4 papers
Communication-Aware Robot Execution for Cloud Inference under Spatially Heterogeneous Connectivity
Fengkai Liu, Yuichi Ohsita, Masayuki Murata +1
Cloud-hosted foundation models enable robots to use semantic reasoning beyond onboard computational limits. In this setting, the robot executes a currently available primitive gene…
Exposure Bias Can Alleviate Itself via Directional and Frequency Rectification in Flow Matching
Guanbo Huang, Jingjia Mao, Fanding Huang +9
Flow Matching (FM) has achieved remarkable generative performance, yet it suffers from exposure bias due to discrepancies between training and inference. Existing mitigation strate…
Geometric bias in eigenspace perturbation under random heterogeneous noise
Fengkai Liu, Ke Wang, Wanjie Wang
Spectral methods rely on the stability of principal eigenspaces under random perturbations. Classically, this is quantified by the Davis-Kahan and Wedin theorems, which bound the e…
A Unified Evaluation Framework for Multi-Annotator Tendency Learning
Liyun Zhang, Fengkai Liu, Xuanmeng Sha +3
Recent works have emerged in multi-annotator learning that shift focus from Consensus-oriented Learning (CoL), which aggregates multiple annotations into a single ground-truth pred…