Conditional Predictive Sufficient Statistics for Visual Representation Learning

arXiv:2609.30647 · cs.CV · Submitted 2026-09-25 · Read on arXiv

cs.CV

Submitted: 2026-09-25

Updated: 2026-09-28

Terminology

• Transformer — 19× in this paper · explained in 2 episodes
• Accuracy — 15× in this paper · explained in 1 episode
• Linear probe — 12× in this paper · explained in 2 episodes
• Representation Learning — 8× in this paper · explained in 2 episodes
• Conference on Computer Vision and Pattern Recognition — 5× in this paper
• Embeddings — 5× in this paper · explained in 2 episodes
• CVF International Conference on Computer Vision — 3× in this paper
• Contrastive Learning — 2× in this paper · explained in 5 episodes
• Degeneracy — 2× in this paper · explained in 3 episodes
• Diffusion Model — 2× in this paper · explained in 8 episodes
• Diffusion Models — 2× in this paper · explained in 6 episodes
• Predictive Coding — 2× in this paper · explained in 2 episodes
• Quantization — 2× in this paper · explained in 12 episodes
• Self-Supervised Learning — 2× in this paper · explained in 7 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes

Sources

• Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens
• Representation Learning with Contrastive Predictive Coding
• RandAR: Decoder-only Autoregressive Visual Generation in Random Orders
• DINOv3
• Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation
• The information bottleneck method
• DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer
• Next-Embedding Prediction Makes Strong Vision Learners

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