CogBlender: Towards Continuous Cognitive Intervention in Text-to-Image Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917501847207936 |
|---|---|
| author | Dang, Shengqi He, Yi Lei, Jiaying Qian, Ziqing Cao, Nan |
| author_facet | Dang, Shengqi He, Yi Lei, Jiaying Qian, Ziqing Cao, Nan |
| contents | Beyond conveying semantic information, images also possess cognitive properties that elicit specific psychological responses from viewers, such as memory encoding or emotional reactions. Although modern text-to-image (T2I) models generate semantically coherent content effectively, they struggle to control cognitive properties (e.g., valence, memorability) and often fail to align with the user's psychological intent. To bridge the gap, we introduce CogBlender, an algorithm that enables continuous and multi-dimensional intervention on cognitive properties through a novel two-stage approach. First, we construct discrete cognition-aware rewritten prompts-variants of the input prompt that represent distinct extreme cognitive states. Second, we translate these discrete prompts into continuous control signals by interpolating within the velocity-field domain of flow-matching models. By dynamically blending the velocity fields predicted from these prompts according to the target cognitive scores, CogBlender smoothly steers the generative trajectory to realize the desired cognitive properties in the final image. Extensive experiments across four cognitive properties (i.e., valence, arousal, dominance, and memorability) demonstrate that CogBlender achieves effective cognitive intervention. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_09286 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CogBlender: Towards Continuous Cognitive Intervention in Text-to-Image Generation Dang, Shengqi He, Yi Lei, Jiaying Qian, Ziqing Cao, Nan Computer Vision and Pattern Recognition Beyond conveying semantic information, images also possess cognitive properties that elicit specific psychological responses from viewers, such as memory encoding or emotional reactions. Although modern text-to-image (T2I) models generate semantically coherent content effectively, they struggle to control cognitive properties (e.g., valence, memorability) and often fail to align with the user's psychological intent. To bridge the gap, we introduce CogBlender, an algorithm that enables continuous and multi-dimensional intervention on cognitive properties through a novel two-stage approach. First, we construct discrete cognition-aware rewritten prompts-variants of the input prompt that represent distinct extreme cognitive states. Second, we translate these discrete prompts into continuous control signals by interpolating within the velocity-field domain of flow-matching models. By dynamically blending the velocity fields predicted from these prompts according to the target cognitive scores, CogBlender smoothly steers the generative trajectory to realize the desired cognitive properties in the final image. Extensive experiments across four cognitive properties (i.e., valence, arousal, dominance, and memorability) demonstrate that CogBlender achieves effective cognitive intervention. |
| title | CogBlender: Towards Continuous Cognitive Intervention in Text-to-Image Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.09286 |