ScAle: Attention Head Scaling as a Minimal Adapter for Spatial Reasoning in Vision Language Models

• URL: http://arxiv.org/abs/2606.29579v1
• Date: Sun, 28 Jun 2026 19:48:39 GMT
• Title: ScAle: Attention Head Scaling as a Minimal Adapter for Spatial Reasoning in Vision Language Models
• Abstract summary: We propose ScAle, an ultra-lightweight adaptation method that learns a small set of scalar coefficients to modulate attention and activations in a fully frozen backbone.<n>Our method achieves up to 134.1% relative accuracy gains using only 1K trainable parameters without requiring millions of trainable parameters as in standard PEFT methods such as LoRA.
• Score: 33.01358619125075
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Spatial reasoning remains a persistent challenge for many vision language models (VLMs), and improving it typically requires fine-tuning with substantial additional parameters. Our preliminary analysis reveals that rescaling activations in selected transformer layers-without modifying pretrained weights-can significantly influence downstream performance. Motivated by this observation, we propose ScAle, an ultra-lightweight adaptation method that learns a small set of scalar coefficients to modulate last-token attention and MLP activations in a fully frozen backbone. We evaluate our method on the synthetic spatial reasoning benchmark SpatialEval and on real-world VQA datasets (COCOQA and VGQA) across multiple model families. Our method, ScAle, achieves up to 134.1% relative accuracy gains using only 1K trainable parameters without requiring millions of trainable parameters as in standard PEFT methods such as LoRA. Despite its extreme compactness, our approach recovers a substantial fraction of standard PEFT performance while preserving strong non-spatial VQA accuracy. These results demonstrate that bounded activation reweighting provides a simple, architecture-agnostic, and highly parameter-efficient alternative for adapting pretrained VLMs.

