Related papers: Multi-perspective Contrastive Logit Distillation
Knowledge distillation (KD) methods can transfer knowledge of a parameter-heavy teacher model to a light-weight student model. The status quo for feature KD methods is to utilize loss functions based on logits (i.e., pre-softmax class…
Multi-teacher knowledge distillation (KD), a more effective technique than traditional single-teacher methods, transfers knowledge from expert teachers to a compact student model using logit or feature matching. However, most existing…
To apply the latest computer vision techniques that require a large computational cost in real industrial applications, knowledge distillation methods (KDs) are essential. Existing logit-based KDs apply the constant temperature scaling to…
Efficient Multimodal Large Language Models (MLLMs) compress vision tokens to reduce resource consumption, but the loss of visual information can degrade comprehension capabilities. Although some priors introduce Knowledge Distillation to…
Knowledge Distillation (KD), aiming to train a better student model by mimicking the teacher model, plays an important role in model compression. One typical way is to align the output logits. However, we find a common issue named…
Logit Knowledge Distillation has gained substantial research interest in recent years due to its simplicity and lack of requirement for intermediate feature alignment; however, it suffers from limited interpretability in its decision-making…
We address the challenge of producing trustworthy and accurate compact models for edge devices. While Knowledge Distillation (KD) has improved model compression in terms of achieving high accuracy performance, calibration of these compact…
Knowledge Distillation (KD) is a promising technique for reducing the high computational demand of large language models (LLMs). However, previous KD methods are primarily applied to white-box classification models or training small models…
Large language models (LLMs) have garnered increasing attention owing to their powerful logical reasoning capabilities. Generally, larger LLMs (L-LLMs) that require paid interfaces exhibit significantly superior performance compared to…
Knowledge distillation is an effective technique for pre-trained language model compression. However, existing methods only focus on the knowledge distribution among layers, which may cause the loss of fine-grained information in the…
Knowledge distillation has proven effective for model compression by transferring knowledge from a larger network called the teacher to a smaller network called the student. Current knowledge distillation in time series is predominantly…
Recently, machine unlearning approaches have been proposed to remove sensitive information from well-trained large models. However, most existing methods are tailored for LLMs, while MLLM-oriented unlearning remains at its early stage.…
Knowledge distillation (KD) has witnessed its powerful capability in learning compact models in object detection. Previous KD methods for object detection mostly focus on imitating deep features within the imitation regions instead of…
Knowledge distillation (KD) is an effective model compression method that can transfer the internal capabilities of large language models (LLMs) to smaller ones. However, the multi-modal probability distribution predicted by teacher LLMs…
Knowledge distillation (KD) is a powerful paradigm for compressing large language models (LLMs), whose effectiveness depends on intertwined choices of divergence direction, optimization strategy, and data regime. We break down the design of…
With the rapid development of computer vision, Vision Transformers (ViTs) offer the tantalising prospect of unified information processing across visual and textual domains due to the lack of inherent inductive biases in ViTs. ViTs require…
Deploying large language models (LLMs) of several billion parameters can be impractical in most industrial use cases due to constraints such as cost, latency limitations, and hardware accessibility. Knowledge distillation (KD) offers a…
Vision Transformers (ViTs) have achieved significant advancement in computer vision tasks due to their powerful modeling capacity. However, their performance notably degrades when trained with insufficient data due to lack of inherent…
Reverse Kullback-Leibler (RKL) divergence has recently emerged as the preferred objective for large language model (LLM) distillation, consistently outperforming forward KL (FKL), particularly in regimes with large vocabularies and…
The upscaling of Large Language Models (LLMs) has yielded impressive advances in natural language processing, yet it also poses significant deployment challenges. Weight quantization has emerged as a widely embraced solution to reduce…