SII-liangtianyi
tianyilt
AI & ML interests
deep generative model augmented content creation in CG
Recent Activity
authored a paper about 8 hours ago
OmniVAE: An Audio-Video VAE with Cross-Modal Alignment for Joint Generation authored a paper about 8 hours ago
FourierSampler: Unlocking Non-Autoregressive Potential in Diffusion Language Models via Frequency-Guided Generation authored a paper about 8 hours ago
Thinking with Video: Video Generation as a Promising Multimodal
Reasoning ParadigmOrganizations
