# CogBlender: Towards Continuous Cognitive Intervention in Text-to-Image Generation

arXiv: https://arxiv.org/abs/2603.09286 · HTML: https://mlsanity.com/paper/2603.09286/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 43 references that are in the map.
- First posted on arXiv 10 Mar 2026.

## Builds on (most cited first, 24 of 24)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2308.06721/) (2023)
- [T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.08453/) (2023)
- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022)
- [GANalyze: Toward Visual Definitions of Cognitive Image Properties](https://mlsanity.com/paper/1906.10112/) (2019)
- [EmoGen: Emotional Image Content Generation with Text-to-Image Diffusion Models](https://mlsanity.com/paper/2401.04608/) (2024)
- [EmotiCrafter: Text-to-Emotional-Image Generation based on Valence-Arousal Model](https://mlsanity.com/paper/2501.05710/) (2025)
- [FindingEmo: An Image Dataset for Emotion Recognition in the Wild](https://mlsanity.com/paper/2402.01355/) (2024)
- [UniEmo: Unifying Emotional Understanding and Generation with Learnable Expert Queries](https://mlsanity.com/paper/2507.23372/) (2025)
- [Memorability: An image-computable measure of information utility](https://mlsanity.com/paper/2104.00805/) (2021)
- [EmoFeedback2: Reinforcement of Continuous Emotional Image Generation via LVLM-based Reward and Textual Feedback](https://mlsanity.com/paper/2511.19982/) (2025)
- [EmoCtrl: Controllable Emotional Image Content Generation](https://mlsanity.com/paper/2512.22437/) (2025)
- [MUSE: Manipulating Unified Framework for Synthesizing Emotions in Images via Test-Time Optimization](https://mlsanity.com/paper/2511.21051/) (2025)
- [Emotion-Director: Bridging Affective Shortcut in Emotion-Oriented Image Generation](https://mlsanity.com/paper/2512.19479/) (2025)
- [VisRecall: Quantifying Information Visualisation Recallability via Question Answering](https://mlsanity.com/paper/2112.15217/) (2021)
- [From Pixels to Feelings: Aligning MLLMs with Human Cognitive Perception of Images](https://mlsanity.com/paper/2511.22805/) (2025)

## Built on by (most cited first, 1 of 1)

- [Amplify What You Gaze At: Target Saliency Boosting in Text-to-Image Generation](https://mlsanity.com/paper/2609.30733/) (2026)

## Abstract (arXiv)

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.