9 papers
Orbis 2: A Hierarchical World Model for Driving
Sudhanshu Mittal, Arian Mousakhan, Silvio Galesso +4
Current world models operate at a single level of abstraction, with most prioritizing perceptual fidelity while lacking the spatial reasoning and semantic understanding required fo…
The Surprising Effectiveness of Canonical Knowledge Distillation for Semantic Segmentation
Muhammad Ali, Kevin Alexander Laube, Madan Ravi Ganesh +3
Recent knowledge distillation (KD) methods for semantic segmentation introduce increasingly complex hand-crafted objectives, yet are typically evaluated under fixed iteration sched…
What Drives Compositional Generalization? The Importance of Continuous Training Objectives in Visual Generative Models
Karim Farid, Rajat Sahay, Yumna Ali Alnaggar +4
Compositional generalization, the ability to generate novel combinations of known concepts, is a key ingredient for visual generative models. Yet, not all mechanisms that enable or…
Towards Understanding Subliminal Learning: When and How Hidden Biases Transfer
Simon Schrodi, Elias Kempf, Fazl Barez +1
Language models can transfer hidden biases during distillation. For example, a teacher that "likes owls" can make its student "like owls" too, even when the training data consists…
Simple LLM Baselines are Competitive for Model Diffing
Elias Kempf, Simon Schrodi, Bartosz CywiÅski +3
Standard LLM evaluations only test capabilities or dispositions that evaluators designed them for, missing unexpected differences such as behavioral shifts between model revisions…
cVLA: Towards Efficient Camera-Space VLAs
Max Argus, Jelena Bratulic, Houman Masnavi +4
Vision-Language-Action (VLA) models offer a compelling framework for tackling complex robotic manipulation tasks, but they are often expensive to train. In this paper, we propose a…