Cite
Notes
Only stored in your browser.
Attribution
Learning on LLM Output Signatures for gray-box LLM Behavior Analysis
arXiv 2025
Graph Inductive Biases in Transformers without Message Passing
arXiv 2023
Structuring Representation Geometry with Rotationally Equivariant Contrastive Learning
from 3 papers
Adriana Romero-Soriano
Chen Lin
Fabrizio Frasca
Gal Chechik
Guy Bar-Shalom
Haggai Maron
Joshua Robinson
Liheng Ma
Mark Coates
Philip Torr