OmniOPD: Stable On-Policy Distillation for Joint Audio-Video Generation
cs.CV, cs.AI, cs.SD
Submitted: 2026-11-02
Updated: 2026-11-02
Terminology
Sources
- Flow-OPD: On-Policy Distillation for Flow Matching Models
- LTX-2: Efficient Joint Audio-Visual Foundation Model
- DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models
- Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation
- UniVerse-1: Unified Audio-Video Generation via Stitching of Experts
- STEP-OPD: Rethinking Output Targets and Internal Dynamics in On-Policy Distillation for Diffusion Models
- Trust Region On-Policy Distillation
- DanceGRPO: Unleashing GRPO on Visual Generation
- OmniNFT: Modality-wise Omni Diffusion Reinforcement for Joint Audio-Video Generation
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