相关论文: Standing on the Shoulders of Giants: Stabilized Kn…

Large language models (LLMs) deliver remarkable performance but are costly to deploy, motivating knowledge distillation (KD) for efficient inference. Existing KD objectives typically match student and teacher probabilities via softmax,…

This study proposes a knowledge distillation algorithm based on large language models and feature alignment, aiming to effectively transfer the knowledge of large pre-trained models into lightweight student models, thereby reducing…

We propose a straightforward approach called Distillation Contrastive Decoding (DCD) to enhance the reasoning capabilities of Large Language Models (LLMs) during inference. In contrast to previous approaches that relied on smaller amateur…

Since the advent of reasoning-based large language models, many have found great success from distilling reasoning capabilities into student models. Such techniques have significantly bridged the gap between reasoning and standard LLMs on…

Knowledge Distillation (KD) has been validated as an effective model compression technique for learning compact object detectors. Existing state-of-the-art KD methods for object detection are mostly based on feature imitation. In this…

Developers introduce code clones to improve programming productivity. Many existing studies have achieved impressive performance in monolingual code clone detection. However, during software development, more and more developers write…

Knowledge distillation (KD) is an established paradigm for transferring privileged knowledge from a cumbersome model to a lightweight and efficient one. In recent years, logit-based KD methods are quickly catching up in performance with…

Large Language Models (LLMs) have shown promising performance in knowledge-intensive reasoning tasks that require a compound understanding of knowledge. However, deployment of the LLMs in real-world applications can be challenging due to…

Modern software relies on a multitude of automated testing and quality assurance tools to prevent errors, bugs and potential vulnerabilities. This study sets out to provide a head-to-head, quantitative and qualitative evaluation of six…

This paper addresses the limitations of large-scale language models in safety alignment and robustness by proposing a fine-tuning method that combines contrastive distillation with noise-robust training. The method freezes the backbone…

The increasing complexity of modern software systems exacerbates the prevalence of security vulnerabilities, posing risks of severe breaches and substantial economic loss. Consequently, robust code vulnerability detection is essential for…

Large language models (LLMs) have significantly advanced various natural language processing tasks, but deploying them remains computationally expensive. Knowledge distillation (KD) is a promising solution, enabling the transfer of…

Large-scale models (LSMs) can be an effective framework for semantic representation and understanding, thereby providing a suitable tool for designing semantic communication (SC) systems. However, their direct deployment is often hindered…

Knowledge distillation (KD) is known as a promising solution to compress large language models (LLMs) via transferring their knowledge to smaller models. During this process, white-box KD methods usually minimize the distance between the…

Large language models (LLMs) have achieved significant progress in natural language processing but face challenges in deployment due to high memory and computational requirements. Weight quantization is a common approach to address these…

In this paper, we propose a simple yet effective contrastive knowledge distillation framework that achieves sample-wise logit alignment while preserving semantic consistency. Conventional knowledge distillation approaches exhibit…

Large code models (LCMs) have remarkably advanced the field of code generation. Despite their impressive capabilities, they still face practical deployment issues, such as high inference costs, limited accessibility of proprietary LCMs, and…

We propose a resource-efficient framework for compressing large language models through knowledge distillation, combined with guided chain-of-thought reinforcement learning. Using Qwen 3B as the teacher and Qwen 0.5B as the student, we…

The learning objective of vision-language approach of CLIP does not effectively account for the noisy many-to-many correspondences found in web-harvested image captioning datasets, which contributes to its compute and data inefficiency. To…

Large reasoning models such as DeepSeek-R1 and their distilled variants achieve strong performance on complex reasoning tasks. Yet, distilling these models often demands large-scale data for supervised fine-tuning (SFT), motivating the…