activity
20242026
collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2026

Interpretability Without Tradeoffs: Disentangling Polysemanticity At Equal Predictive Performance

Doğukan Bağcı, Bernt Schiele, Simone Schaub-Meyer +2

Deep neural networks (DNNs) are widely used, but interpreting what they actually learn remains difficult. A major obstacle is that individual neurons often encode multiple unrelate…

cs.LG2026

FaCT: Faithful Concept Traces for Explaining Neural Network Decisions

Amin Parchami-Araghi, Sukrut Rao, Jonas Fischer +1

Deep networks have shown remarkable performance across a wide range of tasks, yet getting a global concept-level understanding of how they function remains a key challenge. Many po…

cs.LG2025

A Granular Study of Safety Pretraining under Model Abliteration

Shashank Agnihotri, Jonas Jakubassa, Priyam Dey +4

Open-weight LLMs can be modified at inference time with simple activation edits, which raises a practical question for safety: do common safety interventions like refusal training…

cs.LG2025

Spatial Reasoners for Continuous Variables in Any Domain

Bart Pogodzinski, Christopher Wewer, Bernt Schiele +1

We present Spatial Reasoners, a software framework to perform spatial reasoning over continuous variables with generative denoising models. Denoising generative models have become…

cs.LG2025

Pixel-level Certified Explanations via Randomized Smoothing

Alaa Anani, Tobias Lorenz, Mario Fritz +1

Post-hoc attribution methods aim to explain deep learning predictions by highlighting influential input pixels. However, these explanations are highly non-robust: small, impercepti…

cs.LG2025

TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters

Haiyang Wang, Yue Fan, Muhammad Ferjad Naeem +5

Transformers have become the predominant architecture in foundation models due to their excellent performance across various domains. However, the substantial cost of scaling these…