Papers
1–3 of 3Research Paper·Mar 11, 2026
From Images to Words: Efficient Cross-Modal Knowledge Distillation to Language Models from Black-box Teachers
Knowledge distillation (KD) methods are pivotal in compressing large pre-trained language models into smaller models, ensuring computational efficiency without significantly dropping performance. Trad...
7.0 viability
Research Paper·Mar 16, 2026
DAIT: Distillation from Vision-Language Models to Lightweight Classifiers with Adaptive Intermediate Teacher Transfer
Large-scale Vision-Language Models (VLMs) encode rich multimodal semantics that are highly beneficial for fine-grained visual categorization (FGVC). However, their prohibitive computational cost hinde...
6.0 viability
Research Paper·Jan 22, 2026
Integrating Knowledge Distillation Methods: A Sequential Multi-Stage Framework
Knowledge distillation (KD) transfers knowledge from large teacher models to compact student models, enabling efficient deployment on resource constrained devices. While diverse KD methods, including ...
3.0 viability