Variational Masked Diffusion Models
"生成质量" 相关文章
Variance-Reduction Guidance: Sampling Trajectory Optimization for Diffusion Models
Latent Discrete Diffusion Models
Latent Discrete Diffusion Models
Just-In-Time Objectives: A General Approach for Specialized AI Interactions
Temporal Alignment Guidance: On-Manifold Sampling in Diffusion Models
Temporal Alignment Guidance: On-Manifold Sampling in Diffusion Models
Learning Robust Diffusion Models from Imprecise Supervision
A Comparison of Independent and Joint Fine-tuning Strategies for Retrieval-Augmented Generation
LightFair: Towards an Efficient Alternative for Fair T2I Diffusion via Debiasing Pre-trained Text Encoders
Disentanglement of Variations with Multimodal Generative Modeling
Dynamic-TreeRPO: Breaking the Independent Trajectory Bottleneck with Structured Sampling
Fast and Fluent Diffusion Language Models via Convolutional Decoding and Rejective Fine-tuning
PC-Sampler: Position-Aware Calibration of Decoding Bias in Masked Diffusion Models
Zero-Residual Concept Erasure via Progressive Alignment in Text-to-Image Model
Learning Diffusion Models with Flexible Representation Guidance
LEDOM: An Open and Fundamental Reverse Language Model
Idea撞车何恺明「分形生成模型」！速度领先10倍，性能更强
谢赛宁新作：表征学习有多重要？一个操作刷新SOTA，DiT训练速度暴涨18倍
谢赛宁新作：表征学习有多重要？一个操作刷新SOTA，DiT训练速度暴涨18倍
