ORCA: Hunting Compositional Failures in Text-to-Image Diffusion

arXiv:2610.09841 · cs.CV, cs.LG · Submitted 2026-10-07 · Read on arXiv

cs.CV, cs.LG

Submitted: 2026-10-07

Updated: 2026-10-07

Terminology

• Alignment — 29× in this paper · explained in 1 episode
• Diffusion Model — 19× in this paper · explained in 8 episodes
• Transformer — 11× in this paper · explained in 2 episodes
• Ablation — 7× in this paper · explained in 1 episode
• Core — 6× in this paper · explained in 2 episodes
• Diffusion Models — 6× in this paper · explained in 6 episodes
• Embeddings — 5× in this paper · explained in 2 episodes
• Generative Model — 5× in this paper · explained in 2 episodes
• Grounding — 5× in this paper · explained in 3 episodes
• Accuracy — 4× in this paper · explained in 1 episode
• Benchmark — 4× in this paper · explained in 2 episodes
• Fidelity — 4× in this paper · explained in 2 episodes
• Generative Models — 4× in this paper · explained in 2 episodes
• Rectified Flow — 3× in this paper · explained in 3 episodes
• Adam — 2× in this paper · explained in 2 episodes
• Cosine Similarity — 2× in this paper · explained in 3 episodes
• Institutional Review Board — 2× in this paper
• Latent Space — 2× in this paper · explained in 7 episodes
• Loss Function — 2× in this paper · explained in 2 episodes
• Scaling Laws — 2× in this paper · explained in 4 episodes
• Self-Supervised Learning — 2× in this paper · explained in 8 episodes
• Entanglement — 1× in this paper · explained in 4 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Generative Modeling — 1× in this paper · explained in 3 episodes
• Gradient Flow — 1× in this paper · explained in 2 episodes
• Latent Diffusion Model — 1× in this paper · explained in 2 episodes
• Latent Diffusion Models — 1× in this paper · explained in 2 episodes
• Nash Equilibrium — 1× in this paper · explained in 2 episodes
• Reconstruction Error — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Score Function — 1× in this paper · explained in 4 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Transfer Learning — 1× in this paper · explained in 10 episodes
• Visual Grounding — 1× in this paper · explained in 2 episodes

Sources

• CompAlign: Improving Compositional Text-to-Image Generation with a Complex Benchmark and Fine-Grained Feedback
• Infinity and Beyond: Compositional Alignment in VAR and Diffusion T2I Models
• Improving Compositional Attribute Binding in Text-to-Image Generative Models via Enhanced Text Embeddings
• DINOv2: Learning Robust Visual Features without Supervision
• Flow Matching for Generative Modeling

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models