EPIC: Efficient Predicate-Guided Inference-Time Control for Compositional Text-to-Image Generation
cs.CV, cs.LG
Submitted: 2026-05-12
Updated: 2026-11-04
Terminology
Sources
- Qwen3-VL Technical Report
- Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generation
- Benchmarking Spatial Relationships in Text-to-Image Generation
- RAISE: Requirement-Adaptive Evolutionary Refinement for Training-Free Text-to-Image Alignment
- GenEval 2: Addressing Benchmark Drift in Text-to-Image Evaluation
- LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models
- Flow Matching for Generative Modeling
- Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
- Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps
- GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
- A General Framework for Inference-time Scaling and Steering of Diffusion Models
- Denoising Diffusion Implicit Models
- Score-Based Generative Modeling through Stochastic Differential Equations
- SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
- Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis
- SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer
- Inference-time Scaling of Diffusion Models through Classical Search
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs