AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

MASP: Multi-Aspect Guided Emotion Reasoning with Soft Prompt Tuning In Vision-Language Models

SangEun Lee, Yubeen Lee, Eunil Park, Wonseok Chae

AAAI 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Visual instruction tuning · 1 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.

Proposes MASP, a multi-aspect guided emotion reasoning method for vision-language models that uses soft prompt tuning instead of costly instruction tuning to capture multi-faceted emotional cues in images.

Problem

Emotion understanding from images in vision-language models; existing methods rely on global visual representations that miss nuanced multi-faceted emotional cues and typically use costly instruction-tuning datasets.

Approach

Guides emotion reasoning with multiple emotion-related aspects (local visual cues) and trains soft prompts rather than fine-tuning on instruction data, targeting a cheaper alternative to instruction tuning.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add trained aspect modules to zero-shot VLM without soft prompt (ablation)Qwen2-VL-7B · FIaccuracy (%): 58.16 -> 44.54Hurt
add trained soft prompt to zero-shot VLM (ablation)Qwen2-VL-7B · FIaccuracy (%): 58.16 -> 76.63Improved
add trained soft prompt to zero-shot VLM (ablation)Qwen2-VL-7B · Emotion6accuracy (%): 51.68 -> 70.88Improved
add aspect modules on top of the soft prompt (ablation)MASP · FIaccuracy (%): 76.63 -> 80.06Improved
add aspect modules on top of the soft prompt (ablation)MASP · Emotion6accuracy (%): 70.88 -> 74.75Improved
use random untrained soft prompt with aspect modules instead of trained prompt (ablation)MASP · FIaccuracy (%): 80.06 -> 41.47Hurt
use all six aspect modules instead of one (ablation)MASP · FIaccuracy (%): 78.72 -> 80.06Improved
use both brightness and colorfulness modules instead of one (ablation)MASP · Abstractaccuracy (%): 39.13 -> 45.65Improved
increase soft prompt length from 32 to 128 (ablation)MASP · ArtPhotoaccuracy (%): 53.09 -> 42.59Hurt
reduce soft prompt length from 32 to 8 (ablation)MASP · Emotion6accuracy (%): 74.75 -> 70.20Hurt
use soft prompt tuning instead of QLoRA instruction tuningQwen2-VL-7B · trainable parameterstrainable parameters: 2,523,136 -> 114,688Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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