Entity · paper

Semantic Browsing: Controllable Diversity for Image Generation

paperactivesemantic-browsing-controllable-diversity-for-image-generation-f22d66d6·1 events·first seen Jun 23, 2026

Aliases: Semantic Browsing: Controllable Diversity for Image Generation

More like this (12)

Subject-driven Image Generation Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation StylisticBias: A Few Human Visual Cues Drive Most Social Biases in MLLMs Local Diversity One Polluted Page Is Enough: Evaluating Web Content Pollution in Generative Recommenders On-Policy Self-Distillation with Sampled Demonstrations Reduces Output Diversity Multimodal Augmented Generation via Multimodal Retrieval Workshop Semantic Generative Tuning (SGT)Google Generative AI (Search)Uncertainty-Aware Generation and Decision-Making Under Ambiguity Data Selection Through Iterative Self-Filtering for Vision-Language Settings Supervised Semantic Differential

Recent events (1)

4arXiv · cs.LG·Jun 23, 2026·source ↗

Semantic Browsing: structured diversity for text-to-image generation via text-level variation

Researchers introduce Semantic Browsing, a method for generating structured, navigable galleries of images where each variation corresponds to a meaningful semantic decision rather than stochastic noise. The approach decouples semantic decision-making from pixel generation by inducing diversity at the text level, using a Vision Language Model in an agentic workflow to enumerate interpretable axes of variation. This addresses the well-known mode collapse problem in text-to-image models, where strict prompt adherence reduces output diversity to a single visual interpretation.

Agent and Tool Ecosystem Multimodal Progress Semantic Browsing: Controllable Diversity for Image Generation