Related papers: X-Token: Projection-Guided Cross-Tokenizer Knowled…

Traditional knowledge distillation focuses on aligning the student's predicted probabilities with both ground-truth labels and the teacher's predicted probabilities. However, the transition to predicted probabilities from logits would…

Logit-based knowledge distillation (KD) for classification is cost-efficient compared to feature-based KD but often subject to inferior performance. Recently, it was shown that the performance of logit-based KD can be improved by…

Multi-task learning (MTL) has been widely used in recommender systems, wherein predicting each type of user feedback on items (e.g, click, purchase) are treated as individual tasks and jointly trained with a unified model. Our key…

On-policy distillation (OPD) is increasingly used in LLM post-training because it can leverage a teacher model to provide dense supervision on student rollouts. The standard implementation, however, usually reduces distribution matching to…

Knowledge distillation involves transferring soft labels from a teacher to a student using a shared temperature-based softmax function. However, the assumption of a shared temperature between teacher and student implies a mandatory exact…

Pre-trained language models (PLMs) have emerged as powerful tools for code understanding. However, deploying these PLMs in large-scale applications faces practical challenges due to their computational intensity and inference latency.…

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…

Byte Language Models (BLMs) have emerged as a promising direction for scaling language models beyond tokenization. However, existing BLMs typically require training from scratch on trillions of bytes, making them prohibitively expensive. In…

Despite the success of Large Language Models (LLMs), they still face challenges related to high inference costs and memory requirements. To address these issues, Knowledge Distillation (KD) has emerged as a popular method for model…

Knowledge distillation aims to compress a powerful yet cumbersome teacher model into a lightweight student model without much sacrifice of performance. For this purpose, various approaches have been proposed over the past few years,…

Large Vision-Language Models (VLMs) are successful in addressing a multitude of vision-language understanding tasks, such as Visual Question Answering (VQA), but their memory and compute requirements remain a concern for practical…

Chain-of-thought distillation is a powerful technique for transferring reasoning abilities from large language models (LLMs) to smaller student models. Previous methods typically require the student to mimic the step-by-step rationale…

Large Language Models (LLMs) have made significant strides in problem-solving by incorporating reasoning processes. However, this enhanced reasoning capability results in an increased number of output tokens during inference, leading to…

Knowledge Distillation (KD) has been considered as a key solution in model compression and acceleration in recent years. In KD, a small student model is generally trained from a large teacher model by minimizing the divergence between the…

LLMs are often used by downstream users as teacher models for knowledge distillation, compressing their capabilities into memory-efficient models. However, as these teacher models may stem from untrusted parties, distillation can raise…

Post-training of language models (LMs) increasingly relies on the following two stages: (i) knowledge distillation, where the LM is trained to imitate a larger teacher LM, and (ii) reinforcement learning from human feedback (RLHF), where…

Cross-language code clone detection (X-CCD) is challenging because semantically equivalent programs written in different languages often share little surface similarity. Although large language models (LLMs) have shown promise for semantic…

This work studies knowledge distillation (KD) and addresses its constraints for recurrent neural network transducer (RNN-T) models. In hard distillation, a teacher model transcribes large amounts of unlabelled speech to train a student…

Knowledge Distillation (KD) has emerged as a prominent technique for model compression. However, conventional KD approaches primarily focus on homogeneous architectures with identical tokenizers, constraining their applicability in…

Knowledge distillation has been widely adopted in computer vision task processing, since it can effectively enhance the performance of lightweight student networks by leveraging the knowledge transferred from cumbersome teacher networks.…