From the 1 of 6 linked papers with an AI index.
6 papers
Distilling Answer Set Programming Theories from Large Language Models
Nelson Higuera Ruiz, Markus Hofmarcher, Claudiu Leoveanu-Condrei
The paper investigates whether large language models can automatically generate correct Answer Set Programming theories for visual question answering tasks within a one‑hour time l…
Retrieval-Augmented Decision Transformer: External Memory for In-context RL
Thomas Schmied, Fabian Paischer, Vihang Patil +3
In-context learning (ICL) is the ability of a model to learn a new task by observing a few exemplars in its context. While prevalent in NLP, this capability has recently also been…
HyDRA: A Hybrid-Driven Reasoning Architecture for Verifiable Knowledge Graphs
Adrian Kaiser, Claudiu Leoveanu-Condrei, Ryan Gold +2
The synergy between symbolic knowledge, often represented by Knowledge Graphs (KGs), and the generative capabilities of neural networks is central to advancing neurosymbolic AI. A…
Linear Alignment of Vision-language Models for Image Captioning
Fabian Paischer, Markus Hofmarcher, Sepp Hochreiter +1
Recently, vision-language models like CLIP have advanced the state of the art in a variety of multi-modal tasks including image captioning and caption evaluation. Many approaches l…
Contrastive Abstraction for Reinforcement Learning
Vihang Patil, Markus Hofmarcher, Elisabeth Rumetshofer +1
Learning agents with reinforcement learning is difficult when dealing with long trajectories that involve a large number of states. To address these learning problems effectively,…
Large Language Models Can Self-Improve At Web Agent Tasks
Ajay Patel, Markus Hofmarcher, Claudiu Leoveanu-Condrei +3
Training models to act as agents that can effectively navigate and perform actions in a complex environment, such as a web browser, has typically been challenging due to lack of tr…