Diffusion models have emerged as state-of-the-art generative methods, particularly excelling in conditional tasks such as prompt-driven image synthesis. While recent research emphasizes the pivotal role of noise seeds in enhancing text-image alignment and generating human-preferred outputs,these works predominantly rely on random Gaussian noise or heuristic local adjustments, , overlooking the potential of global optimization trategies to systematically improve generation quality. To bridge this gap, we propose Seed Optimization based on Evolution (SOE), a hybrid framework that integrates global evolutionary search with local semantic refinement. The global evolutionary stage conducts seed selection by jointly optimizing text-image alignment (via CLIP-Score) and human preference estimation (via ImageReward), while the local stage employs diffusion inversion to inject conditional semantics into the noise seed. Together, these components constitute a model-agnostic, training-free optimization framework for conditional diffusion models. Extensive experiments across various diffusion models demonstrate that SOE consistently improves semantic fidelity and visual quality, highlighting its generalizability and potential as a plug-and-play enhancement for generative diffusion pipelines.

Multi-task learning (MTL) is effective in solving multiple related tasks simultaneously by sharing knowledge. However, a key challenge hindering its applications is the task interference problem where different tasks compete with each other, leading to the gradients conflicts during optimization and suffering from negative transfer. One thread is to manipulate task gradients by adjusting conflicting directions, ignoring architecture learning. Another thread is to learn architectures by generating task-exclusive modules, ignoring all-task balances. We address the problem by proposing a novel Multi-task Architecture learning model via Multi-Objective (MAMO) optimization. It achieves the goal in two steps. First, for the competing tasks detected during architecture learning, MAMO automatically generates a new module of gradient mediative kernel (GMK). Second, MAMO finds a Pareto optimal solution that balances all tasks during model parameter learning. MAMO outperforms various MTL baselines on benchmarks with an effective model size. It is model-agnostic and can be integrated into other SOTA methods to promote their performance. Extensive ablation study is conducted to understand the working of MAMO.