7 papers
SCOPD: Sparse-Context On-Policy Self-Distillation for Efficient Vision-Language Models
Ahmadreza Jeddi, Enming Zhang, Jasper Gerigk +12
Reasoning vision-language models (VLMs) process images and videos as long sequences of visual tokens, making inference expensive. Training-free token pruning reduces this cost, but…
Learning Actuator-Aware Spectral Submanifolds for Precise Control of Continuum Robots
Paul Leonard Wolff, Hugo Buurmeijer, Luis Pabon +6
Continuum robots exhibit high-dimensional, nonlinear dynamics which are often coupled with their actuation mechanism. Spectral submanifold (SSM) reduction has emerged as a leading…
Graph Neural Model Predictive Control for High-Dimensional Systems
Patrick Benito Eberhard, Luis Pabon, Daniele Gammelli +5
The control of high-dimensional systems, such as soft robots, requires models that faithfully capture complex dynamics while remaining computationally tractable. This work presents…
Observing and Controlling Features in Vision-Language-Action Models
Hugo Buurmeijer, Carmen Amo Alonso, Aiden Swann +1
Vision-Language-Action models (VLAs) have shown remarkable progress towards embodied intelligence. While their architecture partially resembles that of Large Language Models (LLMs)…
Sparse Autoencoders Reveal Interpretable and Steerable Features in VLA Models
Aiden Swann, Lachlain McGranahan, Hugo Buurmeijer +2
Vision-Language-Action (VLA) models have emerged as a promising approach for general-purpose robot manipulation. However, little research has mechanistically explored when and why…
Taming High-Dimensional Dynamics: Learning Optimal Projections onto Spectral Submanifolds
Hugo Buurmeijer, Luis A. Pabon, John Irvin Alora +3
High-dimensional nonlinear systems pose considerable challenges for modeling and control across many domains, from fluid mechanics to advanced robotics. Such systems are typically…
Constrained Hierarchical Monte Carlo Belief-State Planning
Arec Jamgochian, Hugo Buurmeijer, Kyle H. Wray +2
Optimal plans in Constrained Partially Observable Markov Decision Processes (CPOMDPs) maximize reward objectives while satisfying hard cost constraints, generalizing safe planning…