Scholar
Antonio Guillen-Perez
Google Scholar ID: BFS6jXwAAAAJ
Research Scientist @ Hewlett Packard Labs HPE
Citations & Impact
Citations
928
H-index
14
i10-index
22
Publications
20
Co-authors
0
Publications
Resume
Academic Achievements
- Hierarchical RL work 'GreenDCC' accepted to AAAI 2025 Demonstration Track (Nov 2024)
- MARL benchmark 'SustainDC' accepted to NeurIPS 2024 Datasets and Benchmarks Track (Oct 2024)
- New benchmarks 'SustainCluster' and 'SustainLC' accepted to NeurIPS 2025 Datasets and Benchmarks Track (Sept 2025)
- Received Best ML Innovation Award at NeurIPS 2023 Climate Change AI Workshop (Dec 2023)
- Filed U.S. patent on 'Real-Time Carbon Footprint Reduction Controller' (May 2024)
- Achieved state-of-the-art minADE of 0.25 on Waymo Open Motion Dataset
- Developed novel algorithms like LfOD; published at top venues including NeurIPS and AAAI
Research Experience
- Joined HPE AI Labs as an AI Research/Applied Scientist in September 2022
- Initiated a new research stream at HPE on LLM-based agents for dynamic system control (Early 2025)
- Developed 'Efficient Virtuoso', a state-of-the-art latent diffusion Transformer for goal-conditioned trajectory planning in autonomous vehicles
- Led 'Mining the Long Tail' project investigating data curation strategies for robust Offline RL in AVs
- Led 'From Imitation to Optimization' project demonstrating 3.2x higher success rates than behavior cloning baselines in Offline RL for AVs