6 papers · 1 filter
TempAct: Advancing Temporal Plausibility in Autoregressive Video Generation via Planner-Executor RL
Jing Wang, Xiangxin Zhou, Jiajun Liang +5
Autoregressive (AR) video diffusion models enable low-latency streaming generation by synthesizing videos chunk by chunk with cached visual context, but this chunk-wise formulation…
iTryOn: Mastering Interactive Video Virtual Try-On with Spatial-Semantic Guidance
Jun Zheng, Zhengze Xu, Mengting Chen +6
Video Virtual Try-On (VVT) aims to seamlessly replace a garment on a person in a video with a new one. While existing methods have made significant strides in maintaining temporal…
GRPO-Guard: Mitigating Implicit Over-Optimization in Flow Matching via Regulated Clipping
Jing Wang, Jiajun Liang, Jie Liu +10
Recently, GRPO-based reinforcement learning has shown remarkable progress in optimizing flow-matching models, effectively improving their alignment with task-specific rewards. With…
WISA: World Simulator Assistant for Physics-Aware Text-to-Video Generation
Jing Wang, Ao Ma, Ke Cao +9
Recent rapid advancements in text-to-video (T2V) generation, such as SoRA and Kling, have shown great potential for building world simulators. However, current T2V models struggle…
Dynamic Try-On: Taming Video Virtual Try-on with Dynamic Attention Mechanism
Jun Zheng, Jing Wang, Fuwei Zhao +2
Video try-on stands as a promising area for its tremendous real-world potential. Previous research on video try-on has primarily focused on transferring product clothing images to…
Qihoo-T2X: An Efficient Proxy-Tokenized Diffusion Transformer for Text-to-Any-Task
Jing Wang, Ao Ma, Jiasong Feng +3
The global self-attention mechanism in diffusion transformers involves redundant computation due to the sparse and redundant nature of visual information, and the attention map of…