8 papers
Beyond Information Seeking: Severity-Aware Question Supervision for Proactive Medical Dialogue
Chenxuan Li, Xinrong Chen, Luyan Zhang +4
Proactive medical dialogue requires an agent to decide what to ask from incomplete patient information. Existing information-seeking approaches commonly prioritize questions that m…
SparseStreet: Sparse Gaussian Splatting for Real-Time Street Scene Simulation
Qingpo Wuwu, Xiaobao Wei, Peng Chen +6
While 3D Gaussian Splatting has shown promising results in street scene reconstruction, existing methods require massive numbers of Gaussian primitives to capture fine details, lea…
ManipDreamer3D : Synthesizing Plausible Robotic Manipulation Video with Occupancy-aware 3D Trajectory
Ying Li, Xiaobao Wei, Xiaowei Chi +7
Data scarcity continues to be a major challenge in the field of robotic manipulation. Although diffusion models provide a promising solution for generating robotic manipulation vid…
BranchGRPO: Stable and Efficient GRPO with Structured Branching in Diffusion Models
Yuming Li, Yikai Wang, Yuying Zhu +4
Recent progress in aligning image and video generative models with Group Relative Policy Optimization (GRPO) has improved human preference alignment, but existing variants remain i…
EMD: Explicit Motion Modeling for High-Quality Street Gaussian Splatting
Xiaobao Wei, Qingpo Wuwu, Zhongyu Zhao +5
Photorealistic reconstruction of street scenes is essential for developing real-world simulators in autonomous driving. While recent methods based on 3D/4D Gaussian Splatting (GS)…
FastInit: Fast Noise Initialization for Temporally Consistent Video Generation
Chengyu Bai, Yuming Li, Zhongyu Zhao +5
Video generation has made significant strides with the development of diffusion models; however, achieving high temporal consistency remains a challenging task. Recently, FreeInit…