4 papers
PRIME: Perception Feedback with Situational Memory Embeddings in VLA Models
Erik Deinzer, Naya Baslan, Luca Paparusso +3
Current Vision-Language-Action (VLA) models for autonomous driving operate primarily through feedforward inference across the perception--reasoning--planning hierarchy. While moder…
Information-Theoretic Policy Pre-Training with Empowerment
Moritz Schneider, Robert Krug, Narunas Vaskevicius +3
Empowerment, an information-theoretic measure of an agent's potential influence on its environment, has emerged as a powerful intrinsic motivation and exploration framework for rei…
GraphEQA: Using 3D Semantic Scene Graphs for Real-time Embodied Question Answering
Saumya Saxena, Blake Buchanan, Chris Paxton +6
In Embodied Question Answering (EQA), agents must explore and develop a semantic understanding of an unseen environment to answer a situated question with confidence. This problem…
The Surprising Ineffectiveness of Pre-Trained Visual Representations for Model-Based Reinforcement Learning
Moritz Schneider, Robert Krug, Narunas Vaskevicius +2
Visual Reinforcement Learning (RL) methods often require extensive amounts of data. As opposed to model-free RL, model-based RL (MBRL) offers a potential solution with efficient da…