Jonathan Hayase

Jhayase's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 7 papers 4 months ago

DataComp: In search of the next generation of multimodal datasets

Paper • 2304.14108 • Published Apr 27, 2023 • 2

Scalable Extraction of Training Data from (Production) Language Models

Paper • 2311.17035 • Published Nov 28, 2023 • 3

Query-Based Adversarial Prompt Generation

Paper • 2402.12329 • Published Feb 19, 2024

Git Re-Basin: Merging Models modulo Permutation Symmetries

Paper • 2209.04836 • Published Sep 11, 2022 • 2

Scalable Fingerprinting of Large Language Models

Paper • 2502.07760 • Published Feb 11

PLeaS -- Merging Models with Permutations and Least Squares

Paper • 2407.02447 • Published Jul 2, 2024

SuperBPE: Space Travel for Language Models

Paper • 2503.13423 • Published Mar 17 • 12

authored a paper about 1 year ago

Data Mixture Inference: What do BPE Tokenizers Reveal about their Training Data?

Paper • 2407.16607 • Published Jul 23, 2024 • 23

authored a paper over 1 year ago

Stealing Part of a Production Language Model

Paper • 2403.06634 • Published Mar 11, 2024 • 92