Paper Notes
Search
搜索
暗色模式
亮色模式
探索
标签: text-to-image-generation
此标签下有18条笔记。
2026年5月
Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation
2026年5月
Beyond Pairwise Preferences: Listwise Reward-Aware Alignment for Diffusion Models
2026年5月
DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models
2026年5月
Do Less, Achieve More: Do We Need Every-Step Optimization for RL Fine-tuning of Diffusion Models?
2026年5月
E²PO: Embedding-perturbed Exploration Preference Optimization for Flow Models
2026年5月
Flow-OPD: On-Policy Distillation for Flow Matching Models
2026年5月
HiDream-O1-Image: A Natively Unified Image Generative Foundation Model with Pixel-level Unified Transformer
2026年5月
Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models
2026年5月
MARBLE: Multi-Aspect Reward Balance for Diffusion RL
2026年5月
Precise: SDE-Consistent Stochastic Sampling for RL Post-Training of Flow-Matching Models
2026年5月
Unlocking Complex Visual Generation via Closed-Loop Verified Reasoning
2026年4月
Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning
2026年3月
Gen-Searcher: Reinforcing Agentic Search for Image Generation
2025年11月
HBridge: H-Shape Bridging of Heterogeneous Experts for Unified Multimodal Understanding and Generation
2025年11月
Image-Free Timestep Distillation via Continuous-Time Consistency with Trajectory-Sampled Pairs
2025年10月
LightFusion: A Light-weighted, Double Fusion Framework for Unified Multimodal Understanding and Generation
2025年6月
Ovis-U1 Technical Report
2025年5月
MMaDA: Multimodal Large Diffusion Language Models