23 citations · 23 across the 4 of their papers we have counts for
4 papers
Reward Valuation in Large Language Models: Causal Induction of Anhedonia
Melika Honarmand, Samin Mahdipour Aghabagher, Martin Schrimpf
Recent frontier models mimic complex aspects of human cognition. Here we ask whether this alignment extends into reward valuation, which we assess in a mechanistic framework. Speci…
Inducing Dyslexia in Vision Language Models
Melika Honarmand, Ayati Sharma, Badr AlKhamissi +2
Dyslexia, a neurodevelopmental disorder characterized by persistent reading difficulties, is often linked to reduced activity of the visual word form area (VWFA) in the ventral occ…
Fast and flexible long-range models for atomistic machine learning
Philip Loche, Kevin K. Huguenin-Dumittan, Melika Honarmand +5
Most atomistic machine learning (ML) models rely on a locality ansatz, and decompose the energy into a sum of short-ranged, atom-centered contributions. This leads to clear limitat…
An Assessment of PC-mer's Performance in Alignment-Free Phylogenetic Tree Construction
Saeedeh Akbari Rokn Abadi, Melika Honarmand, Ali Hajialinaghi +1
Background: Sequence comparison is essential in bioinformatics, serving various purposes such as taxonomy, functional inference, and drug discovery. The traditional method of align…