Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length Paper • 2512.04677 • Published 3 days ago • 136
Autoregressive Images Watermarking through Lexical Biasing: An Approach Resistant to Regeneration Attack Paper • 2506.01011 • Published Jun 1 • 9
MME-VideoOCR: Evaluating OCR-Based Capabilities of Multimodal LLMs in Video Scenarios Paper • 2505.21333 • Published May 27 • 38
OmniConsistency: Learning Style-Agnostic Consistency from Paired Stylization Data Paper • 2505.18445 • Published May 24 • 63