4 papers
Coarse Semantic Injection for LLM-Conditioned Structured Indoor Prediction
Shuliang Zhu, Tomiwa Adey, Jinjia Zhou
Large language models (LLMs) have recently been used as structured decoders for indoor understanding from 3D point-token inputs. However, point cloud encoders often under-represent…
Adaptive Sampling Scheduler
Qi Wang, Shuliang Zhu, Jinjia Zhou
Consistent distillation methods have evolved into effective techniques that significantly accelerate the sampling process of diffusion models. Although existing methods have achiev…
TopKD: Top-scaled Knowledge Distillation
Qi Wang, Jinjia Zhou
Recent advances in knowledge distillation (KD) predominantly emphasize feature-level knowledge transfer, frequently overlooking critical information embedded within the teacher's l…
Multi-perspective Contrastive Logit Distillation
Qi Wang, Jinjia Zhou
In previous studies on knowledge distillation, the significance of logit distillation has frequently been overlooked. To revitalize logit distillation, we present a novel perspecti…