# Lee Lab @ UW Madison

Our research focuses on developing more effective and efficient algorithms and systems for *deep learning with foundation models*. We strive to accomplish this by conducting theoretical analysis and by devising principled approaches to enhance the performance of current algorithms and systems.

## Selected Work on Deep Learning with Foundation Models

Link | Topic | Title | Summary | Github |
---|---|---|---|---|

NeurIPSW’23 | Theory | The Expressive Power of Low-Rank Adaptation (LoRA) | Summary | Github |

NeurIPSW’23 | LLM | Image Clustering Conditioned on Text Criteria | Summary | Github |

NeurIPSW’23 | LLM | Coded Prompts for Large Language Models | ||

NeurIPSW’23 | CLIP | Zero-shot Improvement of Object Counting with CLIP | ||

NeurIPSW’23 | Diffusion | Super-Resolution Emulation of Large Cosmological Fields with a 3D Conditional Diffusion Model | ||

NeurIPS’23 | Diffusion | Reinforcement learning for improved text-to-image alignment | Summary | Github |

ICML’23 | LLM, Theory | Looped Transformers as Programmable Computers | Summary | |

ICML’23 | Diffusion | Reinforcement learning for faster DDPM sampling | Summary | Github |

ACL’23 (Findings) | LLM | An LLM agent with memory for long-term conversation | Summary | Github |

EMNLP’22 (Findings) | LLM, CLIP | Unsupervised word translation (via connecting two CLIP models) | Summary | Github |

NeurIPS’22 | LLM | LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks | Summary | Github |

NeurIPS’22 | Diffusion, Theory | Score-based Generative Modeling Secretly Minimizes the Wasserstein Distance | Summary | Github |

ICMLW’23 | CLIP, Theory | Mini-Batch Optimization of Contrastive Loss | Github | |

ICMLW’23, NeurIPSW’23 | LLM | Teaching arithmetic to a small Transformer | Summary | Github |

ICMLW’23 | LLM | A compute-latency trade-off for language model decoding | ||

ICMLW’23 | LLM | A looped-Transformer architecture for efficient meta-learning | ||

ACLW’22 | LLM | Debiasing language models via parameter-efficient fine-tuning |

## Selected Talks on Deep Learning with Foundation Models

- (Oct. 2023) Trust Perspectives in Machine Learning, Law, and Public Policy at the Institute for Data, Econometrics, Algorithms, and Learning (IDEAL) @ Northwestern University
- (Oct. 2023) Distinguished Lectures in Microbiology @ University of Wisconsin-Madison
- (May 2023) KSEA Distinguished Guest Series
- (Feb. 2023) Information Theory and Applications Workshop
- (Feb. 2023) The Coordinated Science Laboratory Student Conference @ UIUC
- (Jan. 2023) Information Theory and Data Science Workshop @ National University of Singapore
- (Jan. 2023) Systems, Information, Learning and Optimization (SILO) Seminar @ University of Wisconsin-Madison
- (Aug. 2022) Samsung Advanced Institute of Technology

## News

- (Sep. 2023) One paper is accepted to
**[NeurIPS’23]** - (May 2023) One paper is accepted to
**[ACL’23 (Findings)]** - (Apr. 2023) Three papers are accepted to
**[ICML’23]**