4 papers
Salt++: Context-Aligned Post-Training for Few-Step Streaming Multimodal Generation
Xingtong Ge, Yutong Wang, Lunjie Zhu +7
Few-step streaming audio--video generation requires both causal modeling and step distillation, yet standard training recipes face two context-related challenges. Teacher forcing p…
One-Layer Transformer Provably Learns Multiclass One-Nearest Neighbor in Context
Skanda Athreya, Yutong Wang
We extend recent work establishing an equivalence between one-layer transformers and nearest-neighbor classifiers in the binary setting to the multiclass case. By leveraging the si…
VDOT: Efficient Unified Video Creation via Optimal Transport Distillation
Yutong Wang, Haiyu Zhang, Tianfan Xue +4
The rapid development of generative models has significantly advanced image and video applications. Among these, video creation, aimed at generating videos under various conditions…
ReAugment: Model Zoo-Guided RL for Few-Shot Time Series Augmentation and Forecasting
Haochen Yuan, Yutong Wang, Yihong Chen +2
Time series forecasting, particularly in few-shot learning scenarios, is challenging due to the limited availability of high-quality training data. To address this, we present a pi…