arXiv Machine Learning July 13, 2026 By Ahmed Oumar El-Shangiti, Abzal Nurgazy, Hilal AlQuabeh, Nikolai Rozanov, Kentaro Inui

The Count Is There, but Misaligned: Understanding and Correcting Counting Failures in VLMs

Read the original on arXiv Machine Learning →

arXiv:2607. 09544v1 Announce Type: cross Abstract: Despite strong performance on many multimodal tasks, vision-language models (VLMs) still struggle with basic object counting.

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 Machine Learning.

arXiv AI

Aug 7

HoloCount: A Holistic Visual Counting Benchmark for MLLMs

arXiv:2607. 06420v1 Announce Type: cross Abstract: Visual counting is a fundamental pillar of multimodal intelligence, requiring a seamless integration of fine-grained grounding and spatial reasoning.

By Jinhong Deng, Limeng Qiao, Guanglu Wan

llms multimodal benchmarks safety

arXiv AI

Sep 16

Same Answer, Different Representations: Hidden instability in VLMs

arXiv:2602.06652v2 Announce Type: replace Abstract: The robustness of Vision Language Models (VLMs) is commonly assessed through output-level invariance, implicitly assuming that stable predictions r...

By Farooq Ahmad Wani, Alessandro Suglia, Rohit Saxena, Aryo Pradipta Gema, Wai-Chung Kwan, Fazl Barez, Maria Sofia Bucarelli, Fabrizio Silvestri, Pasquale Minervini

llms rag multimodal benchmarks safety

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.

By Xingzhou Pang, Yifan Hou, Junling Wang, Mrinmaya Sachan

llms multimodal benchmarks

arXiv Computer Vision

4d ago

Why MLLMs Struggle to Count: Overcoming Individuation and Aggregation Bottlenecks with ConvStack

arXiv:2609.37096v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) consistently struggle with fine-grained visual counting, yet the underlying causes remain poorly understood. I...

By Liwei Che, Yihao Quan, Sen Fang, Hongyi Wang, Ranjay Krishna, Ruixiang Tang, Vladimir Pavlovic

llms fine-tuning multimodal benchmarks

arXiv AI

Sep 21

DiaVLo: Diagnosing Behaviours of Vision-Language Models

DiaVLo is a diagnostic framework for vision‑language models (VLMs) that uses human curation and VLM generation to create specifications of desired and observed behaviours, revealing potential misalignments. It also offers causal estimates to pinpoint the most influential concepts driving VLM behaviour. Experiments on several open‑source VLMs under classification and generation tasks show that DiaVLo’s behaviour labels correlate with model performance and illuminate how VLMs perceive, organise, and prioritise concepts.

By Lorenzo Corti, Jie Yang

llms multimodal

arXiv AI

Jun 24

Listening makes Vision Clear for VLMs

arXiv:2606. 23763v1 Announce Type: cross Abstract: Recent work typically assesses vision--language consistency using attention distributions of answer-side tokens.

By Yiyang Chen, Yixin Tan, Binrui Shen

safety

One email a morning, machine-written

Related stories

HoloCount: A Holistic Visual Counting Benchmark for MLLMs

Same Answer, Different Representations: Hidden instability in VLMs

Unveiling the Visual Counting Bottleneck in Vision-Language Models

Why MLLMs Struggle to Count: Overcoming Individuation and Aggregation Bottlenecks with ConvStack

DiaVLo: Diagnosing Behaviours of Vision-Language Models

Listening makes Vision Clear for VLMs