-
University of Minnesota, Twin Cities
- USA
- https://dykang.github.io/
- @dongyeopkang
- https://minnesotanlp.github.io/
- https://github.com/minnesotanlp
Highlights
- Pro
Stars
Khanh Chi Le et al's paper on ScholaWrite: A Dataset of End-to-End Scholarly Writing Process
Code for Shuyu Gan et al's paper "SanSi: A Looped Typed Decision Model for System 1.5 Thinking"
Code and data for paper "EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific Discovery"
A visual Overleaf guide to the Minnesota NLP LaTeX style, with live previews and one-line setup.
Code for "Meta^n: Recursive Self-Improvement through Emergent Depth"
Official code, models, and dataset for NeuRIP 2026 paper "Evolution Fine-Tuning (EFT): Learning to Discover Across 371 Optimization Tasks"
Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA
Codebase for the paper, "Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models"
Zae Myung Kim's paper on "The Amazing Agent Race: Strong Tool Users, Weak Navigators"
⚡️ Superpowers for your Openclaw. Powerful prebuilt agent workflows.
AI agents running research on single-GPU nanochat training automatically
End-to-end pipeline for seeing how LLMs actually process your prompts. Capture attention across every layer, render heatmaps and cooking curves, compare variants with evidence — not vibes.
Unofficial Python client library for Semantic Scholar APIs.
An agentic skills framework & software development methodology that works.
Our library for RL environments + evals
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
Minimal reproduction of DeepSeek R1-Zero
Karin de Langis's EMNLP 2024 paper on "Dynamic Multi-Reward Weighting for Multi-Style Controllable Generation"
The full dataset behind paperswithcode.com
Parkar and Kim et al.'s paper on :SelectLLM: Can LLMs Select Important Instructions to Annotate?"
Code repository for Kim et al's ACL 2024 paper: "Threads of Subtlety: Detecting Machine-Generated Texts Through Discourse Motifs"
Code for Das et al.'s paper "Which Modality should I use -- Text, Motif, or Image? : Understanding Graphs with Large Language Models"
Survey of LLM generated data
Code and dataset for de Langis et al's paper "A Comparative Study on Textual Saliency of Styles from Eye Tracking, Annotations, and Language Models"
Code for Hayati et al's paper "StyLEx: Explaining Styles with Lexicon-Based Human Perception"