Profiles2023-2026
Mariya Toneva
Max Planck Institute for Software Systems
11Papers
11Last author
16Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers11
- When Language Models Lose Their Mind: The Consequences of Brain MisalignmentAuthor 2 of 2ICLR 2026 · 3 citations
- Tracking Equivalent Mechanistic Interpretations Across Neural NetworksAuthor 2 of 2ICLR 2026 · 1 citation
- Fine-grained Analysis of Brain-LLM Alignment through Input AttributionAuthor 3 of 3ICML 2026
- Brain-tuning Improves Generalizability and Efficiency of Brain Alignment in Speech ModelsAuthor 2 of 2NeurIPS 2025 · 7 citations
- Hints Help Finding and Fixing Bugs Differently in Python and Text-Based Program RepresentationsAuthor 5 of 5ICSE 2025 · 1 citation
- Large Language Models as Model Organisms for Human Associative LearningAuthor 3 of 3NeurIPS 2025 · 1 citation
- Improving Semantic Understanding in Speech Language Models via Brain-tuningAuthor 3 of 3ICLR 2025
- Language models and brains align due to more than next-word prediction and word-level informationAuthor 2 of 2EMNLP 2024 · 2 citations
- Speech language models lack important brain-relevant semanticsAuthor 4 of 4ACL 2024
- Joint processing of linguistic properties in brains and language modelsAuthor 3 of 3NeurIPS 2023 · 64 citations
- Training language models to summarize narratives improves brain alignmentAuthor 2 of 2ICLR 2023 · 11 citations
