-
University of Minnesota
- Minneapolis, MN
-
01:21
(UTC -04:00) - guangyan.me
- @GuangyanS
- in/guangyansun
Highlights
- Pro
Stars
A lightweight, powerful framework for multi-agent workflows
Gemini is a modern LaTex beamerposter theme 🖼
Write HTML. Render video. Built for agents.
Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, an…
PRO-V: An Efficient Program Generation Multi-Agent System for Automatic RTL Verification
Benchmarking Hardware-Aware CUDA Optimization for Large Language Models Against CUDA Experts
Automated Multi-Agents End-to-End GPU Programing Framework-ICML'26
A Minimalist, Batteries-included Repository for Advancing World Model Science.
SpatialBench: Is Your Spatial Foundation Model an All-Round Player?
Simple and easily configurable grid world environments for reinforcement learning
40+ tips for getting the most out of Claude Code, from basics to advanced - includes a custom status line script and Claude Code running itself in a container. Also includes the dx plugin: skills f…
Video-R1: Reinforcing Video Reasoning in MLLMs [🔥the first paper to explore R1 for video]
The official implementation of the paper "MLP Memory: A Retriever-Pretrained Memory for Large Language Models". (ICLR 2026)
🔥🔥🔥 [Awesome] Latest Papers, Codes & Datasets on Streaming / Online Video Understanding — Building Always-on, Real-time Video AI 🤖
PaperBanana: Automating Academic Illustration For AI Scientists
21 writing rules for AI coding and writing agents. Drop-in for Claude Code, Codex, Copilot, Cursor, and Aider, so their output reads like a tech pro.
GradMem: Learning to Write Context into Memory with Test-Time Gradient Descent [ICML 2026]
Edit Banana: A framework for converting statistical formats into editable.
The first continuous diffusion language model that rivals discrete counterparts on standard language modeling benchmarks like LM1B and OpenWebText.
Code for "Back into Plato's Cave: Examining Cross-modal Representational Convergence at Scale"
Manuscript source: Self-orthogonalizing attractor neural networks emerging from the free energy principle
Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepowe…