Lee Lab @ UW Madison

LanguageInterfacedFineTuning. Code for Language-Interfaced FineTuning for Non-Language Machine Learning Tasks.

LLM-judge-reporting. A simple plug-in framework that corrects bias and computes confidence intervals in reporting LLM-as-a-judge evaluation, and an adaptive algorithm that efficiently allocates calibration samples to reduce uncertainty in estimates.

CoBSAT. Implementation and dataset for paper "Can MLLMs Perform Text-to-Image In-Context Learning?"

VersaPRM. Python

SFT-PG. Code for "Optimizing DDPM Sampling with Shortcut Fine-Tuning" (https://arxiv.org/abs/2301.13362), ICML 2023

Expressive_Power_of_LoRA. Code for "The Expressive Power of Low-Rank Adaptation".

ReJump. Jupyter Notebook

score-wasserstein. Code for "Score-based Generative Modeling Secretly Minimizes the Wasserstein Distance", NeurIPS 2022

looped-tf. Code for Looped Transformers for Length Generalization (https://arxiv.org/abs/2409.15647), ICLR 2025

CLIP_Counting. Code for "Zero-shot Improvement of Object Counting with CLIP"

Dual_Operating_Modes_of_ICL. Python

TAPE. Python

InRep. Python

Transformers-in-the-Dark. Repository for "Transformers in the Dark: Navigating Unknown Search Spaces via Bandit Feedback"

ENTP. Python

Coded_Prompts_for_LLMs. Code for "Coded Prompts for Large Language Models".

CodedInvNet. ICML2021

walip. Python

GenLabel_official. ICML 2022 Paper entitled "GenLabel: Mixup Relabeling using Generative Models": https://arxiv.org/pdf/2201.02354.pdf