Related papers

• TLoRA+: A Low-Rank Parameter-Efficient Fine-Tuning Method for Large Language Models [4.092357804635167]
  We propose a novel PEFT method that incorporates the TLoRA+ into the weight matrices of pre-trained models.<n>The proposed approach not only preserves the efficiency of low-rank adaptation but also further enhances performance without significantly increasing computational cost.
  arXiv  Detail & Related papers  (2026-04-15T00:30:57Z)
• Benchmarking Few-shot Transferability of Pre-trained Models with Improved Evaluation Protocols [123.73663884421272]
  Few-shot transfer has been revolutionized by stronger pre-trained models and improved adaptation algorithms.<n>We establish FEWTRANS, a comprehensive benchmark containing 10 diverse datasets.<n>By releasing FEWTRANS, we aim to provide a rigorous "ruler" to streamline reproducible advances in few-shot transfer learning research.
  arXiv  Detail & Related papers  (2026-02-28T05:41:57Z)
• High-Rank Structured Modulation for Parameter-Efficient Fine-Tuning [57.85676271833619]
  Low-rank Adaptation (LoRA) uses a low-rank update method to simulate full parameter fine-tuning.<n>We present textbfSMoA, a high-rank textbfStructured textbfMOdulation textbfAdapter that uses fewer trainable parameters while maintaining a higher rank.
  arXiv  Detail & Related papers  (2026-01-12T13:06:17Z)
• FIESTA: Fisher Information-based Efficient Selective Test-time Adaptation [2.876586838098149]
  This paper introduces a novel Fisher-driven selective adaptation framework that dynamically identifies and updates only the most critical model parameters.<n> Experiments on the challenging AffWild2 benchmark demonstrate that our approach significantly outperforms existing TTA methods.<n>The proposed approach not only enhances recognition accuracy but also dramatically reduces computational overhead, making test-time adaptation more practical for real-world affective computing applications.
  arXiv  Detail & Related papers  (2025-03-29T23:56:32Z)
• SALT: Parameter-Efficient Fine-Tuning via Singular Value Adaptation with Low-Rank Transformation [6.267971370719281]
  Large foundation models offer considerable flexibility, yet the cost of fine-tuning these models remains a significant barrier.<n>We propose SALT, a method that selectively adapts the most influential singular values using trainable scale and shift parameters.<n>This hybrid approach harnesses the advantages of both LoRA and SVD, enabling effective adaptation without relying on increasing model size or depth.
  arXiv  Detail & Related papers  (2025-03-20T11:42:41Z)
• Refining Salience-Aware Sparse Fine-Tuning Strategies for Language Models [14.68920095399595]
  sparsity-based PEFT (SPEFT) introduces trainable sparse adaptations to the weight matrices in the model.<n>We conduct the first systematic evaluation of salience metrics for SPEFT, inspired by zero-cost NAS proxies.<n>We compare static and dynamic masking strategies, finding that static masking, which predetermines non-zero entries before training, delivers efficiency without sacrificing performance.
  arXiv  Detail & Related papers  (2024-12-18T04:14:35Z)
• FineGates: LLMs Finetuning with Compression using Stochastic Gates [7.093692674858257]
  Large Language Models (LLMs) present significant challenges for full finetuning due to the high computational demands.<n>Lightweight finetuning techniques have been proposed, like learning low-rank adapter layers.<n>We propose an adaptor model based on gates that simultaneously sparsify the frozen base model with task-specific adaptation.
  arXiv  Detail & Related papers  (2024-12-17T14:33:05Z)
• ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts [71.91042186338163]
  ALoRE is a novel PETL method that reuses the hypercomplex parameterized space constructed by Kronecker product to Aggregate Low Rank Experts.<n>Thanks to the artful design, ALoRE maintains negligible extra parameters and can be effortlessly merged into the frozen backbone.
  arXiv  Detail & Related papers  (2024-12-11T12:31:30Z)
• SaRA: High-Efficient Diffusion Model Fine-tuning with Progressive Sparse Low-Rank Adaptation [52.6922833948127]
  In this work, we investigate the importance of parameters in pre-trained diffusion models.<n>We propose a novel model fine-tuning method to make full use of these ineffective parameters.<n>Our method enhances the generative capabilities of pre-trained models in downstream applications.
  arXiv  Detail & Related papers  (2024-09-10T16:44:47Z)
• ETHER: Efficient Finetuning of Large-Scale Models with Hyperplane Reflections [59.839926875976225]
  We propose the ETHER transformation family, which performs Efficient fineTuning via HypErplane Reflections. In particular, we introduce ETHER and its relaxation ETHER+, which match or outperform existing PEFT methods with significantly fewer parameters.
  arXiv  Detail & Related papers  (2024-05-30T17:26:02Z)
• Towards Efficient Vision-Language Tuning: More Information Density, More Generalizability [73.34532767873785]
  We propose the concept of Information Density'' (ID) to indicate whether a matrix strongly belongs to certain feature spaces. We introduce the Dense Information Prompt (DIP) to enhance information density to improve generalization. DIP significantly reduces the number of tunable parameters and the requisite storage space, making it particularly advantageous in resource-constrained settings.
  arXiv  Detail & Related papers  (2023-12-17T20:42:43Z)
• Parameter and Computation Efficient Transfer Learning for Vision-Language Pre-trained Models [79.34513906324727]
  In this paper, we aim at parameter and efficient transfer learning (PCETL) for vision-language pre-trained models. We propose a novel dynamic architecture skipping (DAS) approach towards effective PCETL.
  arXiv  Detail & Related papers  (2023-09-04T09:34:33Z)
• LoRAPrune: Structured Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning [56.88751562302793]
  Low-rank adaption (LoRA) has emerged to fine-tune large language models (LLMs) LoRAPrune is a new framework that delivers an accurate structured pruned model in a highly memory-efficient manner. LoRAPrune achieves a reduction in perplexity by 4.81 on WikiText2 and 3.46 on PTB, while also decreasing memory usage by 52.6%.
  arXiv  Detail & Related papers  (2023-05-28T15:15:48Z)

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.