3 papers
cs.CL2026
RCEM: Robust Conversational Search EMbedder in Distributional Shift
Kilho Son, Paul Hsu, Cha Zhang +1
We propose RCEM, a Robust Conversational search EMbedder that is additionally equipped with LLM's query reformulation capability without losing base model's generalization. Unlike…
cs.CV2018
Bootstrapping Deep Neural Networks from Approximate Image Processing Pipelines
Kilho Son, Jesse Hostetler, Sek Chai
Complex image processing and computer vision systems often consist of a processing pipeline of functional modules. We intend to replace parts or all of a target pipeline with deep…
cs.CV2016
Learning to Remove Multipath Distortions in Time-of-Flight Range Images for a Robotic Arm Setup
Kilho Son, Ming-Yu Liu, Yuichi Taguchi
Range images captured by Time-of-Flight (ToF) cameras are corrupted with multipath distortions due to interaction between modulated light signals and scenes. The interaction is oft…