arXiv AI July 21, 2026 By Anna Bavaresco, Ina Klari\'c, Raquel Fern\'andez, Marie-Francine Moens

What Makes Linguistic Representations Good Models of High-Level Visual Perception in the Human Brain?

arXiv:2607. 16214v1 Announce Type: cross Abstract: Image descriptions represented with language models (LMs) predict human brain responses to naturalistic images in high-level visual regions, but the factors driving this predictivity remain unclear.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jun 16

Attention, not scale, drives human-AI alignment in multimodal language prediction

arXiv:2308. 06035v4 Announce Type: replace Abstract: Humans routinely draw on visual context to predict upcoming words.

By Viktor Kewenig, Andrew Lampinen, Samuel A. Nastase, Christopher Edwards, Quitterie Lacome D'Elascombe, Akilles Rechardt, Jeremy I Skipper, Gabriella Vigliocco

llms multimodal benchmarks safety

arXiv AI

Jun 12

LatentLens: Revealing Highly Interpretable Visual Tokens in LLMs

arXiv:2602. 00462v4 Announce Type: replace-cross Abstract: Transforming a large language model (LLM) into a vision-language model (VLM) can be achieved by mapping the visual tokens from a vision encoder into the embedding space of an LLM.

By Benno Krojer, Shravan Nayak, Oscar Ma\~nas, Vaibhav Adlakha, Desmond Elliott, Siva Reddy, Marius Mosbach

llms rag multimodal safety

arXiv AI

Sep 2

Uncovering the Computational Ingredients of Human-Like Representations in LLMs

arXiv:2510.01030v2 Announce Type: replace Abstract: The human ability to translate diverse perceptual and linguistic inputs into structured behavior has been thought to rest on learning robust repres...

By Zach Studdiford, Timothy T. Rogers, Kushin Mukherjee, Siddharth Suresh

llms fine-tuning multimodal benchmarks safety

arXiv AI

Jul 13

Evolution of Accuracy and Visual-Cognitive Errors in a Decade of Vision-Language AI Models

arXiv:2607. 09654v1 Announce Type: cross Abstract: Vision language models (VLMs) have made remarkable progress in visual reasoning during the last decade.

By Shravan Murlidaran, Miguel P. Eckstein

llms computer-vision multimodal benchmarks safety

arXiv AI

Jun 11

Brain-IT-VQA: From Brain Signals to Answers

arXiv:2605. 29588v2 Announce Type: replace-cross Abstract: Decoding visual content from fMRI signals recorded while a person views images, and specifically answering questions about the seen images, is a long-standing challenge.

By Roman Beliy, Matias Cosarinsky, Oliver Heinimann, Navve Wasserman, Michal Irani

llms nlp benchmarks

arXiv AI

Sep 7

Cross-Task Generalization Between Understanding and Generation in Unified Vision-Language Models: A Controlled Study

The study investigates how unified vision‑language models (VLMs) can simultaneously support visual understanding and generation. Using controlled benchmarks (SmartWatch and modified CelebA) that pair VQA, captioning, and text‑to‑image tasks, the authors evaluate several LLM‑based architectures built on SigLIP and VQ‑VAE visual spaces. Results show that mixed training can improve both understanding and generation, but the gains depend on how well the visual input and output spaces are aligned; misaligned or distorted visual spaces can weaken or reverse these benefits. The paper also demonstrates that balancing data across tasks and controlling attribute frequencies can help recover underrepresented visual concepts, and that the transfer is driven more by the base language model’s learned relationships than by visual adapters.

By Jihai Zhang, Tianle Li, Linjie Li, Zhengyuan Yang, Yu Cheng

llms diffusion multimodal benchmarks

One email a morning, machine-written

Related stories

Attention, not scale, drives human-AI alignment in multimodal language prediction

LatentLens: Revealing Highly Interpretable Visual Tokens in LLMs

Uncovering the Computational Ingredients of Human-Like Representations in LLMs

Evolution of Accuracy and Visual-Cognitive Errors in a Decade of Vision-Language AI Models

Brain-IT-VQA: From Brain Signals to Answers

Cross-Task Generalization Between Understanding and Generation in Unified Vision-Language Models: A Controlled Study