From Pixels to Feelings: Aligning MLLMs with Human Cognitive Perception of Images
By: Yiming Chen , Junlin Han , Tianyi Bai and more
Potential Business Impact:
Makes AI understand how pictures make people feel.
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.
Similar Papers
What Makes a Good Generated Image? Investigating Human and Multimodal LLM Image Preference Alignment
CV and Pattern Recognition
Helps AI understand what makes pictures look good.
Do Multimodal LLMs See Sentiment?
CV and Pattern Recognition
Helps computers understand feelings in pictures.
Multimodal LLM Augmented Reasoning for Interpretable Visual Perception Analysis
Human-Computer Interaction
Helps computers understand pictures like people do.