activity
20242026
collaborators

10 papers

cs.CL2026

RABBiT: Rapidly adaptive BOLD foundation model via brain-tuning for accurate zero-shot and few-shot prediction of speech-elicited responses in the brain

Omer Moussa, Mariya Toneva

Language understanding in the brain is context-dependent, varying across experimental stimuli and individuals, which makes it difficult to build computational models that generaliz…

cs.HC2026

Neural Signatures of Programming Expertise: Classifying Programmer Skill Levels Using EEG Data

Maurice Rekrut, Mahima Mahabaleshwar Acharya, Taisiia Ulianova +5

Accurately assessing a programmer's skill level is critical for hiring, team composition, and performance evaluation in the software industry. Conventional methods, such as coding…

cs.AI2026

Temporal Context Reinstatement Drives Episodic-Like Order Memory in Long-Context Language Models

Mathis Pink, Vy Ai Vo, Qinyuan Wu +7

Human episodic memory supports the retrieval of experiences that unfold over extended timescales, yet the computational mechanisms underlying this ability remain debated due to the…

cs.LG2026

Tracking Equivalent Mechanistic Interpretations Across Neural Networks

Alan Sun, Mariya Toneva

Mechanistic interpretability (MI) is an emerging framework for interpreting neural networks. Given a task and model, MI aims to discover a succinct algorithmic process, an interpre…

cs.CL2026

When Language Models Lose Their Mind: The Consequences of Brain Misalignment

Gabriele Merlin, Mariya Toneva

While brain-aligned large language models (LLMs) have garnered attention for their potential as cognitive models and for potential for enhanced safety and trustworthiness in AI, th…

cs.CL2025

Fine-grained Analysis of Brain-LLM Alignment through Input Attribution

Michela Proietti, Roberto Capobianco, Mariya Toneva

Understanding the alignment between large language models (LLMs) and human brain activity can reveal computational principles underlying language processing. We introduce a fine-gr…