arXiv Machine Learning June 29, 2026 By David Steinmann, Antonia W\"ust, Kristian Kersting, Wolfgang Stammer

COCOLogic-V2: Identifying Logical Inconsistencies via Truly Hard-Negatives

Read the original on arXiv Machine Learning →

arXiv:2606. 28194v1 Announce Type: new Abstract: While interpretable models such as concept bottleneck models (CBMs) and program synthesis methods enable verification of model decisions, their evaluation is typically limited to simple tasks, leaving complex reasoning on real-world images largely unexplored.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Jul 1

Can VLMs Reason Robustly? A Neuro-Symbolic Investigation

arXiv:2603. 23867v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) have been applied to a wide range of reasoning tasks, yet it remains unclear whether they can reason robustly under distribution shifts.

By Weixin Chen, Antonio Vergari, Han Zhao

llms fine-tuning multimodal

arXiv AI

Aug 7

CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generation

arXiv:2603. 08652v2 Announce Type: replace Abstract: Recent advancements in Unified Multimodal Models (UMMs) have significantly advanced text-to-image (T2I) generation, particularly through the integration of Chain-of-Thought (CoT) reasoning.

By Haodong Li, Chunmei Qing, Huanyu Zhang, Dongzhi Jiang, Yihang Zou, Hongbo Peng, Dingming Li, Yuhong Dai, ZePeng Lin, Juanxi Tian, Yi Zhou, Siqi Dai, Jingwei Wu, Pheng-Ann Heng

diffusion multimodal

arXiv AI

Jul 14

Answer-Conditioned Chain-of-Thought Distillation for Few-Shot Industrial Vision with Small VLMs

arXiv:2607. 10666v1 Announce Type: cross Abstract: Deploying AI-based visual inspection in manufacturing is hard because requirements change often, new defect types appear, and large labeled datasets are rarely available.

By Shubham Rao

llms fine-tuning efficiency multimodal

arXiv AI

Jul 13

Explaining is Harder Than Predicting Alone: Evaluating Concept-based Explanations of MLLMs as ICL Visual Classifiers

arXiv:2605. 28215v2 Announce Type: replace Abstract: In-context learning (ICL) enables multimodal large language models (MLLMs) to classify images from a few labelled examples.

By Carmen Quiles-Ram\'irez, Leticia L. Rodr\'iguez, Nicol\'as Martorell, Natalia D\'iaz-Rodr\'iguez

llms multimodal benchmarks

arXiv AI

Jun 26

From Hallucination to Grounding: Diagnosing Visual Spatial Intelligence via CRISP

arXiv:2606. 26535v1 Announce Type: cross Abstract: Current VLM evaluations often conflate language priors with genuine spatial reasoning.

By Zhixing Li, Yinan Yu

multimodal safety

arXiv AI

Jun 3

Distilling Answer-Set Programming Rules from LLMs for Neurosymbolic Visual Question Answering

arXiv:2606. 03269v1 Announce Type: new Abstract: Visual Question Answering (VQA) is the task of answering questions about images, requiring the integration of multimodal input and reasoning.

By Thomas Eiter, Nelson Higuera Ruiz, Johannes Oetsch

llms nlp efficiency multimodal safety

Related stories

Can VLMs Reason Robustly? A Neuro-Symbolic Investigation

CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generation

Answer-Conditioned Chain-of-Thought Distillation for Few-Shot Industrial Vision with Small VLMs

Explaining is Harder Than Predicting Alone: Evaluating Concept-based Explanations of MLLMs as ICL Visual Classifiers

From Hallucination to Grounding: Diagnosing Visual Spatial Intelligence via CRISP

Distilling Answer-Set Programming Rules from LLMs for Neurosymbolic Visual Question Answering