5 papers
SlotMemory: Object-Centric KV Memory for Streaming Long-Video Generation
Weijia Dou, Hui Li, Jiahao Cui +3
Streaming video generation models typically rely on temporal-centric memory, which organizes historical context as raw frames, chunk segments, or unclustered tokens. This organizat…
WAM-Flow: Parallel Coarse-to-Fine Motion Planning via Discrete Flow Matching for Autonomous Driving
Yifang Xu, Jiahao Cui, Feipeng Cai +8
We introduce WAM-Flow, a vision-language-action (VLA) model that casts ego-trajectory planning as discrete flow matching over a structured token space. In contrast to autoregressiv…
WAM-Diff: A Masked Diffusion VLA Framework with MoE and Online Reinforcement Learning for Autonomous Driving
Mingwang Xu, Jiahao Cui, Feipeng Cai +8
End-to-end autonomous driving systems based on vision-language-action (VLA) models integrate multimodal sensor inputs and language instructions to generate planning and control sig…
Hallo4: High-Fidelity Dynamic Portrait Animation via Direct Preference Optimization
Jiahao Cui, Yan Chen, Mingwang Xu +7
Generating highly dynamic and photorealistic portrait animations driven by audio and skeletal motion remains challenging due to the need for precise lip synchronization, natural fa…
Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformer
Jiahao Cui, Hui Li, Yun Zhan +7
Existing methodologies for animating portrait images face significant challenges, particularly in handling non-frontal perspectives, rendering dynamic objects around the portrait,…