works on

From the 1 of 6 linked papers with an AI index.

collaborators

6 papers

cs.CV2026

Attentive multilayer fusion for vision transformers

Laure Ciernik, Marco Morik, Lukas Thede +4

The paper introduces Attentive Layer Fusion (ALF), a method that dynamically combines representations from all layers of a Vision Transformer to improve linear probing on downstrea…

cs.LG2026

CapTrack: Multifaceted Evaluation of Forgetting in LLM Post-Training

Lukas Thede, Stefan Winzeck, Zeynep Akata +1

Large language model (LLM) post-training enhances latent skills, unlocks value alignment, improves performance, and enables domain adaptation. Unfortunately, post-training is known…

cs.CL2026

Structural Pruning of Large Vision Language Models: A Comprehensive Study on Pruning Dynamics, Recovery, and Data Efficiency

Yiran Huang, Lukas Thede, Massimiliano Mancini +2

While Large Vision Language Models (LVLMs) demonstrate impressive capabilities, their substantial computational and memory requirements pose deployment challenges on resource-const…

cs.CL2025

WikiBigEdit: Understanding the Limits of Lifelong Knowledge Editing in LLMs

Lukas Thede, Karsten Roth, Matthias Bethge +2

Keeping large language models factually up-to-date is crucial for deployment, yet costly retraining remains a challenge. Knowledge editing offers a promising alternative, but metho…

cs.LG2025

Reflecting on the State of Rehearsal-free Continual Learning with Pretrained Models

Lukas Thede, Karsten Roth, Olivier J. Hénaff +2

With the advent and recent ubiquity of foundation models, continual learning (CL) has recently shifted from continual training from scratch to the continual adaptation of pretraine…

cs.CL2025

Investigating Structural Pruning and Recovery Techniques for Compressing Multimodal Large Language Models: An Empirical Study

Yiran Huang, Lukas Thede, Massimiliano Mancini +2

While Multimodal Large Language Models (MLLMs) demonstrate impressive capabilities, their substantial computational and memory requirements pose significant barriers to practical d…