CLI for common Playwright actions. Record and generate Playwright code, inspect selectors and take screenshots.

Automatic solver for plane geometry problems.

Tongyi Deep Research, the Leading Open-source Deep Research Agent

Resources and paper list for "Thinking with Images for LVLMs". This repository accompanies our survey on how LVLMs can leverage visual information for complex reasoning, planning, and generation.

[AAAI 2026] Multimodal Deepresearcher: Generating Text-Chart Interleaved Reports From Scratch with Agentic Framework

R1-onevision, a visual language model capable of deep CoT reasoning.

Leveraging Multimodal Prompt for Visualization Authoring with LLMs

Vega-Lite Chart Dataset and NL Generation Framework using LLMs

Code for BLT research paper

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

PyTorch Implementation of Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model

Pytorch implementation of Transfusion, "Predict the Next Token and Diffuse Images with One Multi-Modal Model", from MetaAI

Awesome-Paper-list: Visualization meets LLM

A benchmark designed to evaluate visualization generation methods.

Graph Diffusion Policy Optimization

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

General technology for enabling AI capabilities w/ LLMs and MLLMs

[CVPR 2024] VCoder: Versatile Vision Encoders for Multimodal Large Language Models

Repository for the paper "Cognitive Mirage: A Review of Hallucinations in Large Language Models"

Build AI Agents, Visually

Here is the official implementation of the model KD3A in paper "KD3A: Unsupervised Multi-Source Decentralized Domain Adaptation via Knowledge Distillation".

OI / ACM-ICPC essays and learning materials