7 papers
Stream-R1: Reliability-Perplexity Aware Reward Distillation for Streaming Video Generation
Bin Wu, Mengqi Huang, Shaojin Wu +4
Distillation-based acceleration has become foundational for making autoregressive streaming video diffusion models practical, with distribution matching distillation (DMD) as the d…
CoCoDiff: Correspondence-Consistent Diffusion Model for Fine-grained Style Transfer
Wenbo Nie, Zixiang Li, Renshuai Tao +3
Transferring visual style between images while preserving semantic correspondence between similar objects remains a central challenge in computer vision. While existing methods hav…
NativeTok: Native Visual Tokenization for Improved Image Generation
Bin Wu, Mengqi Huang, Weinan Jia +1
VQ-based image generation typically follows a two-stage pipeline: a tokenizer encodes images into discrete tokens, and a generative model learns their dependencies for reconstructi…
HunyuanOCR Technical Report
Hunyuan Vision Team, Pengyuan Lyu, Xingyu Wan +29
This paper presents HunyuanOCR, a commercial-grade, open-source, and lightweight (1B parameters) Vision-Language Model (VLM) dedicated to OCR tasks. The architecture comprises a Na…
MuseTalk: Real-Time High-Fidelity Video Dubbing via Spatio-Temporal Sampling
Yue Zhang, Zhizhou Zhong, Minhao Liu +7
Real-time video dubbing that preserves identity consistency while achieving accurate lip synchronization remains a critical challenge. Existing approaches face a trilemma: diffusio…
Synthetic Data is an Elegant GIFT for Continual Vision-Language Models
Bin Wu, Wuxuan Shi, Jinqiao Wang +1
Pre-trained Vision-Language Models (VLMs) require Continual Learning (CL) to efficiently update their knowledge and adapt to various downstream tasks without retraining from scratc…