3 papers
cs.CV2026
Local Dense Logit Relations for Enhanced Knowledge Distillation
Liuchi Xu, Kang Liu, Jinshuai Liu +3
State-of-the-art logit distillation methods exhibit versatility, simplicity, and efficiency. Despite the advances, existing studies have yet to delve thoroughly into fine-grained r…
cs.GR2025
LayerD: Decomposing Raster Graphic Designs into Layers
Tomoyuki Suzuki, Kang-Jun Liu, Naoto Inoue +1
Designers craft and edit graphic designs in a layer representation, but layer-based editing becomes impossible once composited into a raster image. In this work, we propose LayerD,…
cs.IR2025
Optimizing Conversational Product Recommendation via Reinforcement Learning
Kang Liu
We propose a reinforcement learning-based approach to optimize conversational strategies for product recommendation across diverse industries. As organizations increasingly adopt i…