AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Beyond Counting: Evaluating Abstract and Emotional Reasoning in Vision-Language Models

Yuan Zhou, Yan Zhang, Jianlong Chang, Xin Gu, Ying Wang, Kun Ding, Guangwen Yang, Shiming Xiang

AAAI 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Chain-of-thought multimodal reasoning · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Introduces EmojiGrid, a diagnostic benchmark probing fine-grained, higher-order, abstract and emotional reasoning in vision-language models.

Problem

Existing VLM benchmarks focus on coarse-grained object recognition or simple relational reasoning, leaving fine-grained and higher-order (abstract, emotional) reasoning largely unexamined.

Approach

A diagnostic benchmark (EmojiGrid) built around emoji-based grid visual stimuli to test abstract and emotional reasoning in VLMs; details beyond the abstract are not available.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
move from perception tasks to abstraction tasksGemini-2.5-Pro · EmojiGridaccuracy (%): Perception 71.23 -> Abstraction 75.46 (Counting 60.04)Hurt
scale up model size within a family (Qwen-VL2.5 7B to 72B)Qwen-VL2.5 · EmojiGrid overallaccuracy (%): 38.62 -> 51.02Improved
scale up Gemma3 from 4B to 27BGemma3 · EmojiGrid overallaccuracy (%): 33.93 -> 40.82Improved
scale up Intern-VL3 from 8B to 78BIntern-VL3 · EmojiGrid overallaccuracy (%): 44.14 -> 47.09 (14B 46.64, 38B 46.74)Mixed
use reasoning-enhanced model instead of standard model (Gemini-2.5-Pro vs GPT-4o)closed-source VLMs · EmojiGrid overallaccuracy (%): 49.98 -> 73.37Improved
reasoning-enhanced open model QVQ-72B-Preview versus non-reasoning Qwen-VL2.5-72B72B open VLMs · EmojiGrid overallaccuracy (%): 51.02 -> 34.83Hurt
longer reasoning outputreasoning VLMs · EmojiGrid-liteaccuracy vs token countNo clear effect
Chinese instead of English questionsmost VLMs · EmojiGrid language splitaccuracyHurt

Experimental setup

Benchmarks: EmojiGrid

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy