There is No VAE: End-to-End Pixel-Space Generative Modeling via Self-Supervised Pre-training

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Lei, Jiachen, Liu, Keli, Berner, Julius, Yu, Haiming, Zheng, Hongkai, Wu, Jiahong, Chu, Xiangxiang
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

PaCo-FR: Patch-Pixel Aligned End-to-End Codebook Learning for Facial Representation Pre-training
di: Xie, Yin, et al.
Pubblicazione: (2025)

In Pursuit of Pixel Supervision for Visual Pre-training
di: Yang, Lihe, et al.
Pubblicazione: (2025)

USP: Unified Self-Supervised Pretraining for Image Generation and Understanding
di: Chu, Xiangxiang, et al.
Pubblicazione: (2025)

Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation
di: Zhao, Chenxi, et al.
Pubblicazione: (2026)

Generative Planning with 3D-vision Language Pre-training for End-to-End Autonomous Driving
di: Li, Tengpeng, et al.
Pubblicazione: (2025)

REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers
di: Leng, Xingjian, et al.
Pubblicazione: (2025)

AlphaVAE: Unified End-to-End RGBA Image Reconstruction and Generation with Alpha-Aware Representation Learning
di: Wang, Zile, et al.
Pubblicazione: (2025)

MAR-GRPO: Stabilized GRPO for AR-diffusion Hybrid Image Generation
di: Ma, Xiaoxiao, et al.
Pubblicazione: (2026)

Masks and Manuscripts: Advancing Medical Pre-training with End-to-End Masking and Narrative Structuring
di: Gowda, Shreyank N, et al.
Pubblicazione: (2024)

DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation
di: Ma, Zehong, et al.
Pubblicazione: (2025)

Zero-Shot Cross-City Generalization in End-to-End Autonomous Driving: Self-Supervised versus Supervised Representations
di: Naeinian, Fatemeh, et al.
Pubblicazione: (2026)

SS3D: End2End Self-Supervised 3D from Web Videos
di: Hariat, Marwane, et al.
Pubblicazione: (2026)

Is Self-Supervision Enough? Benchmarking Foundation Models Against End-to-End Training for Mitotic Figure Classification
di: Ganz, Jonathan, et al.
Pubblicazione: (2024)

Boundary-Refined Prototype Generation: A General End-to-End Paradigm for Semi-Supervised Semantic Segmentation
di: Dong, Junhao, et al.
Pubblicazione: (2023)

End-to-End Training for Autoregressive Video Diffusion via Self-Resampling
di: Guo, Yuwei, et al.
Pubblicazione: (2025)

GenAD: Generative End-to-End Autonomous Driving
di: Zheng, Wenzhao, et al.
Pubblicazione: (2024)

SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representation
di: Sun, Wenchao, et al.
Pubblicazione: (2024)

Revisiting End-to-End Learning with Slide-level Supervision in Computational Pathology
di: Tang, Wenhao, et al.
Pubblicazione: (2025)

From Pixels to Nucleotides: End-to-End Token-Based Video Compression for DNA Storage
di: Ruan, Cihan, et al.
Pubblicazione: (2026)

StereoSpace: Depth-Free Synthesis of Stereo Geometry via End-to-End Diffusion in a Canonical Space
di: Behrens, Tjark, et al.
Pubblicazione: (2025)

Without Paired Labeled Data: End-to-End Self-Supervised Learning for Drone-view Geo-Localization
di: Chen, Zhongwei, et al.
Pubblicazione: (2025)

UniLS: End-to-End Audio-Driven Avatars for Unified Listening and Speaking
di: Chu, Xuangeng, et al.
Pubblicazione: (2025)

DINO Pre-training for Vision-based End-to-end Autonomous Driving
di: Juneja, Shubham, et al.
Pubblicazione: (2024)

Will Pre-Training Ever End? A First Step Toward Next-Generation Foundation MLLMs via Self-Improving Systematic Cognition
di: Zhang, Xiaoying, et al.
Pubblicazione: (2025)

End-to-End Autoregressive Image Generation with 1D Semantic Tokenizer
di: Chu, Wenda, et al.
Pubblicazione: (2026)

BEEP3D: Box-Supervised End-to-End Pseudo-Mask Generation for 3D Instance Segmentation
di: Yoo, Youngju, et al.
Pubblicazione: (2025)

Enhancing Semantic Segmentation with Continual Self-Supervised Pre-training
di: Ebouky, Brown, et al.
Pubblicazione: (2025)

OneVision: An End-to-End Generative Framework for Multi-view E-commerce Vision Search
di: Zheng, Zexin, et al.
Pubblicazione: (2025)

Explanations of Classifiers Enhance Medical Image Segmentation via End-to-end Pre-training
di: Chen, Jiamin, et al.
Pubblicazione: (2024)

PRIX: Learning to Plan from Raw Pixels for End-to-End Autonomous Driving
di: Wozniak, Maciej K., et al.
Pubblicazione: (2025)

MaskedCLIP: Bridging the Masked and CLIP Space for Semi-Supervised Medical Vision-Language Pre-training
di: Zhu, Lei, et al.
Pubblicazione: (2025)

Generalized Semi-Supervised Learning via Self-Supervised Feature Adaptation
di: Liang, Jiachen, et al.
Pubblicazione: (2024)

MatchED: Crisp Edge Detection Using End-to-End, Matching-based Supervision
di: Cetinkaya, Bedrettin, et al.
Pubblicazione: (2026)

Towards End-to-End Semi-Supervised Table Detection with Semantic Aligned Matching Transformer
di: Shehzadi, Tahira, et al.
Pubblicazione: (2024)

End-to-End Semi-Supervised approach with Modulated Object Queries for Table Detection in Documents
di: Ehsan, Iqraa, et al.
Pubblicazione: (2024)

Taming Hallucinations: Boosting MLLMs' Video Understanding via Counterfactual Video Generation
di: Huang, Zhe, et al.
Pubblicazione: (2025)

SceneLCM: End-to-End Layout-Guided Interactive Indoor Scene Generation with Latent Consistency Model
di: Lin, Yangkai, et al.
Pubblicazione: (2025)

Beyond Hungarian: Match-Free Supervision for End-to-End Object Detection
di: Qiu, Shoumeng, et al.
Pubblicazione: (2026)

LFP: Efficient and Accurate End-to-End Lane-Level Planning via Camera-LiDAR Fusion
di: You, Guoliang, et al.
Pubblicazione: (2024)

Hydra-MDP++: Advancing End-to-End Driving via Expert-Guided Hydra-Distillation
di: Li, Kailin, et al.
Pubblicazione: (2025)