From Pixels to Feelings: Aligning MLLMs with Human Cognitive Perception of Images
Abstract
CogIP-Bench evaluates MLLMs on image cognitive properties, revealing a gap that post-training can bridge, enhancing human-like perception and improving creative tasks.
While Multimodal Large Language Models (MLLMs) are adept at answering what is in an image-identifying objects and describing scenes-they often lack the ability to understand how an image feels to a human observer. This gap is most evident when considering subjective cognitive properties, such as what makes an image memorable, funny, aesthetically pleasing, or emotionally evocative. To systematically address this challenge, we introduce CogIP-Bench, a comprehensive benchmark for evaluating MLLMs on such image cognitive properties. Our evaluation reveals a significant gap: current models are poorly aligned with human perception of these nuanced properties. We then demonstrate that a post-training phase can effectively bridge this gap, significantly enhancing the model's alignment with human judgments. Furthermore, we show that this learned cognitive alignment is not merely predictive but also transferable to downstream creative tasks. By integrating our cognitively-aligned MLLM into an image generation pipeline, we can guide the synthesis process to produce images that better embody desired traits, such as being more memorable or visually appealing. Our work provides a benchmark to measure this human-like perception, a post-training pipeline to enhance it, and a demonstration that this alignment unlocks more human-centric AI.
Community
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Latent Sketchpad: Sketching Visual Thoughts to Elicit Multimodal Reasoning in MLLMs (2025)
- BLINK-Twice: You see, but do you observe? A Reasoning Benchmark on Visual Perception (2025)
- Zooming into Comics: Region-Aware RL Improves Fine-Grained Comic Understanding in Vision-Language Models (2025)
- Personalized Reward Modeling for Text-to-Image Generation (2025)
- AesTest: Measuring Aesthetic Intelligence from Perception to Production (2025)
- Emu3.5: Native Multimodal Models are World Learners (2025)
- TRAVL: A Recipe for Making Video-Language Models Better Judges of Physics Implausibility (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper