相关论文: Personalised Distillation: Empowering Open-Sourced…

Large Language Models (LLMs) face significant challenges at inference time due to their high computational demands. To address this, we present Performance-Guided Knowledge Distillation (PGKD), a cost-effective and high-throughput solution…

Most deep metric learning (DML) methods employ a strategy that forces all positive samples to be close in the embedding space while keeping them away from negative ones. However, such a strategy ignores the internal relationships of…

We present DistillFlow, a knowledge distillation approach to learning optical flow. DistillFlow trains multiple teacher models and a student model, where challenging transformations are applied to the input of the student model to generate…

Model distillation enables the transfer of knowledge from large-scale models to compact student models, facilitating deployment in resource-constrained environments. However, conventional distillation approaches often suffer from…

Knowledge distillation compresses a larger neural model (teacher) into smaller, faster student models by training them to match teacher outputs. However, the internal computational transformations that occur during this process remain…

Knowledge distillation has attracted a great deal of interest recently to compress pre-trained language models. However, existing knowledge distillation methods suffer from two limitations. First, the student model simply imitates the…

Neural Machine Translation (NMT) models achieve state-of-the-art performance on many translation benchmarks. As an active research field in NMT, knowledge distillation is widely applied to enhance the model's performance by transferring…

Growing efforts to improve knowledge distillation (KD) in large language models (LLMs) replace dense teacher supervision with selective distillation, which uses a subset of token positions, vocabulary classes, or training samples for…

Autonomous driving is an important and safety-critical task, and recent advances in LLMs/VLMs have opened new possibilities for reasoning and planning in this domain. However, large models demand substantial GPU memory and exhibit high…

We introduce the problem of continual distillation learning (CDL) in order to use knowledge distillation (KD) to improve prompt-based continual learning (CL) models. The CDL problem is valuable to study since the use of a larger vision…

Instruction tuning is crucial for aligning Large Language Models (LLMs), yet the quality of instruction-following data varies significantly. While high-quality data is paramount, it is often scarce; conversely, abundant low-quality data is…

Owing to their powerful semantic reasoning capabilities, Large Language Models (LLMs) have been effectively utilized as recommenders, achieving impressive performance. However, the high inference latency of LLMs significantly restricts…

Scarcity of parallel sentence-pairs poses a significant hurdle for training high-quality Neural Machine Translation (NMT) models in bilingually low-resource scenarios. A standard approach is transfer learning, which involves taking a model…

Knowledge Distillation (KD) is a critical tool for training Large Language Models (LLMs), yet the majority of research focuses on approaches that rely solely on output logits, neglecting semantic information in the teacher's intermediate…

Large language models (LLMs) have demonstrated remarkable capabilities across various NLP tasks. However, their computational costs are prohibitively high. To address this issue, previous research has attempted to distill the knowledge of…

Instruction tuning aims to align large language models (LLMs) with open-domain instructions and human-preferred responses. While several studies have explored autonomous approaches to distilling and annotating instructions from powerful…

Knowledge Distillation (KD) has been used in image classification for model compression. However, rare studies apply this technology on single-stage object detectors. Focal loss shows that the accumulated errors of easily-classified samples…

Feature distillation is an effective way to improve the performance for a smaller student model, which has fewer parameters and lower computation cost compared to the larger teacher model. Unfortunately, there is a common obstacle - the gap…

Improving large language model (LLM) reasoning requires supervision that is both aligned with the model's own test-time states and informative at the token level. Reinforcement learning with verifiable rewards provides on-policy exploration…

On-policy self-distillation trains a reasoning model on its own rollouts while a teacher, often the same model conditioned on privileged context, provides dense token-level supervision. Existing objectives typically weight the teacher's…