Afraid Language Models Aren't Modeling Ambiguity" (Liu et al., 2023)
Agent Laboratory is an end-to-end autonomous research workflow meant to assist you as the human researcher toward implementing your research ideas
Neuroimaging analysis and visualization suite
Data visualization code generation benchmark: Evaluates LLMs' ability to generate visualization code from DataFrame descriptions.
💡 Resources about Sign Language Processing (e.g., Sign Language Recognition / Translation / Production)
Charlie the Coding Cow: Classroom Edition
Visualize country borders from different times in history (2000 BC-1994)
Source Code of Paper "GPTScore: Evaluate as You Desire"
[ICCV 2025] GRAB: A Challenging GRaph Analysis Benchmark for Large Multimodal Models
MathVista: data, code, and evaluation for Mathematical Reasoning in Visual Contexts
[ICLR 2025] ChartMimic: Evaluating LMM’s Cross-Modal Reasoning Capability via Chart-to-Code Generation
A handbook for EEG data analysis based on Python
DVQA Dataset: A Bar chart question answering dataset presented at CVPR 2018