7 papers
Which Trajectory Is Safer? Combining Rule and Learning for Safety Evaluation
Xuewen Luo, Linlian Jiang, Bo Yu +3
Collision rate remains a dominant metric for evaluating autonomous driving trajectory safety, but its binary nature obscures substantial safety differences among collision-free tra…
One Rollout Is All You Get: Fully Test-Time Adaptation for GUI Agents
Ziqiang Wang, Li Gu, Zhixiang Chi +6
GUI agents are deployed with frozen weights and discard everything they experience on the job. Existing ways to update an agent's weights assume something deployment withholds: gro…
TRACE-GS: On-Policy Trajectory Distillation with Privileged Geometric Conditioning for Sparse-View 3DGS Restoration
Linlian Jiang, Yuchen Xi, Sadman Rakib Pinon +3
We present TRACE-GS, an on-policy trajectory distillation framework that leverages privileged geometric conditioning at training time, thereby adapting a diffusion prior to sparse-…
No Adaptation Without Observation: Observability-Constrained Test-Time Prompt Tuning for LiDAR Semantic Segmentation
Linlian Jiang, Wentao Ju, Sadman Rakib Pinon +4
LiDAR semantic segmentation often degrades under real-world deployment due to evolving sensing conditions, while collecting new annotations for retraining is impractical. Test-time…
FACT-GS: Frequency-Aligned Complexity-Aware Texture Reparameterization for 2D Gaussian Splatting
Tianhao Xie, Linlian Jiang, Xinxin Zuo +2
Realistic scene appearance modeling has advanced rapidly with Gaussian Splatting, which enables real-time, high-quality rendering. Recent advances introduced per-primitive textures…
PointMAC: Meta-Learned Adaptation for Robust Test-Time Point Cloud Completion
Linlian Jiang, Rui Ma, Li Gu +3
Point cloud completion is essential for robust 3D perception in safety-critical applications such as robotics and augmented reality. However, existing models perform static inferen…
P2M2-Net: Part-Aware Prompt-Guided Multimodal Point Cloud Completion
Linlian Jiang, Pan Chen, Ye Wang +2
Inferring missing regions from severely occluded point clouds is highly challenging. Especially for 3D shapes with rich geometry and structure details, inherent ambiguities of the…