Sphere Encoder 2
cs.CV
Submitted: 2026-10-01
Updated: 2026-10-07
Code: https://github.com/kaiyuyue/sphere2
Terminology
Sources
- Generative Modeling via Drifting
- Efficient Image Synthesis with Sphere Latent Encoder
- Representation Distribution Matching for One-Step Visual Generation
- Classifier-Free Diffusion Guidance
- Hyperspherical Latents Improve Continuous-Token Autoregressive Generation
- Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders
- Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
- One-step Latent-free Image Generation with Pixel Mean Flows
- Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed
- High Fidelity Image Synthesis With Deep VAEs In Latent Space
- Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference
- GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
- DINOv3
- SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
- Image Generation with a Sphere Encoder
- Latent Variables on Spheres for Autoencoders in High Dimensions
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