Markus Hofmarcher

Joined

September 2018

Names

Markus Hofmarcher (Preferred)

Emails

****@ml.jku.at (Confirmed)

Personal Links

Google Scholar

DBLP

Career & Education History

PhD student

Johannes Kepler Universität Linz (jku.at)

2016 – 2024

Undergrad student

Johannes Kepler Universität Linz (jku.at)

2010 – 2016

Advisors, Relations & Conflicts

PhD Advisor

Sepp Hochreiter

2016 – 2024

Expertise

Reinforcement Learning

Present

Large Language Models

Present

Convolutional Neural Networks

Present

Recurrent Neural Networks

Present

Publications

Large Language Models Can Self-Improve At Web Agent Tasks
Ajay Patel, Markus Hofmarcher, Claudiu Leoveanu-Condrei, Marius-Constantin Dinu, Chris Callison-Burch, Sepp Hochreiter
- arXiv
- Readers: Everyone
Large Language Models Can Self-Improve At Web Agent Tasks
Ajay Patel, Markus Hofmarcher, Claudiu Leoveanu-Condrei, Marius-Constantin Dinu, Chris Callison-Burch, Sepp Hochreiter
- Submitted to ICLR 2025
- Readers: Everyone
Retrieval-Augmented Decision Transformer: External Memory for In-context RL
Thomas Schmied, Fabian Paischer, Vihang Prakash Patil, Markus Hofmarcher, Razvan Pascanu, Sepp Hochreiter
- Submitted to ICLR 2025
- Readers: Everyone
Contrastive Abstraction for Reinforcement Learning
Vihang Patil, Markus Hofmarcher, Elisabeth Rumetshofer, Sepp Hochreiter
- GenPlan'23
- Readers: Everyone
Close the Gap: Lightweight Image Captioning via Retrieval Augmentation
Fabian Paischer, Thomas Adler, Markus Hofmarcher, Sepp Hochreiter
- Submitted to ICLR 2024
- Readers: Everyone
Learning to Modulate pre-trained Models in RL
Thomas Schmied, Markus Hofmarcher, Fabian Paischer, Razvan Pascanu, Sepp Hochreiter
- NeurIPS 2023 poster
- Readers: Everyone
Semantic HELM: A Human-Readable Memory for Reinforcement Learning
Fabian Paischer, Thomas Adler, Markus Hofmarcher, Sepp Hochreiter
- NeurIPS 2023 poster
- Readers: Everyone
Learning to Modulate pre-trained Models in RL
Thomas Schmied, Markus Hofmarcher, Fabian Paischer, Razvan Pascanu, Sepp Hochreiter
- Published: 03 Mar 2023, Last Modified: 15 Feb 2026
- RRL 2023 Oral
- Readers: Everyone
Foundation Models for History Compression in Reinforcement Learning
Fabian Paischer, Thomas Adler, Andreas Radler, Markus Hofmarcher, Sepp Hochreiter
- 08 Oct 2022 (modified: 05 May 2023)
- Deep RL Workshop 2022
- Readers: Everyone
Foundation Models for History Compression in Reinforcement Learning
Fabian Paischer, Thomas Adler, Andreas Radler, Markus Hofmarcher, Sepp Hochreiter
- 05 Oct 2022 (modified: 05 May 2023)
- FMDM@NeurIPS2022
- Readers: Everyone

View all 27 publications

Co-Authors

View all 47 co-authors