conftrace_

input space

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

adversarial robustness (2) neural activation pattern (1) large language model (1) input distribution (1) text transformation (1) class mixture (1) continuous-time function (1) predicted label (1) region count (1) batch size (1)

Papers

Language Models Are Implicitly Continuous ICLR 2025 Understanding Nonlinear Implicit Bias via Region Counts in Input Space ICML 2025 Towards Reliable Neural Specifications ICML 2023 Sibylvariant Transformations for Robust Text Classification ACL 2022