arXiv Machine Learning
TPSO: Training-Free Diverse Image Generation via Semantic Prompt Embedding Optimization
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Computer Vision
Sep 3
Diversifying Long Prompt Image Generation through Structured Prompt Embedding Space Sampling
The paper investigates how long, richly detailed prompts cause modern text-to-image models to lose diversity, even when many visual aspects are unspecified. It introduces PromptMoG, a training‑free method that samples prompt embeddings from a Mixture‑of‑Gaussians distribution to restore diversity while preserving semantic fidelity. The authors also present LPD‑Bench, a benchmark for evaluating fidelity and diversity under long, semantically dense prompts, and demonstrate PromptMoG’s effectiveness on four large diffusion models.
arXiv AI
4d ago
Controllable Diverse Sampling through Pullback Directions
arXiv:2610.14294v1 Announce Type: new Abstract: Conditional diffusion models can generate high-quality images that align closely with a given prompt. However, samples generated from different random...
arXiv AI
Jun 4
On-the-fly Repulsion in the Contextual Space for Rich Diversity in Diffusion Transformers
arXiv:2603. 28762v2 Announce Type: replace-cross Abstract: Modern Text-to-Image (T2I) diffusion models have achieved remarkable semantic alignment, yet they often suffer from a significant lack of variety, converging on a narrow set of visual solutions for any given prompt.
arXiv Computer Vision
Sep 2
DiverseVAR: Balancing Diversity and Quality of Next-Scale Visual Autoregressive Models
arXiv:2511.21415v2 Announce Type: replace Abstract: We introduce DiverseVAR, a framework that enhances the diversity of text-conditioned visual autoregressive models (VAR) at test time without requir...
arXiv Computation and Language
Aug 28
Visual Information-Guided Parallel Decoding for Diffusion Multimodal Large Language Models
Visual Information-Guided Parallel Decoding for Diffusion Multimodal Large Language Models introduces the VIG‑Sampler, a method that prioritizes tokens for decoding based on their attention to image tokens and penalizes redundancy in image‑attention distributions. The approach aims to improve the quality of multimodal generation by selecting more informative tokens during diffusion decoding. Experiments on seven captioning and VQA benchmarks with three open‑source dMLLMs show that VIG‑Sampler outperforms the Info‑Gain Sampler by an average of 19.3 CIDEr points and achieves better COCO Caption results using only half as many decoding steps.
arXiv AI
4d ago
Uncovering the Generative Landscape of Diffusion Models: A Spectral-Guided Quality-Diversity Diffusion Framework
arXiv:2610.15724v1 Announce Type: cross Abstract: Denoising Diffusion Probabilistic Models have emerged as powerful generative priors across domains ranging from molecular design to high-resolution i...