6 papers
UniTemp: Unlocking Video Generation in Any Temporal Order via Bidirectional Distillation
Lin Zhang, Sicheng Mo, Zefan Cai +6
Autoregressive video diffusion models have emerged as a promising approach for long video generation, achieving strong performance in streaming settings. However, existing methods…
DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models
Zhuoming Liu, Jinhong Lin, Kwan Man Cheng +3
Many modern vision-language models (VLMs) build on autoregressive decoding of discrete tokens. While text-based output interfaces enable scalable pretraining and strong zero-shot g…
Data Warmup: Complexity-Aware Curricula for Efficient Diffusion Training
Jinhong Lin, Pan Wang, Zitong Zhan +2
A key inefficiency in diffusion training occurs when a randomly initialized network, lacking visual priors, encounters gradients from the full complexity spectrum--most of which it…
Scaling Up Audio-Synchronized Visual Animation: An Efficient Training Paradigm
Lin Zhang, Zefan Cai, Yufan Zhou +10
Recent advances in audio-synchronized visual animation enable control of video content using audios from specific classes. However, existing methods rely heavily on expensive manua…
From Prototypes to General Distributions: An Efficient Curriculum for Masked Image Modeling
Jinhong Lin, Cheng-En Wu, Huanran Li +3
Masked Image Modeling (MIM) has emerged as a powerful self-supervised learning paradigm for visual representation learning, enabling models to acquire rich visual representations b…
Patch Ranking: Efficient CLIP by Learning to Rank Local Patches
Cheng-En Wu, Jinhong Lin, Yu Hen Hu +1
Contrastive image-text pre-trained models such as CLIP have shown remarkable adaptability to downstream tasks. However, they face challenges due to the high computational requireme…