Small Language Models (SLMs) are transformer-based language models with significantly fewer parameters than large-scale counterparts, typically ranging from tens of millions to a few billion parameters. Despite their reduced size, SLMs can achieve competitive performance on targeted tasks through techniques such as knowledge distillation, efficient pretraining, and task-specific fine-tuning. They are suited for deployment in resource-constrained environments, including edge devices, embedded systems, and latency-sensitive applications, where computational cost and memory footprint are critical constraints.

Posts

Uncertainty-Aware Knowledge Distillation for Multimodal Large Language Models

/in /by

Knowledge distillation establishes a learning paradigm that leverages both data supervision and teacher guidance. However, determining the optimal balance between learning from data and learning from the teacher is challenging, as some samples may be noisy while others are subject to teacher uncertainty. This motivates the need for adaptively balancing data and teacher supervision. We propose Beta-weighted Knowledge Distillation (Beta-KD), an uncertainty-aware distillation framework that adaptively modulates how much the student relies on teacher guidance. Specifically, we formulate teacher–student learning from a unified Bayesian perspective and interpret teacher supervision as a Gibbs prior over student activations. This yields a closed-form, uncertainty-aware weighting mechanism and supports arbitrary distillation objectives and their combinations. Extensive experiments on multimodal VQA benchmarks demonstrate that distilling student Vision-Language Models from a large teacher VLM consistently improves performance. The results show that Beta-KD outperforms existing knowledge distillation methods.

Read more