Refining Few-Step Text-to-Multiview Diffusion via Reinforcement Learning
cs.LG, cs.CV
Submitted: 2025-05-26
Updated: 2026-11-11
Code: https://github.com/ZiyiZhang27/MVC-ZigAL
Terminology
Sources
- 3DTopia: Large Text-to-3D Generation Model with Hybrid Diffusion Priors
- Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference
- Proximal Policy Optimization Algorithms
- Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model
- ImageDream: Image-Prompt Multi-view Diffusion for 3D Generation
- Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis
Related papers
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis
- (Mis)generalization of Helpful-Only Fine-tuning