Ángela López Cardona
I am a researcher specializing in Large Language Models, multimodal architectures, and cognitive-signal integration for human alignment and interpretability. My work includes reward modeling (RLHF, DPO), dataset creation, and cognitively inspired training pipelines developed during my industrial PhD at Telefónica Innovación Digital and Universitat Politècnica de Catalunya (UPC) under the supervision of Sergi Abadal and Ioannis Arapakis.
Before transitioning into research, I spent four years leading end-to-end development of AI-driven products in the energy sector. I am currently in my third year of the PhD and hold two Master’s degrees: one in Industrial Engineering and another in Artificial Intelligence.
news
| Sep 14, 2026 | Started as a SPAR fellow where I will be working on the project Detecting Hidden Traits in Synthetic Data |
|---|---|
| Jun 03, 2026 | Paper accepted at RLxF: Reinforcement Learning from World Feedback @ ICML 2026: VLFEEDBACK-EEG: Neural Signals as Implicit Feedback for Vision-Language Model Alignment. |
| May 01, 2026 | Started a research stay at the Universitat Pompeu Fabra within the COLT Group. |
| Feb 22, 2026 | Started a short-term research stay at the University of Zurich within the Digital Linguistics Group. |
| Feb 21, 2026 | Invited talk How cognitive data can improve LLM alignment at Cohere Labs: Community Talks. Video.. |
| Sep 22, 2025 | Paper accepted at UniReps 2025, NeurIPS: Brain–Language Model Alignment: Insights into the Platonic Hypothesis and Intermediate-Layer Advantage. |
| Sep 13, 2025 | Attended the M2l Summer School in Split, Croatia. |
| Apr 14, 2025 | Started a research stay at the University of Glasgow where I will focus on Multimodal LLMs. |
| Apr 01, 2025 | Paper accepted at IJCNN 2025: Integrating Cognitive Processing Signals into Language Models: A Review of Advances, Applications and Future Directions. |
| Mar 28, 2025 | Paper accepted at ETVIS ETRA 2025: A Comparative Study of Scanpath Models in Graph-Based Visualization. |
| Mar 13, 2025 | Paper accepted at ETRA 2025: OASST-ETC Dataset: Alignment Signals from Eye-tracking Analysis of LLM Responses. |
| Jan 22, 2025 | Paper accepted at ICLR 2025: Seeing Eye to AI: Human Alignment via Gaze-Based Response Rewards for Large Language Models. |
| Jul 20, 2024 | Attended the EEML Summer School in Novi Sad, Serbia. |
| Jul 12, 2024 | Invited talk Brain-Computer Interfaces for Large Language Models at the WINC Workshop and Nanonetworking Day at Universitat Politècnica de Catalunya (UPC). |
| May 10, 2024 | Invited talk Unveiling LLM: What Lies Behind and How to Leverage Them at the Innovation Week held at Campus 42. |
| May 01, 2024 | Invited talk Brain-Computer Interfaces for Large Language Models at the the International Student Workshop of TelecoRenta from CTTC. |
| May 01, 2023 | Started PhD at the Universitat Politècnica de Catalunya (UPC) in Barcelona, Spain. |