Projectable Models: One-Shot Generation of Small Specialized Transformers from Large Ones

• URL: http://arxiv.org/abs/2506.05641v1
• Date: Fri, 06 Jun 2025 00:05:38 GMT
• Title: Projectable Models: One-Shot Generation of Small Specialized Transformers from Large Ones
• Authors: Andrey Zhmoginov, Jihwan Lee, Mark Sandler,
• Abstract summary: We explore a technique for mapping parameters of a large Transformer to parameters of a smaller specialized model.<n>By making this transformation task-specific, we aim to capture a narrower scope of the knowledge needed for performing a specific task by a smaller model.<n>We study our method on image modeling tasks, showing that performance of generated models exceeds that of universal conditional models.
• Score: 12.265271319203794
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Modern Foundation Models (FMs) are typically trained on corpora spanning a wide range of different data modalities, topics and downstream tasks. Utilizing these models can be very computationally expensive and is out of reach for most consumer devices. Furthermore, most of the broad FM knowledge may actually be irrelevant for a specific task at hand. Here we explore a technique for mapping parameters of a large Transformer to parameters of a smaller specialized model. By making this transformation task-specific, we aim to capture a narrower scope of the knowledge needed for performing a specific task by a smaller model. We study our method on image modeling tasks, showing that performance of generated models exceeds that of universal conditional models.

Related papers

• Specialized Foundation Models Struggle to Beat Supervised Baselines [60.23386520331143]
  We look at three modalities -- genomics, satellite imaging, and time series -- with multiple recent FMs and compare them to a standard supervised learning workflow.<n>We find that it is consistently possible to train simple supervised models that match or even outperform the latest foundation models.
  arXiv  Detail & Related papers  (2024-11-05T04:10:59Z)
• DEEM: Diffusion Models Serve as the Eyes of Large Language Models for Image Perception [66.88792390480343]
  We propose DEEM, a simple but effective approach that utilizes the generative feedback of diffusion models to align the semantic distributions of the image encoder.<n>DEEM exhibits enhanced robustness and a superior capacity to alleviate model hallucinations while utilizing fewer trainable parameters, less pre-training data, and a smaller base model size.
  arXiv  Detail & Related papers  (2024-05-24T05:46:04Z)
• EMR-Merging: Tuning-Free High-Performance Model Merging [55.03509900949149]
  We show that Elect, Mask & Rescale-Merging (EMR-Merging) shows outstanding performance compared to existing merging methods. EMR-Merging is tuning-free, thus requiring no data availability or any additional training while showing impressive performance.
  arXiv  Detail & Related papers  (2024-05-23T05:25:45Z)
• Diffscaler: Enhancing the Generative Prowess of Diffusion Transformers [34.611309081801345]
  This paper focuses on enabling a single pre-trained diffusion transformer model to scale across multiple datasets swiftly. We propose DiffScaler, an efficient scaling strategy for diffusion models where we train a minimal amount of parameters to adapt to different tasks. We find that transformer-based diffusion models significantly outperform CNN-based diffusion models methods while performing fine-tuning over smaller datasets.
  arXiv  Detail & Related papers  (2024-04-15T17:55:43Z)
• Learning from models beyond fine-tuning [78.20895343699658]
  Learn From Model (LFM) focuses on the research, modification, and design of foundation models (FM) based on the model interface.<n>The study of LFM techniques can be broadly categorized into five major areas: model tuning, model distillation, model reuse, meta learning and model editing.<n>This paper gives a comprehensive review of the current methods based on FM from the perspective of LFM.
  arXiv  Detail & Related papers  (2023-10-12T10:20:36Z)
• Heterogeneous Generative Knowledge Distillation with Masked Image Modeling [33.95780732124864]
  Masked image modeling (MIM) methods achieve great success in various visual tasks but remain largely unexplored in knowledge distillation for heterogeneous deep models. We develop the first Heterogeneous Generative Knowledge Distillation (H-GKD) based on MIM, which can efficiently transfer knowledge from large Transformer models to small CNN-based models in a generative self-supervised fashion. Our method is a simple yet effective learning paradigm to learn the visual representation and distribution of data from heterogeneous teacher models.
  arXiv  Detail & Related papers  (2023-09-18T08:30:55Z)
• Fast Adaptation with Bradley-Terry Preference Models in Text-To-Image Classification and Generation [0.0]
  We leverage the Bradley-Terry preference model to develop a fast adaptation method that efficiently fine-tunes the original model. Extensive evidence of the capabilities of this framework is provided through experiments in different domains related to multimodal text and image understanding.
  arXiv  Detail & Related papers  (2023-07-15T07:53:12Z)
• An Efficient General-Purpose Modular Vision Model via Multi-Task Heterogeneous Training [79.78201886156513]
  We present a model that can perform multiple vision tasks and can be adapted to other downstream tasks efficiently. Our approach achieves comparable results to single-task state-of-the-art models and demonstrates strong generalization on downstream tasks.
  arXiv  Detail & Related papers  (2023-06-29T17:59:57Z)
• Prototype-guided Cross-task Knowledge Distillation for Large-scale Models [103.04711721343278]
  Cross-task knowledge distillation helps to train a small student model to obtain a competitive performance. We propose a Prototype-guided Cross-task Knowledge Distillation (ProC-KD) approach to transfer the intrinsic local-level object knowledge of a large-scale teacher network to various task scenarios.
  arXiv  Detail & Related papers  (2022-12-26T15:00:42Z)
• Exploring and Evaluating Personalized Models for Code Generation [9.25440316608194]
  We evaluate transformer model fine-tuning for personalization. We consider three key approaches: (i) custom fine-tuning, which allows all the model parameters to be tuned. We compare these fine-tuning strategies for code generation and discuss the potential generalization and cost benefits of each in various deployment scenarios.
  arXiv  Detail & Related papers  (2022-08-29T23:28:46Z)
• Advancing Plain Vision Transformer Towards Remote Sensing Foundation Model [97.9548609175831]
  We resort to plain vision transformers with about 100 million parameters and make the first attempt to propose large vision models customized for remote sensing tasks. Specifically, to handle the large image size and objects of various orientations in RS images, we propose a new rotated varied-size window attention. Experiments on detection tasks demonstrate the superiority of our model over all state-of-the-art models, achieving 81.16% mAP on the DOTA-V1.0 dataset.
  arXiv  Detail & Related papers  (2022-08-08T09:08:40Z)

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.