StepX-OPD: Rethinking Multi-Teacher On-Policy Distillation in Diffusion Models
cs.CV
Submitted: 2026-11-03
Updated: 2026-11-03
Terminology
Sources
- PaddleOCR 3.0 Technical Report
- Flow-OPD: On-Policy Distillation for Flow Matching Models
- SenseFlow: Scaling Distribution Matching for Flow-based Text-to-Image Distillation
- TangPoetryBench: A Multi-Dimensional Benchmark and Rubric-Conditioned Evaluator for Poetry-to-Image Generation
- D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models
- FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space
- Continuous-Time Distribution Matching for Few-Step Diffusion Distillation
- Unified Reward Model for Multimodal Understanding and Generation
- Qwen-Image-Flash: Rethinking the Training Recipe for Few-Step Distillation
- Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis
- DanceOPD: On-Policy Generative Field Distillation
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs