What Visual Generators Need from Teachers: Rethinking Representation Alignment

arXiv:2609.34732 · cs.CV · Submitted 2026-09-28 · Read on arXiv

cs.CV

Submitted: 2026-09-28

Updated: 2026-09-28

Terminology

• Alignment — 57× in this paper · explained in 1 episode
• Transformer — 16× in this paper · explained in 2 episodes
• Diffusion Model — 9× in this paper · explained in 8 episodes
• Diffusion Models — 9× in this paper · explained in 6 episodes
• Flow Matching — 8× in this paper · explained in 8 episodes
• Ablation — 7× in this paper · explained in 1 episode
• Distillation — 5× in this paper · explained in 2 episodes
• Calibration — 4× in this paper · explained in 7 episodes
• Generative Model — 4× in this paper · explained in 2 episodes
• Generative Models — 4× in this paper · explained in 2 episodes
• Accuracy — 3× in this paper · explained in 1 episode
• Conference on Computer Vision and Pattern Recognition — 3× in this paper
• Knowledge Distillation — 3× in this paper · explained in 11 episodes
• Latent Diffusion Model — 2× in this paper · explained in 2 episodes
• Latent Diffusion Models — 2× in this paper · explained in 2 episodes
• Linear Probing — 2× in this paper · explained in 2 episodes
• Rectified Flow — 2× in this paper · explained in 3 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• CVF International Conference on Computer Vision — 1× in this paper
• Compositional Generalization — 1× in this paper · explained in 4 episodes
• Entanglement — 1× in this paper · explained in 3 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Generative Modeling — 1× in this paper · explained in 3 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• Nash Equilibrium — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Representation Alignment and Recoverability Estimation — 1× in this paper
• Self-Supervised Learning — 1× in this paper · explained in 8 episodes
• Self-distillation — 1× in this paper · explained in 6 episodes

Sources

• Demystifying MMD GANs
• Quantifying Knowledge Distillation Using Partial Information Decomposition
• How Compositional Generalization and Creativity Improve as Diffusion Models are Trained
• Image Generators are Generalist Vision Learners
• SPARE: Structural Parameter-Free Affinity Regularization for Flow Matching
• Attention Deficits in Language Models: Causal Explanations for Procedural Hallucinations
• DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers
• Flow Matching for Generative Modeling
• Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
• AHPA: Adaptive Hierarchical Prior Alignment for Diffusion Transformers
• Spectrum Matching: a Unified Perspective for Superior Diffusability in Latent Diffusion
• DINOv2: Learning Robust Visual Features without Supervision
• REGLUE Your Latents with Global and Local Semantics for Entangled Diffusion
• Improved Baselines with Representation Autoencoders
• Conditioning Residuals for Diffusion Models via Representation Feedback
• Beyond Point-Wise Matching: Structural Representation Alignment for Accelerating Diffusion Transformers
• A Theory of Usable Information Under Computational Constraints
• Representation Fr'echet Loss for Visual Generation
• Hidden Error Awareness in Chain-of-Thought Reasoning: The Signal Is Diagnostic, Not Causal
• Dyna-DINO: Efficient ViT Distillation Via Adaptive Representation Anchoring

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