activity
20242026
collaborators

9 papers

cs.CV2026

Fourier Self-Supervision for Fine-Grained Generalized Category Discovery

Sarah Rastegar, Mina Ghadimi Atigh, Pascal Mettes +2

Generalized Category Discovery aims to recognize known categories while identifying novel ones within unlabeled data. Existing methods, typically based on self-supervision and cont…

cs.CL2026

What Layers When: Learning to Skip Compute in LLMs with Residual Gates

Filipe Laitenberger, Dawid Kopiczko, Cees G. M. Snoek +1

We introduce GateSkip, a simple residual-stream gating mechanism that enables token-wise layer skipping in decoder-only LMs. Each Attention/MLP branch is equipped with a sigmoid-li…

cs.CL2026

Better Language Models Exhibit Higher Visual Alignment

Jona Ruthardt, Gertjan J. Burghouts, Serge Belongie +1

How well do text-only large language models (LLMs) align with the visual world? We present a systematic evaluation of this question by incorporating frozen representations of vario…

cs.CL2025

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…

cs.CV2025

MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning

Mohammadreza Salehi, Shashanka Venkataramanan, Ioana Simion +3

Dense self-supervised learning has shown great promise for learning pixel- and patch-level representations, but extending it to videos remains challenging due to the complexity of…

cs.CV2025

Near, far: Patch-ordering enhances vision foundation models' scene understanding

Valentinos Pariza, Mohammadreza Salehi, Gertjan Burghouts +2

We introduce NeCo: Patch Neighbor Consistency, a novel self-supervised training loss that enforces patch-level nearest neighbor consistency across a student and teacher model. Comp…