Papers

Filtered to audio-video VAE · clear filter

Browse by term

continual learning 64reinforcement learning 34large language models 17benchmarking 12vision-language models 10generative models 8language models 8video generation 7multimodal models 6natural language processing 6robotics 6world models 6benchmarks 5diffusion models 5on-policy distillation 5policy optimization 5scalability 5self-distillation 5vision-language-action models 5autoregressive models 4computer vision 4diffusion transformers 4LLMs 4multimodal large language models 4verifiable rewards 4attention mechanisms 3embodied intelligence 3image editing 3long-term memory 3multimodal learning 3

Matching papers

OmniVAE: An Audio-Video VAE with Cross-Modal Alignment for Joint Generation

21 upvotes · 26 JUL 2026 · Jun Zhan, Chen Yang, Yitian Gong et al.

This paper develops a new generative model called OmniVAE that can jointly generate synchronized audio and video with fine-grained cross-modal correspondence, and its approach is expected to improve the quality of downstream text-to-audio-video generation tasks.

audio-video VAEcross-modal alignmentlatent space alignmentmodality-specific semantic encoders