Correction Training for Diffusion Models
cs.AI
Submitted: 2026-10-09
Updated: 2026-10-14
Project page: https://sunovivid.github.io/correction-training
Terminology
Sources
- BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset
- Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning
- Flow Reasoning Models: Turning Flows Into Efficient Recurrent Reasoners
- Classifier-Free Diffusion Guidance
- ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment
- Spectral Prior for Reducing Exposure Bias in Diffusion Models
- DiffusionBench: On Holistic Evaluation of Diffusion Transformers
- Flow Matching for Generative Modeling
- Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
- Revisiting Classifier Two-Sample Tests
- Input Perturbation Reduces Exposure Bias in Diffusion Models
- Learn from Your Mistakes: Self-Correcting Masked Diffusion Models
- Selective Underfitting in Diffusion Models
- Score-Based Generative Modeling through Stochastic Differential Equations
- Self-conditioned Flow Map Language Models via Fixed-point Flows
- Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems