TOAST: Transformer Optimization using Adaptive and Simple Transformations

• URL: http://arxiv.org/abs/2410.04941v6
• Date: Mon, 06 Oct 2025 09:49:19 GMT
• Title: TOAST: Transformer Optimization using Adaptive and Simple Transformations
• Authors: Irene Cannistraci, Simone Antonelli, Emanuele Palumbo, Thomas M. Sutter, Emanuele Rodolà, Bastian Rieck, Julia E. Vogt,
• Abstract summary: We introduce TOAST, a framework that exploits redundancies to approximate entire transformer blocks with lightweight closed-form mappings.<n>Results show that large portions of transformer depth can be replaced by trivial functions, opening a new perspective on efficient foundation models.
• Score: 40.311292704886235
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Foundation models achieve State-of-the-Art (SOTA) performance across different tasks, but their size and computational demands raise concerns about accessibility and sustainability. Existing efficiency methods often require additional retraining or fine-tuning, limiting their practicality. Recent findings suggest that deep neural networks exhibit internal representation similarities. While such similarities across different models have been exploited for enabling techniques such as model stitching and merging, intra-network redundancy remains underexplored as a source for efficiency gains. In this paper, we introduce TOAST (Transformer Optimization using Adaptive and Simple Transformations), a framework that exploits these redundancies to approximate entire transformer blocks with lightweight closed-form mappings, such as linear transformation or even the identity, without any additional training. Across SOTA pretrained vision models (e.g., ViT, DINOv2, DeiT) and datasets ranging from MNIST to ImageNet-1k, TOAST reduces parameters and computation while preserving, and in some cases improving, downstream performance. These results show that large portions of transformer depth can be replaced by trivial functions, opening a new perspective on efficient foundation models.

Related papers

• Elastic ViTs from Pretrained Models without Retraining [74.5386166956142]
  Vision foundation models achieve remarkable performance but are only available in a limited set of pre-determined sizes.<n>We introduce SnapViT: Single-shot network approximation for pruned Vision Transformers.<n>Our approach efficiently combines gradient information with cross-network structure correlations, approximated via an evolutionary algorithm.
  arXiv  Detail & Related papers  (2025-10-20T16:15:03Z)
• Structural Similarity-Inspired Unfolding for Lightweight Image Super-Resolution [88.20464308588889]
  We propose a Structural Similarity-Inspired Unfolding (SSIU) method for efficient image SR.<n>This method is designed through unfolding an SR optimization function constrained by structural similarity.<n>Our model outperforms current state-of-the-art models, boasting lower parameter counts and reduced memory consumption.
  arXiv  Detail & Related papers  (2025-06-13T14:29:40Z)
• Intention-Conditioned Flow Occupancy Models [69.79049994662591]
  Large-scale pre-training has fundamentally changed how machine learning research is done today.<n>Applying this same framework to reinforcement learning is appealing because it offers compelling avenues for addressing core challenges in RL.<n>Recent advances in generative AI have provided new tools for modeling highly complex distributions.
  arXiv  Detail & Related papers  (2025-06-10T15:27:46Z)
• Neural Parameter Search for Slimmer Fine-Tuned Models and Better Transfer [17.463052541838504]
  Fine-tuned models often struggle outside their specific domains and exhibit considerable redundancy.<n>Recent studies suggest that combining a pruned fine-tuned model with the original pre-trained model can mitigate interference when merging model parameters across tasks.<n>We introduce a novel method called Neural Pruning (NPS-Pruning) for slimming down fine-tuned models.
  arXiv  Detail & Related papers  (2025-05-24T14:27:20Z)
• Learning Transformer-based World Models with Contrastive Predictive Coding [58.0159270859475]
  We show that the next state prediction objective is insufficient to fully exploit the representation capabilities of Transformers.<n>We propose to extend world model predictions to longer time horizons by introducing TWISTER, a world model using action-conditioned Contrastive Predictive Coding.<n>TWISTER achieves a human-normalized mean score of 162% on the Atari 100k benchmark, setting a new record among state-of-the-art methods that do not employ look-ahead search.
  arXiv  Detail & Related papers  (2025-03-06T13:18:37Z)
• LESA: Learnable LLM Layer Scaling-Up [57.0510934286449]
  Training Large Language Models (LLMs) from scratch requires immense computational resources, making it prohibitively expensive.<n>Model scaling-up offers a promising solution by leveraging the parameters of smaller models to create larger ones.<n>We propose textbfLESA, a novel learnable method for depth scaling-up.
