arXiv:2609.26512v1 Announce Type: new Abstract: Convolutional neural networks (CNNs) and vision transformers are both used to model the human visual system, but whether the two architectures diverge...
arXiv:2605.20337v2 Announce Type: replace Abstract: How interpretable are the features of leading vision models? The question is increasingly pressing as these models move from research benchmarks in...
arXiv:2605. 20448v2 Announce Type: replace-cross Abstract: Vision-language models reliably name objects in a scene, but do they represent the 3D layout those objects inhabit?
arXiv:2605.05556v2 Announce Type: replace Abstract: Artificial neural networks trained on visual tasks develop internal representations resembling those of the primate visual system, a discovery that...
arXiv:2603. 13994v2 Announce Type: replace-cross Abstract: Vision foundation models trained with self-supervised objectives achieve strong performance across diverse tasks and exhibit emergent object segmentation properties.
The paper introduces PCSR-Bench, a benchmark of 84,373 question‑answer pairs derived from 2,600 omnidirectional images across 26 indoor environments, designed to evaluate perspective‑conditioned spatial reasoning (PCSR) in multimodal large language models (MLLMs). It reports a significant perception–reasoning gap, with accuracy dropping from 57.59% on limited field‑of‑view reasoning to as low as 0.64% on open‑ended compositional directional chains. An RL‑based diagnostic study on a 7B‑scale model shows that reward shaping can improve performance to 60.06% on a controlled task, indicating partial plasticity of PCSR capabilities.
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.
arXiv:2605.12413v4 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) show strong visual perception, yet remain limited in reasoning about space under changing viewpoints. We s...
arXiv:2606. 24716v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) are increasingly used to extract interpretable concepts from vision and vision language models, yet existing evaluation methods largely rely on proxy metrics or qualitative inspection rather than measuring semantic correspondence.
arXiv:2607. 00491v1 Announce Type: cross Abstract: Benchmarks for vision-language models (VLMs) mostly test observational spatial reasoning: models describe relations already visible in the input.
The study explores how to fine‑tune visual brain encoding models so that their internal representations better match individual human perceptual similarity judgments. Using similarity data from 100 images collected from eight participants in the Natural Scenes Dataset, the authors adapted a generic similarity model (DreamSim) to create personalized perceptual similarity models for each subject. They then fine‑tuned each participant’s baseline encoder with either generic or personalized similarity information, finding that models trained with personalized judgments were most aligned with human perceptual similarity and preserved inter‑subject correlations of those judgments.
arXiv:2610.28059v1 Announce Type: cross Abstract: Concept Bottleneck Models (CBMs) promise predictions that humans can inspect and correct through concepts such as "curved beak". Yet on CUB-200-2011,...