相关论文: Distilling Interpretable Models into Human-Readabl…

Reasoning distillation transfers complex reasoning abilities from large language models (LLMs) to smaller ones, yet its success depends on how well the training data align with the student model. This paper introduces the Data-Model…

Distilling the thinking traces of a Large Language Model (LLM) with reasoning capabilities into a smaller model has been proven effective. Yet, there is a scarcity of work done on how model performances scale with the quantity of…

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…

Knowledge distillation introduced in the deep learning context is a method to transfer knowledge from one architecture to another. In particular, when the architectures are identical, this is called self-distillation. The idea is to feed in…

Many natural language processing tasks can be modeled into structured prediction and solved as a search problem. In this paper, we distill an ensemble of multiple models trained with different initialization into a single model. In addition…

Knowledge distillation is a technique for improving the performance of a simple "student" model by replacing its one-hot training labels with a distribution over labels obtained from a complex "teacher" model. While this simple approach has…

Topic modeling is a dominant method for exploring document collections on the web and in digital libraries. Recent approaches to topic modeling use pretrained contextualized language models and variational autoencoders. However, large…

Enhancing small language models for real-life application deployment is a significant challenge facing the research community. Due to the difficulties and costs of using large language models, researchers are seeking ways to effectively…

Ensemble knowledge distillation can extract knowledge from multiple teacher models and encode it into a single student model. Many existing methods learn and distill the student model on labeled data only. However, the teacher models are…

Visual object tracking was generally tackled by reasoning independently on fast processing algorithms, accurate online adaptation methods, and fusion of trackers. In this paper, we unify such goals by proposing a novel tracking methodology…

Knowledge distillation is a common technique for improving the performance of a shallow student network by transferring information from a teacher network, which in general, is comparatively large and deep. These teacher networks are…

Techniques such as ensembling and distillation promise model quality improvements when paired with almost any base model. However, due to increased test-time cost (for ensembles) and increased complexity of the training pipeline (for…

Knowledge distillation learns a lightweight student model that mimics a cumbersome teacher. Existing methods regard the knowledge as the feature of each instance or their relations, which is the instance-level knowledge only from the…

Interpretable machine learning tackles the important problem that humans cannot understand the behaviors of complex machine learning models and how these models arrive at a particular decision. Although many approaches have been proposed, a…

Histopathology can help clinicians make accurate diagnoses, determine disease prognosis, and plan appropriate treatment strategies. As deep learning techniques prove successful in the medical domain, the primary challenges become limited…

Unlike existing knowledge distillation methods focus on the baseline settings, where the teacher models and training strategies are not that strong and competing as state-of-the-art approaches, this paper presents a method dubbed DIST to…

Diffusion models are central to modern generative modeling, and understanding how they balance memorization and generalization is critical for reliable deployment. Recent work has shown that memorization in diffusion models is shaped by…

Visual data is used in numerous different scientific workflows ranging from remote sensing to ecology. As the amount of observation data increases, the challenge is not just to make accurate predictions but also to understand the underlying…

Self-supervised speech pre-training enables deep neural network models to capture meaningful and disentangled factors from raw waveform signals. The learned universal speech representations can then be used across numerous downstream tasks.…

Knowledge distillation from large language models (LLMs) assumes that the teacher's output distribution is a high-quality training signal. On reasoning tasks, this assumption is frequently violated. A model's intermediate representations…