4 papers
Elastic ViTs from Pretrained Models without Retraining
Walter Simoncini, Michael Dorkenwald, Tijmen Blankevoort +2
Vision foundation models achieve remarkable performance but are only available in a limited set of pre-determined sizes, forcing sub-optimal deployment choices under real-world con…
KV Cache Steering for Controlling Frozen LLMs
Max Belitsky, Dawid J. Kopiczko, Michael Dorkenwald +4
We propose cache steering, a lightweight method for implicit steering of language models via a one-shot intervention applied directly to the key-value cache. To validate its effect…
GLOV: Guided Large Language Models as Implicit Optimizers for Vision Language Models
M. Jehanzeb Mirza, Mengjie Zhao, Zhuoyuan Mao +12
In this work, we propose GLOV, which enables Large Language Models (LLMs) to act as implicit optimizers for Vision-Language Models (VLMs) to enhance downstream vision tasks. GLOV p…
Lost in Time: A New Temporal Benchmark for VideoLLMs
Daniel Cores, Michael Dorkenwald, Manuel Mucientes +2
Large language models have demonstrated impressive performance when integrated with vision models even enabling video understanding. However, evaluating video models presents its o…