Boomerang Distillation Enables Zero-Shot Model Size Interpolation

• URL: http://arxiv.org/abs/2510.05064v1
• Date: Mon, 06 Oct 2025 17:41:20 GMT
• Title: Boomerang Distillation Enables Zero-Shot Model Size Interpolation
• Authors: Sara Kangaslahti, Nihal V. Nayak, Jonathan Geuter, Marco Fumero, Francesco Locatello, David Alvarez-Melis,
• Abstract summary: Existing approaches build model families by training each size independently, which is expensive and provides only coarse-grained size options.<n>In this work, we identify a novel phenomenon that we call boomerang distillation.<n>One first distills down to a small student and then progressively reconstructs intermediate-sized models by re-incorporating blocks of teacher layers into the student.
• Score: 30.74896485280105
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) are typically deployed under diverse memory and compute constraints. Existing approaches build model families by training each size independently, which is prohibitively expensive and provides only coarse-grained size options. In this work, we identify a novel phenomenon that we call boomerang distillation: starting from a large base model (the teacher), one first distills down to a small student and then progressively reconstructs intermediate-sized models by re-incorporating blocks of teacher layers into the student without any additional training. This process produces zero-shot interpolated models of many intermediate sizes whose performance scales smoothly between the student and teacher, often matching or surpassing pretrained or distilled models of the same size. We further analyze when this type of interpolation succeeds, showing that alignment between teacher and student through pruning and distillation is essential. Boomerang distillation thus provides a simple and efficient way to generate fine-grained model families, dramatically reducing training cost while enabling flexible adaptation across deployment environments. The code and models are available at https://github.com/dcml-lab/boomerang-distillation.

Related papers

• Nemotron Elastic: Towards Efficient Many-in-One Reasoning LLMs [80.72350166388601]
  Nemotron Elastic is a framework for building reasoning-oriented LLMs.<n>It embeds nested submodels within a single parent model.<n>Each of these submodels shares weights with the parent model and can be extracted zero-shot during deployment.
  arXiv  Detail & Related papers  (2025-11-20T18:59:21Z)
• Learning from Stochastic Teacher Representations Using Student-Guided Knowledge Distillation [64.15918654558816]
  Self-distillation (SSD) training strategy is introduced for filtering and weighting teacher representation to distill from task-relevant representations only.<n> Experimental results on real-world affective computing, wearable/biosignal datasets from the UCR Archive, the HAR dataset, and image classification datasets show that the proposed SSD method can outperform state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-04-19T14:08:56Z)
• Exploring and Enhancing the Transfer of Distribution in Knowledge Distillation for Autoregressive Language Models [62.5501109475725]
  Knowledge distillation (KD) is a technique that compresses large teacher models by training smaller student models to mimic them. This paper introduces Online Knowledge Distillation (OKD), where the teacher network integrates small online modules to concurrently train with the student model. OKD achieves or exceeds the performance of leading methods in various model architectures and sizes, reducing training time by up to fourfold.
  arXiv  Detail & Related papers  (2024-09-19T07:05:26Z)
• POA: Pre-training Once for Models of All Sizes [33.72644336390202]
  We propose a novel tri-branch self-supervised training framework, termed as POA (Pre-training Once for All) Our approach introduces an innovative elastic student branch into a modern self-distillation paradigm. It achieves state-of-the-art performance using ViT, Swin Transformer and ResNet backbones.
  arXiv  Detail & Related papers  (2024-08-02T06:13:29Z)
• On the Surprising Efficacy of Distillation as an Alternative to Pre-Training Small Models [7.062887337934677]
  We propose that small models may not need to absorb the cost of pre-training to reap its benefits. We observe that, when distilled on a task from a pre-trained model, a small model can achieve or surpass the performance it would achieve if it was pre-trained then finetuned on that task.
  arXiv  Detail & Related papers  (2024-04-04T07:38:11Z)
• Reusing Pretrained Models by Multi-linear Operators for Efficient Training [65.64075958382034]
  Training large models from scratch usually costs a substantial amount of resources. Recent studies such as bert2BERT and LiGO have reused small pretrained models to initialize a large model. We propose a method that linearly correlates each weight of the target model to all the weights of the pretrained model.
  arXiv  Detail & Related papers  (2023-10-16T06:16:47Z)
• Just CHOP: Embarrassingly Simple LLM Compression [27.64461490974072]
  Large language models (LLMs) enable unparalleled few- and zero-shot reasoning capabilities but at a high computational footprint. We show that simple layer pruning coupled with an extended language model pretraining produces state-of-the-art results against structured and even semi-structured compression of models at a 7B scale. We also show how distillation, which has been super effective in task-agnostic compression of smaller BERT-style models, becomes inefficient against our simple pruning technique.
  arXiv  Detail & Related papers  (2023-05-24T08:18:35Z)
• Dataless Knowledge Fusion by Merging Weights of Language Models [47.432215933099016]
  Fine-tuning pre-trained language models has become the prevalent paradigm for building downstream NLP models.<n>This creates a barrier to fusing knowledge across individual models to yield a better single model.<n>We propose a dataless knowledge fusion method that merges models in their parameter space.
  arXiv  Detail & Related papers  (2022-12-19T20:46:43Z)
• Transfer training from smaller language model [6.982133308738434]
  We find a method to save training time and resource cost by changing the small well-trained model to large model. We test the target model on several data sets and find it is still comparable with the source model.
  arXiv  Detail & Related papers  (2021-04-23T02:56:02Z)
• Reinforced Multi-Teacher Selection for Knowledge Distillation [54.72886763796232]
  knowledge distillation is a popular method for model compression. Current methods assign a fixed weight to a teacher model in the whole distillation. Most of the existing methods allocate an equal weight to every teacher model. In this paper, we observe that, due to the complexity of training examples and the differences in student model capability, learning differentially from teacher models can lead to better performance of student models distilled.
  arXiv  Detail & Related papers  (2020-12-11T08:56:39Z)
• MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers [117.67424061746247]
  We present a simple and effective approach to compress large Transformer based pre-trained models. We propose distilling the self-attention module of the last Transformer layer of the teacher, which is effective and flexible for the student. Experimental results demonstrate that our monolingual model outperforms state-of-the-art baselines in different parameter size of student models.
  arXiv  Detail & Related papers  (2020-02-25T15:21:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.