  arXiv  Detail & Related papers  (2025-02-19T14:58:48Z)
• Transferable Post-training via Inverse Value Learning [83.75002867411263]
  We propose modeling changes at the logits level during post-training using a separate neural network (i.e., the value network)<n>After training this network on a small base model using demonstrations, this network can be seamlessly integrated with other pre-trained models during inference.<n>We demonstrate that the resulting value network has broad transferability across pre-trained models of different parameter sizes.
  arXiv  Detail & Related papers  (2024-10-28T13:48:43Z)
• Unifying Dimensions: A Linear Adaptive Approach to Lightweight Image Super-Resolution [6.857919231112562]
  Window-based transformers have demonstrated outstanding performance in super-resolution tasks. They exhibit higher computational complexity and inference latency than convolutional neural networks. We construct a convolution-based Transformer framework named the linear adaptive mixer network (LAMNet)
  arXiv  Detail & Related papers  (2024-09-26T07:24:09Z)
• TCCT-Net: Two-Stream Network Architecture for Fast and Efficient Engagement Estimation via Behavioral Feature Signals [58.865901821451295]
  We present a novel two-stream feature fusion "Tensor-Convolution and Convolution-Transformer Network" (TCCT-Net) architecture. To better learn the meaningful patterns in the temporal-spatial domain, we design a "CT" stream that integrates a hybrid convolutional-transformer. In parallel, to efficiently extract rich patterns from the temporal-frequency domain, we introduce a "TC" stream that uses Continuous Wavelet Transform (CWT) to represent information in a 2D tensor form.
  arXiv  Detail & Related papers  (2024-04-15T06:01:48Z)
• Self-Supervised Pre-Training for Table Structure Recognition Transformer [25.04573593082671]
  We propose a self-supervised pre-training (SSP) method for table structure recognition transformers. We discover that the performance gap between the linear projection transformer and the hybrid CNN-transformer can be mitigated by SSP of the visual encoder in the TSR model.
  arXiv  Detail & Related papers  (2024-02-23T19:34:06Z)
• A Lightweight Feature Fusion Architecture For Resource-Constrained Crowd Counting [3.5066463427087777]
  We introduce two lightweight models to enhance the versatility of crowd-counting models. These models maintain the same downstream architecture while incorporating two distinct backbones: MobileNet and MobileViT. We leverage Adjacent Feature Fusion to extract diverse scale features from a Pre-Trained Model (PTM) and subsequently combine these features seamlessly.
  arXiv  Detail & Related papers  (2024-01-11T15:13:31Z)
• Efficient Adaptation of Large Vision Transformer via Adapter Re-Composing [8.88477151877883]
  High-capacity pre-trained models have revolutionized problem-solving in computer vision. We propose a novel Adapter Re-Composing (ARC) strategy that addresses efficient pre-trained model adaptation. Our approach considers the reusability of adaptation parameters and introduces a parameter-sharing scheme.
  arXiv  Detail & Related papers  (2023-10-10T01:04:15Z)
• Efficiently Robustify Pre-trained Models [18.392732966487582]
  robustness of large scale models towards real-world settings is still a less-explored topic. We first benchmark the performance of these models under different perturbations and datasets. We then discuss on how complete model fine-tuning based existing robustification schemes might not be a scalable option given very large scale networks.
  arXiv  Detail & Related papers  (2023-09-14T08:07:49Z)
• Multilayer Multiset Neuronal Networks -- MMNNs [55.2480439325792]
  The present work describes multilayer multiset neuronal networks incorporating two or more layers of coincidence similarity neurons. The work also explores the utilization of counter-prototype points, which are assigned to the image regions to be avoided.
  arXiv  Detail & Related papers  (2023-08-28T12:55:13Z)
• Towards a Better Theoretical Understanding of Independent Subnetwork Training [56.24689348875711]
  We take a closer theoretical look at Independent Subnetwork Training (IST) IST is a recently proposed and highly effective technique for solving the aforementioned problems. We identify fundamental differences between IST and alternative approaches, such as distributed methods with compressed communication.
  arXiv  Detail & Related papers  (2023-06-28T18:14:22Z)
• Full Stack Optimization of Transformer Inference: a Survey [58.55475772110702]
  Transformer models achieve superior accuracy across a wide range of applications. The amount of compute and bandwidth required for inference of recent Transformer models is growing at a significant rate. There has been an increased focus on making Transformer models more efficient.
  arXiv  Detail & Related papers  (2023-02-27T18:18:13Z)
• Resource-Efficient Invariant Networks: Exponential Gains by Unrolled Optimization [8.37077056358265]
  We propose a new computational primitive for building invariant networks based instead on optimization. We provide empirical and theoretical corroboration of the efficiency gains and soundness of our proposed method. We demonstrate its utility in constructing an efficient invariant network for a simple hierarchical object detection task.
