5 papers
Online LLM watermark detection via e-processes
Weijie Su, Ruodu Wang, Zinan Zhao
Watermarking for large language models (LLMs) has emerged as an effective tool for distinguishing AI-generated text from human-written content. Statistically, watermark schemes ind…
Recommending Best Paper Awards for ML/AI Conferences via the Isotonic Mechanism
Garrett G. Wen, Buxin Su, Natalie Collina +2
Machine learning and artificial intelligence conferences such as NeurIPS and ICML now regularly receive tens of thousands of submissions, posing significant challenges to maintaini…
Length-MAX Tokenizer for Language Models
Dong Dong, Weijie Su
We introduce a new tokenizer for language models that minimizes the average tokens per character, thereby reducing the number of tokens needed to represent text during training and…
You Are the Best Reviewer of Your Own Papers: The Isotonic Mechanism
Weijie Su
Machine learning (ML) and artificial intelligence (AI) conferences including NeurIPS and ICML have experienced a significant decline in peer review quality in recent years. To addr…
Isotropic Curvature Model for Understanding Deep Learning Optimization: Is Gradient Orthogonalization Optimal?
Weijie Su
In this paper, we introduce a model for analyzing deep learning optimization over a single iteration by leveraging the matrix structure of the weights. We derive the model by assum…