collaborators

8 papers

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.CV2025

-Quant: Towards Learnable Quantization for Low-bit Pattern Recognition

Mishal Fatima, Shashank Agnihotri, Marius Bock +4

Most pattern recognition models are developed on pre-proce\-ssed data. In computer vision, for instance, RGB images processed through image signal processing (ISP) pipelines design…

cs.CV2025

AIM: Amending Inherent Interpretability via Self-Supervised Masking

Eyad Alshami, Shashank Agnihotri, Bernt Schiele +1

It has been observed that deep neural networks (DNNs) often use both genuine as well as spurious features. In this work, we propose "Amending Inherent Interpretability via Self-Sup…

cs.CV2025

Faithful, Interpretable Chest X-ray Diagnosis with Anti-Aliased B-cos Networks

Marcel Kleinmann, Shashank Agnihotri, Margret Keuper

Faithfulness and interpretability are essential for deploying deep neural networks (DNNs) in safety-critical domains such as medical imaging. B-cos networks offer a promising solut…

cs.CL2025

Smart Eyes for Silent Threats: VLMs and In-Context Learning for THz Imaging

Nicolas Poggi, Shashank Agnihotri, Margret Keuper

Terahertz (THz) imaging enables non-invasive analysis for applications such as security screening and material classification, but effective image classification remains challengin…

cs.CV2025

SemSegBench & DetecBench: Benchmarking Reliability and Generalization Beyond Classification

Shashank Agnihotri, David Schader, Jonas Jakubassa +5

Reliability and generalization in deep learning are predominantly studied in the context of image classification. Yet, real-world applications in safety-critical domains involve a…