  arXiv  Detail & Related papers  (2022-03-09T19:04:08Z)
• Modeling Structure with Undirected Neural Networks [20.506232306308977]
  We propose undirected neural networks, a flexible framework for specifying computations that can be performed in any order. We demonstrate the effectiveness of undirected neural architectures, both unstructured and structured, on a range of tasks.
  arXiv  Detail & Related papers  (2022-02-08T10:06:51Z)
• AdaViT: Adaptive Tokens for Efficient Vision Transformer [91.88404546243113]
  We introduce AdaViT, a method that adaptively adjusts the inference cost of vision transformer (ViT) for images of different complexity. AdaViT achieves this by automatically reducing the number of tokens in vision transformers that are processed in the network as inference proceeds.
  arXiv  Detail & Related papers  (2021-12-14T18:56:07Z)
• Redefining Neural Architecture Search of Heterogeneous Multi-Network Models by Characterizing Variation Operators and Model Components [71.03032589756434]
  We investigate the effect of different variation operators in a complex domain, that of multi-network heterogeneous neural models. We characterize both the variation operators, according to their effect on the complexity and performance of the model; and the models, relying on diverse metrics which estimate the quality of the different parts composing it.
  arXiv  Detail & Related papers  (2021-06-16T17:12:26Z)
• Differentiable Neural Architecture Search with Morphism-based Transformable Backbone Architectures [35.652234989200956]
  This study aims at making the architecture search process more adaptive for one-shot or online training. It introduces a growing mechanism for differentiable neural architecture search based on network morphism. We also implement a recently proposed two-input backbone architecture for recurrent neural networks.
  arXiv  Detail & Related papers  (2021-06-14T07:56:33Z)
• Visformer: The Vision-friendly Transformer [105.52122194322592]
  We propose a new architecture named Visformer, which is abbreviated from the Vision-friendly Transformer' With the same computational complexity, Visformer outperforms both the Transformer-based and convolution-based models in terms of ImageNet classification accuracy.
  arXiv  Detail & Related papers  (2021-04-26T13:13:03Z)
• Manifold Regularized Dynamic Network Pruning [102.24146031250034]
  This paper proposes a new paradigm that dynamically removes redundant filters by embedding the manifold information of all instances into the space of pruned networks. The effectiveness of the proposed method is verified on several benchmarks, which shows better performance in terms of both accuracy and computational cost.
  arXiv  Detail & Related papers  (2021-03-10T03:59:03Z)
• Inter-layer Transition in Neural Architecture Search [89.00449751022771]
  The dependency between the architecture weights of connected edges is explicitly modeled in this paper. Experiments on five benchmarks confirm the value of modeling inter-layer dependency and demonstrate the proposed method outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-11-30T03:33:52Z)
• Adversarially Robust Neural Architectures [43.74185132684662]
  This paper aims to improve the adversarial robustness of the network from the architecture perspective with NAS framework. We explore the relationship among adversarial robustness, Lipschitz constant, and architecture parameters. Our algorithm empirically achieves the best performance among all the models under various attacks on different datasets.
  arXiv  Detail & Related papers  (2020-09-02T08:52:15Z)
• DC-NAS: Divide-and-Conquer Neural Architecture Search [108.57785531758076]
  We present a divide-and-conquer (DC) approach to effectively and efficiently search deep neural architectures. We achieve a $75.1%$ top-1 accuracy on the ImageNet dataset, which is higher than that of state-of-the-art methods using the same search space.
  arXiv  Detail & Related papers  (2020-05-29T09:02:16Z)
• Consistency of Spectral Clustering on Hierarchical Stochastic Block Models [5.983753938303726]
  We study the hierarchy of communities in real-world networks under a generic block model. We prove the strong consistency of this method under a wide range of model parameters. Unlike most of existing work, our theory covers multiscale networks where the connection probabilities may differ by orders of magnitude.
  arXiv  Detail & Related papers  (2020-04-30T01:08:59Z)
• Concurrently Extrapolating and Interpolating Networks for Continuous Model Generation [34.72650269503811]
  We propose a simple yet effective model generation strategy to form a sequence of models that only requires a set of specific-effect label images. We show that the proposed method is capable of producing a series of continuous models and achieves better performance than that of several state-of-the-art methods for image smoothing.
  arXiv  Detail & Related papers  (2020-01-12T04:44:44Z)
• Model Fusion via Optimal Transport [64.13185244219353]
  We present a layer-wise model fusion algorithm for neural networks. We show that this can successfully yield "one-shot" knowledge transfer between neural networks trained on heterogeneous non-i.i.d. data.
  arXiv  Detail & Related papers  (2019-10-12T22:07:15Z)

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.