Related papers: X-Token: Projection-Guided Cross-Tokenizer Knowled…
On-policy distillation (OPD) trains a student on its own rollouts with token-level teacher supervision. Recent selective OPD methods exploit the non-uniformity of OPD signals by prioritizing high-entropy or high-disagreement tokens. We…
Knowledge Distillation (KD), a learning manner with a larger teacher network guiding a smaller student network, transfers dark knowledge from the teacher to the student via logits or intermediate features, with the aim of producing a…
Knowledge distillation aims to enhance the performance of a lightweight student model by exploiting the knowledge from a pre-trained cumbersome teacher model. However, in the traditional knowledge distillation, teacher predictions are only…
Recently, large-scale pre-trained models have shown their advantages in many tasks. However, due to the huge computational complexity and storage requirements, it is challenging to apply the large-scale model to real scenes. A common…
Several methods of knowledge distillation have been developed for neural network compression. While they all use the KL divergence loss to align the soft outputs of the student model more closely with that of the teacher, the various…
Despite the success of distillation in large language models (LLMs), most prior work applies identical loss functions to both teacher- and student-generated data. These strategies overlook the synergy between loss formulations and data…
Recent advances in knowledge distillation (KD) have enabled smaller student models to approach the performance of larger teacher models. However, popular methods such as supervised KD and on-policy KD, are adversely impacted by the…
Knowledge distillation, i.e., one classifier being trained on the outputs of another classifier, is an empirically very successful technique for knowledge transfer between classifiers. It has even been observed that classifiers learn much…
It has been commonly observed that a teacher model with superior performance does not necessarily result in a stronger student, highlighting a discrepancy between current teacher training practices and effective knowledge transfer. In order…
This paper addresses the challenges of high computational cost and slow inference in deploying large language models. It proposes a distillation strategy guided by multiple teacher models. The method constructs several teacher models and…
Reinforcement learning (RL) post-training has recently driven major gains in long chain-of-thought reasoning large language models (LLMs), but the high inference cost of such models motivates distillation into smaller students. Most…
Representation learning has been evolving from traditional supervised training to Contrastive Learning (CL) and Masked Image Modeling (MIM). Previous works have demonstrated their pros and cons in specific scenarios, i.e., CL and supervised…
Recent advances in deep learning has lead to rapid developments in the field of image retrieval. However, the best performing architectures incur significant computational cost. Recent approaches tackle this issue using knowledge…
Dominant dual-encoder models enable efficient image-text retrieval but suffer from limited accuracy while the cross-encoder models offer higher accuracy at the expense of efficiency. Distilling cross-modality matching knowledge from…
While knowledge distillation has seen widespread use in pre-training and instruction tuning, its application to aligning language models with human preferences remains underexplored, particularly in the more realistic cross-tokenizer…
Knowledge distillation transfers knowledge from a large model to a small one via task and distillation losses. In this paper, we observe a trade-off between task and distillation losses, i.e., introducing distillation loss limits the…
Knowledge distillation (KD) transfers capabilities from large language models (LLMs) to smaller students, yet it can fail unpredictably and also underpins model leakage risks. Our analysis revealed several distillation traps: tail noise,…
Knowledge Distillation (KD) is an effective framework for compressing deep learning models, realized by a student-teacher paradigm requiring small student networks to mimic the soft target generated by well-trained teachers. However, the…
We propose a novel knowledge distillation approach to facilitate the transfer of dark knowledge from a teacher to a student. Contrary to most of the existing methods that rely on effective training of student models given pretrained…
Vision-language models (VLMs) have achieved remarkable success across multimodal tasks, yet their substantial computational demands hinder efficient deployment. Knowledge distillation (KD) has emerged as a powerful approach for building…