1 citations · 2 across the 5 of their papers we have counts for
6 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…
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…
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…
SIGMA: Sinkhorn-Guided Masked Video Modeling
Mohammadreza Salehi, Michael Dorkenwald, Fida Mohammad Thoker +3
Video-based pretraining offers immense potential for learning strong visual representations on an unprecedented scale. Recently, masked video modeling methods have shown promising…
PIN: Positional Insert Unlocks Object Localisation Abilities in VLMs
Michael Dorkenwald, Nimrod Barazani, Cees G. M. Snoek +1
Vision-Language Models (VLMs), such as Flamingo and GPT-4V, have shown immense potential by integrating large language models with vision systems. Nevertheless, these models face c…