Image de couverture de livre

Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chen, Dong, Wei, Fangyun, Wan, Ziyu, Chen, Dongdong, Zhang, Jiawei, Zhao, Jinjing, Zhang, Sirui, Yue, Yang, Liang, Zhiyang, Guo, Baining, Luo, Chong, Bao, Jianmin, Li, Ji, Shi, Lei, Yang, Qinhong, Wu, Xiuyu, Feng, Xuelu, Lu, Yan, Dong, Yanchen, Wang, Yitong, Chen, Yunuo
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition
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)

Diffusion Models without Classifier-free Guidance
par: Tang, Zhicong, et autres
Publié: (2025)

MageBench: Bridging Large Multimodal Models to Agents
par: Zhang, Miaosen, et autres
Publié: (2024)

VolumeDiffusion: Flexible Text-to-3D Generation with Efficient Volumetric Encoder
par: Tang, Zhicong, et autres
Publié: (2023)

CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation
par: Li, Qixiu, et autres
Publié: (2024)

Rethinking Generative Large Language Model Evaluation for Semantic Comprehension
par: Wei, Fangyun, et autres
Publié: (2024)

SynChart: Synthesizing Charts from Language Models
par: Liu, Mengchen, et autres
Publié: (2024)

LACON: Training Text-to-Image Model from Uncurated Data
par: Liang, Zhiyang, et autres
Publié: (2026)

Efficient Diffusion Training via Min-SNR Weighting Strategy
par: Hang, Tiankai, et autres
Publié: (2023)

From Virtual Games to Real-World Play
par: Sun, Wenqiang, et autres
Publié: (2025)

RubricRL: Simple Generalizable Rewards for Text-to-Image Generation
par: Feng, Xuelu, et autres
Publié: (2025)

Semantic Image Synthesis via Diffusion Models
par: Zhou, Wengang, et autres
Publié: (2022)

CCEdit: Creative and Controllable Video Editing via Diffusion Models
par: Feng, Ruoyu, et autres
Publié: (2023)

EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty
par: Li, Yuhui, et autres
Publié: (2024)

AtlasGS: Atlanta-world Guided Surface Reconstruction with Implicit Structured Gaussians
par: Zhang, Xiyu, et autres
Publié: (2025)

Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%
par: Zhu, Lei, et autres
Publié: (2024)

InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation
par: Yue, Yang, et autres
Publié: (2026)

ReasonGen-R1: CoT for Autoregressive Image generation models through SFT and RL
par: Zhang, Yu, et autres
Publié: (2025)

SmartEraser: Remove Anything from Images using Masked-Region Guidance
par: Jiang, Longtao, et autres
Publié: (2025)

MobileManiBench: Simplifying Model Verification for Mobile Manipulation
par: Wang, Wenbo, et autres
Publié: (2026)

Spatia: Video Generation with Updatable Spatial Memory
par: Zhao, Jinjing, et autres
Publié: (2025)

Full‐Dimensional Penetration Strategy with Degradable PEAI Enables 8.21% Efficiency in Bulk Heterojunction Sb2S3 Solar Cells
par: Yang Wang, et autres
Publié: (2025)

Laparoscopic Cervical Cerclage Offers Greatest Benefit for Patients With Multiple Conizations or Significantly Shortened Cervix: A Retrospective Study Based on Causal Inference Modeling
par: Xia Li, et autres
Publié: (2026)

Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis
par: Zhang, Bowen, et autres
Publié: (2025)

Animate Any Character in Any World
par: Wang, Yitong, et autres
Publié: (2025)

Revisiting Referring Expression Comprehension Evaluation in the Era of Large Multimodal Models
par: Chen, Jierun, et autres
Publié: (2024)

Rethinking Quantum Noise in Quantum Machine Learning: When Noise Improves Learning
par: Zhu, Linghua, et autres
Publié: (2026)

Exploring Pre-trained Text-to-Video Diffusion Models for Referring Video Object Segmentation
par: Zhu, Zixin, et autres
Publié: (2024)

DreamSR: Towards Ultra-High-Resolution Image Super-Resolution via a Receptive-Field Enhanced Diffusion Transformer
par: Dong, Qingji, et autres
Publié: (2026)

Antibacterial Activity of MC‐170, a 2,2‐Disubstituted Indole‐3‐one Derivative, Against Staphylococcus aureus via Phosphatidylglycerol
par: Yumiao Zhao, et autres
Publié: (2025)

Rethinking the Vulnerability of Concept Erasure and a New Method
par: Richardson, Alex D., et autres
Publié: (2025)

Simplified Diffusion Schrödinger Bridge
par: Tang, Zhicong, et autres
Publié: (2024)

CCA: Collaborative Competitive Agents for Image Editing
par: Hang, Tiankai, et autres
Publié: (2024)

Incorporating Pre-trained Diffusion Models in Solving the Schrödinger Bridge Problem
par: Tang, Zhicong, et autres
Publié: (2025)

Rethinking Model Ensemble in Transfer-based Adversarial Attacks
par: Chen, Huanran, et autres
Publié: (2023)

A High‐Efficiency Codesign Method for Bandgap Circuit by Submodule Optimization
par: Yunqi Yang, et autres
Publié: (2025)

VideoVLA: Video Generators Can Be Generalizable Robot Manipulators
par: Shen, Yichao, et autres
Publié: (2025)

New record-breaking binary linear codes constructed from group codes
par: Yu, Cong, et autres
Publié: (2024)

Inevitable Encounters: Backdoor Attacks Involving Lossy Compression
par: Li, Qian, et autres
Publié: (2026)

PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action
par: Shao, Yijia, et autres
Publié: (2024)