6 papers
Stream Forcing: Constructing Unified Training Trajectory for Robust Streaming Video Generation
Yueting Zhu, Yuehao Song, Kaicheng Zhang +5
Streaming video generation holds strong potential for world modeling, where future frames must be inferred online sequentially to form a continuous video stream. However, streaming…
DriveLaW:Unifying Planning and Video Generation in a Latent Driving World
Tianze Xia, Yongkang Li, Lijun Zhou +9
World models have become crucial for autonomous driving, as they learn how scenarios evolve over time to address the long-tail challenges of the real world. However, current approa…
Phased One-Step Adversarial Equilibrium for Video Diffusion Models
Jiaxiang Cheng, Bing Ma, Xuhua Ren +7
Video diffusion generation suffers from critical sampling efficiency bottlenecks, particularly for large-scale models and long contexts. Existing video acceleration methods, adapte…
DeltaMIL: Gated Memory Integration for Efficient and Discriminative Whole Slide Image Analysis
Yueting Zhu, Yuehao Song, Shuai Zhang +2
Whole Slide Images (WSIs) are typically analyzed using multiple instance learning (MIL) methods. However, the scale and heterogeneity of WSIs generate highly redundant and disperse…
MobileI2V: Fast and High-Resolution Image-to-Video on Mobile Devices
Shuai Zhang, Bao Tang, Siyuan Yu +7
Recently, video generation has witnessed rapid advancements, drawing increasing attention to image-to-video (I2V) synthesis on mobile devices. However, the substantial computationa…
Image-Free Timestep Distillation via Continuous-Time Consistency with Trajectory-Sampled Pairs
Bao Tang, Shuai Zhang, Yueting Zhu +5
Timestep distillation is an effective approach for improving the generation efficiency of diffusion models. The Consistency Model (CM), as a trajectory-based framework, demonstrate…