Balancing Emotional Alignment and Semantic Consistency in Image Generation via Reinforcement Learning with Valence-Arousal Anchoring

• URL: http://arxiv.org/abs/2609.12830v1
• Date: Fri, 11 Sep 2026 13:24:35 GMT
• Title: Balancing Emotional Alignment and Semantic Consistency in Image Generation via Reinforcement Learning with Valence-Arousal Anchoring
• Abstract summary: Continuous emotion control in text-to-image generation requires a model to improve affective alignment without changing the objects, layout, or scene described by the prompt.<n>Existing supervised emotion-injection methods often optimize feature-space proxies and may therefore exhibit emotion-semantic drift.<n>We address this problem with a flow-matching image-generation framework that combines continuous valence-arousal conditioning, Group Relative Policy Optimization, and a neutral semantic anchor.
• Score: 55.57242007016976
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Continuous emotion control in text-to-image generation requires a model to improve affective alignment without changing the objects, layout, or scene described by the prompt. Existing supervised emotion-injection methods often optimize feature-space proxies and may therefore exhibit emotion-semantic drift, in which stronger emotional conditioning is accompanied by unintended content changes. We address this problem with a flow-matching image-generation framework that combines continuous valence-arousal (VA) conditioning, Group Relative Policy Optimization (GRPO), and a neutral semantic anchor. The deterministic probability-flow ODE is converted into a marginal-preserving SDE, yielding non-degenerate transition densities for trajectory sampling and policy-ratio estimation. A frozen CLIP-based VA regressor supplies a terminal reward measuring the distance between the predicted and target VA coordinates, while an image generated from the same prompt under zero VA conditioning provides a feature-space reference for semantic preservation. A reduced denoising schedule is used for online RL sampling, whereas the original schedule is retained at inference. Experiments on 3,300 prompt-emotion combinations show substantially lower valence and arousal errors than the VA-conditioned baseline and an improved CLIPScore relative to EmotiCrafter, with a measurable trade-off in reference-free image quality. The results support anchor-regularized Flow-GRPO as a practical approach to balancing emotional alignment and semantic consistency in continuous-affect image synthesis.

Related papers

• Improving Visual Representation Alignment Generation with GRPO [51.071351994330605]
  diffusion transformers have demonstrated strong image synthesis capabilities but remain inefficient to train due to weak alignment.<n>We propose VRPO, a reinforcement-based optimization strategy that replaces REPA's static alignment loss with a generative representation policy optimization objective.<n>Our VRPO-driven training seamlessly integrates into diffusion transformers, introducing negligible cost and preserving full compatibility with SiT and DiT architectures.
  arXiv  Detail & Related papers  (2026-05-30T07:21:40Z)
• Where to Refine, When to Stop: Rethinking Redundancy via Latent Discrepancy for Efficient Visual Autoregressive Generation [50.139984798361375]
  We propose a training-free framework that removes redundancy via latent discrepancy.<n> LD-Pruning substantially reduces inference while maintaining high generation quality, achieving up to 2.35x speedup on Infinity-8B.
  arXiv  Detail & Related papers  (2026-05-29T19:34:39Z)
• MoASE++: Mixture of Activation Sparsity Experts with Domain-Adaptive On-policy Distillation for Continual Test Time Adaptation [65.068801413044]
  Continual test-time adaptation adapts a source-pretrained model to non-stationary, unlabeled target streams.<n>We introduce MoASE, a mixture-of-experts that disentangles domain-agnostic structure from domain-specific texture.
  arXiv  Detail & Related papers  (2026-05-18T01:52:12Z)
• CARE: Contrastive Alignment for ADL Recognition from Event-Triggered Sensor Streams [4.3359440506714]
  We propose Contrastive Alignment for ADL Recognition from Event-Triggered Sensor Streams (CARE)<n>CARE is an end-to-end framework that jointly optimize representation learning via Sequence-Image Contrastive Alignment (SICA) and classification via cross-entropy.<n>CARE achieves state-of-the-art performance (89.8% on Milan, 88.9% on Cairo, and 73.3% on Kyoto7) and demonstrates robustness to sensor malfunctions and layout variability.
  arXiv  Detail & Related papers  (2025-10-19T20:11:12Z)
• OSCAR: Orthogonal Stochastic Control for Alignment-Respecting Diversity in Flow Matching [14.664226708184676]
  Flow-based text-to-image models follow deterministic trajectories, forcing users to repeatedly sample to discover diverse modes.<n>We present a training-free, inference-time control mechanism that makes the flow itself diversity-aware.
  arXiv  Detail & Related papers  (2025-10-10T07:07:19Z)
• Multi-Modality Driven LoRA for Adverse Condition Depth Estimation [61.525312117638116]
  We propose Multi-Modality Driven LoRA (MMD-LoRA) for Adverse Condition Depth Estimation.<n>It consists of two core components: Prompt Driven Domain Alignment (PDDA) and Visual-Text Consistent Contrastive Learning (VTCCL)<n>It achieves state-of-the-art performance on the nuScenes and Oxford RobotCar datasets.
  arXiv  Detail & Related papers  (2024-12-28T14:23:58Z)
• Refign: Align and Refine for Adaptation of Semantic Segmentation to Adverse Conditions [78.71745819446176]
  Refign is a generic extension to self-training-based UDA methods which leverages cross-domain correspondences. Refign consists of two steps: (1) aligning the normal-condition image to the corresponding adverse-condition image using an uncertainty-aware dense matching network, and (2) refining the adverse prediction with the normal prediction using an adaptive label correction mechanism. The approach introduces no extra training parameters, minimal computational overhead -- during training only -- and can be used as a drop-in extension to improve any given self-training-based UDA method.
  arXiv  Detail & Related papers  (2022-07-14T11:30:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.