3 citations · 5 across the 7 of their papers we have counts for
4 papers · 1 filter
GeoMix: Descriptor-Free Visual Localization via Global Context and Multi-Detector Training
Yejun Zhang, Xinjue Wang, Zihan Wang +2
Descriptor-free visual localization eliminates high-dimensional descriptor storage, preserves scene privacy, and simplifies map maintenance, yet its accuracy still lags far behind…
ParkourFormer: Integrating Predictive Supervision and Sequence Modeling into Parkour Locomotion
Yanheng Mai, Wenhao Xu, Zirui Huang +6
Humanoid parkour requires locomotion policies to coordinate whole-body dynamics across rapidly changing terrains such as stairs, gaps, slopes, and obstacles. Existing learning-base…
Finer Parameter Steps for Low-Rank PEFT: A Controlled Study with CP Tensor Adapters
Xinjue Wang, Xiuheng Wang, Yejun Zhang +3
Low-rank adapters are usually compared by sweeping a small set of ranks, but the rank also fixes the resolution of the parameter budget. For a OPT attention proj…
Anisotropic Tensor Deconvolution of Hyperspectral Images
Xinjue Wang, Xiuheng Wang, Esa Ollila +1
Hyperspectral image (HSI) deconvolution is a challenging ill-posed inverse problem, made difficult by the data's high dimensionality.We propose a parameter-parsimonious framework b…