output
20022026
most citedMethods for Interpreting and Understanding Deep Neural Networks

2.8k citations

Showing cs.LGShow all

49 papers · 1 filter

cs.LG2026

Foundation Models for Generalizable Semantic and Goal-Oriented Communication

Boliang Liu, Wint Yi Poe, Riccardo Trivisonno +1

Semantic and goal-oriented communication is increasingly studied for 6G, but generalization beyond seen data remains a key weakness under tight rate budgets. Many existing systems…

cs.LG2026

Distributed Sparse Interventions in Language Models

Maximilian S. Ernst, Lorenz Linhardt, Aaron Peikert +1

Language models perform a wide range of tasks at varying levels of abstraction with the capacity to flexibly infer tasks from context, execute multiple tasks simultaneously, and se…

cs.LG20251 cited

Computational Measurement of Political Positions: A Review of Text-Based Ideal Point Estimation Algorithms

Patrick Parschan, Charlott Jakob

This article presents the first systematic review of unsupervised and semi-supervised computational text-based ideal point estimation (CT-IPE) algorithms, methods designed to infer…

cs.LG20252 cited

Mitigating Clever Hans Strategies in Image Classifiers through Generating Counterexamples

Sidney Bender, Ole Delzer, Jan Herrmann +3

Deep learning models remain vulnerable to spurious correlations, leading to so-called Clever Hans predictors that undermine robustness even in large-scale foundation and self-super…

cs.LG2025

Don't Be Greedy, Just Relax! Pruning LLMs via Frank-Wolfe

Christophe Roux, Max Zimmer, Alexandre d'Aspremont +1

Pruning is a common technique to reduce the compute and storage requirements of Neural Networks. While conventional approaches typically retrain the model to recover pruning-induce…

cs.LG2025

Dynamics-Informed Reservoir Computing with Visibility Graphs

Charlotte Geier, Rasha Shanaz, Merten Stender

Accurate prediction of complex and nonlinear time series remains a challenging problem across engineering and scientific disciplines. Reservoir computing (RC) offers a computationa…