Locus Lab

university

zicokolter

locuslab

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

zekeZZ updated a model 14 days ago

locuslab/llama2-7b_idk_1e-05_forget05

zekeZZ updated a model 14 days ago

locuslab/llama2-7b_idk_1e-05_forget01

zekeZZ updated a model 14 days ago

locuslab/llama2-7b_KL_1e-05_forget05

View all activity

locuslab's activity

zekeZZ

updated 6 models 14 days ago

schwarzschild

authored a paper 6 months ago

Benchmarking ChatGPT on Algorithmic Reasoning

Paper • 2404.03441 • Published Apr 4, 2024

zkolter

authored a paper 7 months ago

Understanding Hallucinations in Diffusion Models through Mode Interpolation

Paper • 2406.09358 • Published Jun 13, 2024 • 4

pratyushmaini

authored a paper 7 months ago

Understanding Hallucinations in Diffusion Models through Mode Interpolation

Paper • 2406.09358 • Published Jun 13, 2024 • 4

sumukhaithal6

authored 3 papers 7 months ago

Understanding Hallucinations in Diffusion Models through Mode Interpolation

Paper • 2406.09358 • Published Jun 13, 2024 • 4

A Closer Look at Smoothness in Domain Adversarial Training

Paper • 2206.08213 • Published Jun 16, 2022

Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data

Paper • 2212.13827 • Published Dec 28, 2022

schwarzschild

authored a paper 8 months ago

Transformers Can Do Arithmetic with the Right Embeddings

Paper • 2405.17399 • Published May 27, 2024 • 52

schwarzschild

authored 3 papers 9 months ago

Baseline Defenses for Adversarial Attacks Against Aligned Language Models

Paper • 2309.00614 • Published Sep 1, 2023 • 2

Universal Guidance for Diffusion Models

Paper • 2302.07121 • Published Feb 14, 2023

Rethinking LLM Memorization through the Lens of Adversarial Compression

Paper • 2404.15146 • Published Apr 23, 2024

pratyushmaini

authored a paper 12 months ago

Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling

Paper • 2401.16380 • Published Jan 29, 2024 • 48

schwarzschild

authored a paper 12 months ago

Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text

Paper • 2401.12070 • Published Jan 22, 2024 • 44

schwarzschild

authored 2 papers about 1 year ago

A Cookbook of Self-Supervised Learning

Paper • 2304.12210 • Published Apr 24, 2023 • 3

NEFTune: Noisy Embeddings Improve Instruction Finetuning

Paper • 2310.05914 • Published Oct 9, 2023 • 14

AI & ML interests

Recent Activity

Team members 9

locuslab's activity