CCA: collaborative competitive agents for image editing.

Optimal Stepsize for Diffusion Sampling.

Equivariant Image Modeling.

Tokenize Image as a Set.

DesignDiffusion: High-Quality Text-to-Design Image Generation with Diffusion Models.

Several questions of visual generation in 2024.

Improved Noise Schedule for Diffusion Training.

Step-aware Preference Optimization: Aligning Preference with Denoising Performance at Each Step.

Simplified Diffusion Schrödinger Bridge.

Energy Efficiency Maximization in RISs-Assisted UAVs-Based Edge Computing Network Using Deep Reinforcement Learning.

Profit maximization in social networks and non-monotone DR-submodular maximization.

VolumeDiffusion: Flexible Text-to-3D Generation with Efficient Volumetric Encoder.

InstructDiffusion: A Generalist Modeling Interface for Vision Tasks.

Adaptive seeding for profit maximization in social networks.

CLIP Itself is a Strong Fine-tuner: Achieving 85.7% and 88.0% Top-1 Accuracy with ViT-B and ViT-L on ImageNet.

Improved Vector Quantized Diffusion Models.

A constrained two-stage submodular maximization.

k-Submodular maximization with two kinds of constraints.

Interaction-aware influence maximization and iterated sandwich method.

A general method of active friending in different diffusion models in social networks.

Data placement in distributed data centers for improved SLA and network cost.

A fast double greedy algorithm for non-monotone DR-submodular function maximization.

PriorGAN: Real Data Prior for Generative Adversarial Nets.