The paper introduces a semantic-first temporal scheduling strategy for flow-matching models in affect-controlled image generation. By using deterministic ODE sampling during the high-noise phase and restricting stochastic SDE exploration and group relative policy optimization (GRPO) to a late window, the method improves prompt faithfulness, affect accuracy, and human-rated semantic preservation. Experiments on FLUX.1-dev and SD3.5-Medium demonstrate reduced subject drift, faster GRPO training, and a clear trade-off between affect-semantic quality and computational cost, establishing denoising time as a practical control dimension for reliable emotional image generation.
By Zhenxuan Wang
arXiv:2609.12830v1 Announce Type: new
Abstract: Continuous emotion control in text-to-image generation requires a model to improve affective alignment without changing the objects, layout, or scene d...
By Jisheng Dang, Zhenxuan Wang, Bin Li, Ronghao Lin, Bin Hu, Tat-Seng Chua
arXiv:2607. 10165v1 Announce Type: cross Abstract: Emotion-aware artistic image generation requires an image to match the input prompt, follow the specified artistic style, and convey the target emotion.
By Dexiang Hong, Yijie Guo, Weidong Chen, Xinyan Liu, Zixuan Zou, Zhendong Mao, Yongdong Zhang
EmoReward is a self‑evolving reward calibration framework for emotional video generation using reinforcement learning. It distills reliability from reward traces during training to adaptively weight multiple reward primitives—such as visual quality, motion, and text alignment—based on emotional evidence. The method employs grounding cues, heterogeneous signal primitives, reflective reward gating, and a RewardMemory module to calibrate fusion weights across training runs, demonstrating improvements on HunyuanVideo 1.5 and transferability to SD 3.5 and FLUX.
By Mingzhe Zheng, Yue Wu, Jing Tan, Chang Zou, Dengyang Jiang, Zeyue Tian, Xuanhua He, Ryan Xu, Yunyang Ge, Sihui Ji, Yunlong Lin, Kaihang Pan, Hongru Yan, Sixiang Chen, Dianyi Wang, Julian Zhang, Weijie Kong, Changlin Li, Lanqing Guo, Zhao Zhong, Qifeng Chen, Harry Yang
Group Relative Policy Optimization (GRPO) has advanced generative model post-training in verifiable domains such as code and mathematics, but evaluating video quality, especially emotional expression,...
AffectDelta is a new image editing framework that moves beyond single emotion labels by modeling edits as transitions between eight‑dimensional emotion distributions. It uses a frozen Emotion Distribution Predictor to estimate the source state and a signed difference vector to encode the desired change, which is then translated into context‑dependent semantic and appearance modifications via a transition encoder and a diffusion backbone. The authors introduce AffectPair‑249K, a dataset of 248,841 source‑target pairs covering both cross‑category and within‑category transitions, and show that AffectDelta outperforms six baselines in affective alignment and content preservation.
By Xingzu Zhan, Lin Gu, Ruogu Fang
AffectDelta is a new image editing framework that moves beyond single emotion labels by modeling edits as transitions between eight‑dimensional emotion distributions. It uses a frozen Emotion Distribution Predictor to estimate the source image’s affective state and encodes the signed difference to guide a diffusion backbone that applies context‑dependent semantic and appearance changes. The authors created a large AffectPair‑249K dataset of source‑target pairs and show that AffectDelta outperforms six baselines in both affective alignment and content preservation, with ablation studies supporting their design choices.
arXiv:2606. 13247v1 Announce Type: new Abstract: Text-to-image diffusion models have achieved impressive results in synthesizing high-quality images from natural language prompts.
By Emna Othmen, Mohamed Yassine Landolsi, Lotfi Ben Romdhane
The paper introduces ROI‑ReFT, a method for emotional image editing that leverages neural representations from fMRI encoding models to guide visual changes while preserving content. By combining source visual responses with predicted affective changes, the approach achieves high target‑emotion accuracy (91.75%) and joint success (83.25%) on a curated set of 400 editing requests. The authors plan to release their code and dataset publicly.
By Xingzu Zhan, Lin Gu, Ruogu Fang
CAST introduces a reinforcement‑learning fine‑tuning framework for diffusion models that addresses three key limitations: it automatically selects the denoising window based on each model’s trajectory, decomposes prompts into verifiable semantic atoms via Causal Scene Graphs, and applies atom‑level rewards spatially weighted in the policy objective. The method is applied to FLUX.2‑dev and Qwen‑Image‑2512, yielding up to 3.07× improvement on the hardest GenEval 2 prompts compared with Flow‑GRPO while also enhancing overall generation quality.
By Shu Yu, Chaochao Lu
arXiv:2606.04457v2 Announce Type: replace
Abstract: Incorporating visual semantic representations as an intermediate step before image generation can reduce the modeling difficulty between text and i...
By Liyu Jia, Fengda Zhang, Jiachun Pan, Kesen Zhao, Saining Zhang, Wang Lin, Weijia Wu, Yue Liao, Aojun Zhou, Hanwang Zhang
arXiv:2606. 17979v1 Announce Type: new Abstract: Existing RL post-training methods for text-to-image generation usually convert the final-image reward into a single scalar advantage and apply it with the same strength to the entire generative trajectory.
By Jinjie Shen, Wei Deng, Xian Hu, Daiguo Zhou, Jian Luan