D2D: Detector-to-Differentiable Critic for Improved Numeracy in Text-to-Image Generation
cs.CV
Submitted: 2025-10-22
Updated: 2026-11-12
Terminology
Sources
- CFG++: Manifold-constrained Classifier Free Guidance for Diffusion Models
- Learning to Count Anything: Reference-less Class-agnostic Counting with Weak Supervision
- Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis
- Detection-Driven Object Count Optimization for Text-to-Image Diffusion Models
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