← Back to all news
arXiv Computer Vision By Zhenxuan Wang

Semantic-First: Temporal Scheduling in Flow Matching for Reliable Emotional Image Generation

Read the original on arXiv Computer Vision →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv AI
2d ago

EmoReward: Self-Evolving Reward Calibration for Emotional Video Generation RL

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
agentsdiffusionreinforcement-learningsafety
More like this →
arXiv AI
Oct 1

CAST: Causal Advantage-Structured Training with Spatially Grounded Compositional Rewards for Diffusion Models

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
diffusionreinforcement-learningfine-tuningbenchmarks
More like this →
arXiv AI
Sep 30

PreviewDiff: Multimodal Critic-Guided Search over Diffusion Latents

PreviewDiff is a test‑time search method that uses multimodal critics to guide diffusion model sampling. By decoding partial previews at selected denoising checkpoints, scoring them with a multimodal judge, and branching over semantic prompt edits, it allows the generation process to be edited and rerouted before completion. The approach consistently outperforms budget‑matched Best‑of‑N sampling and scalar‑search baselines on image and video benchmarks, with early interventions and wider search yielding the biggest gains.

By Vighnesh Subramaniam, Boris Katz, Brian Cheung, Chun-Liang Li, Tomas Pfister, Yale Song
diffusionmultimodalbenchmarks
More like this →