arXiv Computation and Language
Human Cognitive Benchmarks Reveal Foundational Visual Gaps in MLLMs
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv AI
Jul 20
An Exam for Active Observers
arXiv:2607. 16165v1 Announce Type: cross Abstract: Human vision is a closed loop: gaze is continuously redirected by intermediate hypotheses rather than a single snapshot.
arXiv Machine Learning
Jul 9
Unveiling the Visual Counting Bottleneck in Vision-Language Models
arXiv:2605. 30170v2 Announce Type: replace-cross Abstract: While Large Vision-Language Models (VLMs) excel at interpolation, they suffer catastrophic failures in systematic generalization, most notably in visual counting.
arXiv AI
Oct 1
VisualNeedle: Benchmarking Active Visual Search in Information-Dense Scenes
arXiv:2605.26380v2 Announce Type: replace-cross Abstract: Frontier multimodal large language models (MLLMs) have been reported to achieve over 90\% accuracy on fine-grained perception benchmarks. How...
arXiv AI
Oct 9
Humanity's Sixth Sense: Benchmarking Intuitive Visual Reasoning in Multimodal Models
The paper introduces Humanity's Sixth Sense (HSS), a benchmark designed to evaluate intuitive visual reasoning in multimodal large language models. HSS covers a wide range of image and video inputs, organizes them under a structured taxonomy, and pairs each with human‑written prompts that probe implicit temporal, spatial, social, and abstract cues that humans can infer at a glance. Current state‑of‑the‑art models, including GPT‑6‑astra, achieve far lower accuracy than humans (53.6 % vs. 93.1 %), highlighting a significant gap in intuitive visual understanding.
arXiv Computer Vision
Sep 4
VKnowU: Evaluating Visual Knowledge Understanding in Multimodal LLMs
VKnowU is a benchmark that tests multimodal large language models (MLLMs) on their grasp of visual knowledge—intuitive, human-like understanding of physical and social principles in videos. The benchmark contains 1,680 questions across 1,249 videos, covering eight core types of visual knowledge, and shows that current state‑of‑the‑art MLLMs still lag behind human performance, especially on world‑centric tasks. To address this gap, the authors release VKnowQA and VideoKnow+, a baseline model that incorporates visual knowledge via a See‑Think‑Answer framework and reinforcement learning, improving performance on VKnowU and related datasets.
arXiv Computer Vision
Aug 27
Seeing or Knowing? Visual Context Sensitivity in Multimodal Large Language Models
The paper investigates why multimodal large language models (MLLMs) struggle with vision‑centric tasks when visual evidence conflicts with pretrained language knowledge. Using image reconstruction and a new WhatIfVis benchmark, the authors show that MLLMs preserve coarse‑grained visual attributes but fail to consistently use them, and that supervised fine‑tuning and activation patching can improve controllability of visual context sensitivity. The study demonstrates that the main bottleneck lies in the models’ inability to reliably regulate their reliance on visual evidence rather than in visual perception itself.