Entity · model

LLaVA 1.6

modelactiveprovisionalllava-1-6-f38fceac·1 events·first seen Jul 14, 2026

Aliases: LLaVA 1.6

Co-occurring entities

Lesioned Multimodal Language Models Reproduce Aphasic Picture-Naming Patterns Philadelphia Naming Test

More like this (12)

LLaVA-v1.5-Instruct LLaVA-1.5-7B LLaVA-OneVision-1.5-8B LLaVA-1.5-13B LLaDA-1.5-8B LLaVA-665K LLaDA LLaVA OneVision 72B LabVLA Leanstral 1.5 TinyLlama-1.1B Laguna S 2.1

Recent events (1)

5arXiv · cs.CL·Jul 14, 2026·source ↗

Lesioned multimodal LLM reproduces individual aphasic naming error profiles at high fidelity

Researchers applied controlled perturbations (layer-targeted noise) to LLaVA 1.6 and found that the resulting error distributions in picture-naming tasks closely match those of 278 persons with post-stroke aphasia on the Philadelphia Naming Test. Six of seven clinical error categories emerged at clinically comparable proportions, and perturbation configurations reproducing individual patient error profiles were found for 97.8% of participants across six categories and 79.5% across all seven. Monte Carlo baselines confirm the matching reflects genuine joint inter-category structure rather than chance. The work proposes language models as 'digital twins' for aphasia simulation and opens a quantitative framework for clinical cognitive modeling.

Evaluation and Benchmarking Multimodal Progress Lesioned Multimodal Language Models Reproduce Aphasic Picture-Naming Patterns Philadelphia Naming Test LLaVA 1.6