4 papers
What Does an Observability Foundation Model Know?
Dhyey Dharmendrakumar Mavani, Rian Atri, Tairan Ji
A linear probe can show that a label is recoverable from a model's hidden states, but not whether that goes beyond what the input already reveals, or whether the model uses it. We…
Formalizing chip-firing and Riemann--Roch for graphs in Lean 4
Dhyey Dharmendrakumar Mavani, Nathan Pflueger
The Riemann--Roch theorem for graphs, due to Baker and Norine, is a foundational result establishing a powerful analogy between finite graphs and algebraic curves. We describe a co…
Support Tokens, Stability Margins, and a New Foundation for Robust LLMs
Deepak Agarwal, Dhyey Dharmendrakumar Mavani, Suyash Gupta +2
Self-attention is usually described as a flexible, content-adaptive way to mix a token with information from its past. We reinterpret causal self-attention transformers, the backbo…
chipfiring: A Python Package for Efficient Mathematical Analysis of Chip-Firing Games on Multigraphs
Dhyey Dharmendrakumar Mavani, Tairan Ji, Nathan Pflueger
This paper presents `chipfiring`, a comprehensive Python package for the mathematical analysis of chip-firing games on finite graphs. The package provides a robust toolkit for defi…