activity
20242026
collaborators

10 papers

cs.CL2026

Prompt Compression via Activation Aggregation

Thibaud Ardoin, Semira Einsele, Evis Bregu +1

Large language models process prompts by propagating activations through dozens of layers before generating a response. We ask whether the task-relevant information contained in an…

cs.CL2026

Robust Text Watermarking for Large Language Models via Dual Semantic Embeddings

Jonas Schäfer, Cezary Pilaszewicz, Gerhard Wunder

This work presents Dual-Embedding Watermarking (DEW), a semantic watermarking scheme for large language models (LLMs) that leverages contextual and token-level embeddings to enhanc…

cs.AI2026

LLM Self-Recognition: Steering and Retrieving Activation Signatures

Thibaud Ardoin, Jonas Schäfer, Gerhard Wunder

Recent advances in interpretability suggest that large language models (LLMs) implicitly encode signals in their generated text that enable self-recognition of their outputs. We de…

cs.LG2025

ALIGN-FL: Architecture-independent Learning through Invariant Generative component sharing in Federated Learning

Mayank Gulati, Benedikt Groß, Gerhard Wunder

We present ALIGN-FL, a novel approach to distributed learning that addresses the challenge of learning from highly disjoint data distributions through selective sharing of generati…

cs.LG2025

Rethinking Explanation Evaluation under the Retraining Scheme

Yi Cai, Thibaud Ardoin, Mayank Gulati +1

Feature attribution has gained prominence as a tool for explaining model decisions, yet evaluating explanation quality remains challenging due to the absence of ground-truth explan…

cs.LG2025

Machine and Deep Learning for Indoor UWB Jammer Localization

Hamed Fard, Mahsa Kholghi, Benedikt Groß +1

Ultra-wideband (UWB) localization delivers centimeter-scale accuracy but is vulnerable to jamming attacks, creating security risks for asset tracking and intrusion detection in sma…