Image de couverture de livre

Hyperspherical Latents Improve Continuous-Token Autoregressive Generation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Ke, Guolin, Xue, Hui
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Fast Autoregressive Models for Continuous Latent Generation
par: Hang, Tiankai, et autres
Publié: (2025)

Unified Autoregressive Visual Generation and Understanding with Continuous Tokens
par: Fan, Lijie, et autres
Publié: (2025)

Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens
par: Fan, Lijie, et autres
Publié: (2024)

Fresh-CL: Feature Realignment through Experts on Hypersphere in Continual Learning
par: Zhou, Zhongyi, et autres
Publié: (2025)

VibeToken: Scaling 1D Image Tokenizers and Autoregressive Models for Dynamic Resolution Generations
par: Patel, Maitreya, et autres
Publié: (2026)

End-to-End Autoregressive Image Generation with 1D Semantic Tokenizer
par: Chu, Wenda, et autres
Publié: (2026)

Neural Collapse by Design: Learning Class Prototypes on the Hypersphere
par: Koromilas, Panagiotis, et autres
Publié: (2026)

Hyperspherical Autoencoder for High-Fidelity Image Reconstruction and Generation
par: Chang, Hun, et autres
Publié: (2026)

MADFormer: Mixed Autoregressive and Diffusion Transformers for Continuous Image Generation
par: Chen, Junhao, et autres
Publié: (2025)

VTBench: Evaluating Visual Tokenizers for Autoregressive Image Generation
par: Lin, Huawei, et autres
Publié: (2025)

Closed-Loop Transformers: Autoregressive Modeling as Iterative Latent Equilibrium
par: Jafari, Akbar Anbar, et autres
Publié: (2025)

Probabilistic Contrastive Learning with Explicit Concentration on the Hypersphere
par: Li, Hongwei Bran, et autres
Publié: (2024)

HyperTokens: Controlling Token Dynamics for Continual Video-Language Understanding
par: Nguyen, Toan, et autres
Publié: (2026)

Semantic Prompting with Image-Token for Continual Learning
par: Han, Jisu, et autres
Publié: (2024)

MixAR: Mixture Autoregressive Image Generation
par: Hu, Jinyuan, et autres
Publié: (2025)

Multimodal Latent Language Modeling with Next-Token Diffusion
par: Sun, Yutao, et autres
Publié: (2024)

Radioactive Watermarks in Diffusion and Autoregressive Image Generative Models
par: Meintz, Michel, et autres
Publié: (2025)

Reward-Forcing: Autoregressive Video Generation with Reward Feedback
par: Zhang, Jingran, et autres
Publié: (2026)

Improved Training Technique for Latent Consistency Models
par: Dao, Quan, et autres
Publié: (2025)

VFM-VAE: Vision Foundation Models Can Be Good Tokenizers for Latent Diffusion Models
par: Bi, Tianci, et autres
Publié: (2025)

Annealed Relaxation of Speculative Decoding for Faster Autoregressive Image Generation
par: Li, Xingyao, et autres
Publié: (2026)

Improving Autoregressive Visual Generation with Cluster-Oriented Token Prediction
par: Hu, Teng, et autres
Publié: (2025)

AGDC: Autoregressive Generation of Variable-Length Sequences with Joint Discrete and Continuous Spaces
par: Shin, Yeonsang, et autres
Publié: (2026)

E-CAR: Efficient Continuous Autoregressive Image Generation via Multistage Modeling
par: Yuan, Zhihang, et autres
Publié: (2024)

DART: Denoising Autoregressive Transformer for Scalable Text-to-Image Generation
par: Gu, Jiatao, et autres
Publié: (2024)

ACDC: Autoregressive Coherent Multimodal Generation using Diffusion Correction
par: Chung, Hyungjin, et autres
Publié: (2024)

Continuity-Preserving Convolutional Autoencoders for Learning Continuous Latent Dynamical Models from Images
par: Zhu, Aiqing, et autres
Publié: (2025)

Latent Domain Modeling Improves Robustness to Geographic Shifts
par: Crasto, Ruth, et autres
Publié: (2025)

CLA: Latent Alignment for Online Continual Self-Supervised Learning
par: Cignoni, Giacomo, et autres
Publié: (2025)

From Tokens to Numbers: Continuous Number Modeling for SVG Generation
par: Ogezi, Michael, et autres
Publié: (2026)

What's in a Latent? Leveraging Diffusion Latent Space for Domain Generalization
par: Thomas, Xavier, et autres
Publié: (2025)

Hawk: Leveraging Spatial Context for Faster Autoregressive Text-to-Image Generation
par: Chen, Zhi-Kai, et autres
Publié: (2025)

Spatiotemporal Satellite Image Downscaling with Transfer Encoders and Autoregressive Generative Models
par: Xiang, Yang, et autres
Publié: (2025)

TIMED: Adversarial and Autoregressive Refinement of Diffusion-Based Time Series Generation
par: EskandariNasab, MohammadReza, et autres
Publié: (2025)

ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Model
par: Lu, Shunlin, et autres
Publié: (2024)

Bright 4B: Scaling Hyperspherical Learning for Segmentation in 3D Brightfield Microscopy
par: Khan, Amil, et autres
Publié: (2025)

Denoising Autoregressive Representation Learning
par: Li, Yazhe, et autres
Publié: (2024)

Dense Policy: Bidirectional Autoregressive Learning of Actions
par: Su, Yue, et autres
Publié: (2025)

Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation
par: Wang, Yuqing, et autres
Publié: (2025)

From Broad Exploration to Stable Synthesis: Entropy-Guided Optimization for Autoregressive Image Generation
par: Song, Han, et autres
Publié: (2026)