paper-with-me

홈 › Papers

Efficient Test-Time Scaling for Small Vision-Language Models

2025-10-03 · Mehmet Onurcan Kaya, Desmond Elliott, Dim P. Papadopoulos arxiv

Small Vision-Language Models (VLMs) provide a computationally efficient alternative to larger models, at the cost of weaker generalization abilities and downstream task performance. These shortcomings could be addressed by test-time scaling techniques, but existing methods are typically computationally demanding, contradicting the resource-efficient design goals of small models. To address these limitations, we propose two novel and efficient test-time scaling strategies that leverage the model-internal features rather than external supervision: (i) Test-Time Augmentation (TTAug), which generates multiple augmented inputs and aggregates outputs at the token level without parameter updates, and (ii) Test-Time Adaptation (TTAdapt), which adapts model parameters during inference using consensus-based pseudolabels from TTAug. Through extensive experiments across nine benchmarks, we demonstrate consistent performance improvements while maintaining computational efficiency suitable for resource-constrained environments. The generality of our approach is demonstrated both within models at different scales and across different VLMs without additional tuning.

📄 PDF Abstract BibTeX arXiv:2510.03574

Code (0)

등록된 구현이 없습니다.

Tasks

Computational EfficiencyTest-time Adaptation

Similar Papers 제목 키워드 기반

Training Vision-Language Process Reward Models for Test-Time Scaling in Multimodal Reasoning: Key Insights and Lessons Learned

2025-09-27 · Brandon Ong, Tej Deep Pala, Vernon Toh, William Chandra Tjhi 외 arxiv

Process Reward Models (PRMs) provide step-level supervision that improves the reliability of reasoning in large language models. While PRMs have been extensively studied in text-based domains, their extension to Vision L…

Multimodal ReasoningVisual Grounding

On Test-Time Scaling for Vision-Language Models

2026-06-27 · Fawaz Sammani, Tzoulio Chamiti, Nikos Deligiannis arxiv

Test-time scaling is a paradigm where large models use additional compute at inference to achieve better performance, without changing model weights. While it has been widely studied for Large Language Models (LLMs), its…

RoboMonkey: Scaling Test-Time Sampling and Verification for Vision-Language-Action Models

2025-06-21 · Jacky Kwok, Christopher Agia, Rohan Sinha, Matt Foutter 외

Vision-Language-Action (VLA) models have demonstrated remarkable capabilities in visuomotor control, yet ensuring their robustness in unstructured real-world environments remains a persistent challenge. In this paper, we…

Synthetic Data GenerationVision-Language-Action

Rethinking Test-Time Scaling for Medical AI: Model and Task-Aware Strategies for LLMs and VLMs

2025-06-16 · Gyutaek Oh, Seoyeon Kim, Sangjoon Park, Byung-Hoon Kim

Test-time scaling has recently emerged as a promising approach for enhancing the reasoning capabilities of large language models or vision-language models during inference. Although a variety of test-time scaling strateg…

Scaling Verification Can Be More Effective than Scaling Policy Learning for Vision-Language-Action Alignment

2026-02-12 · Jacky Kwok, Xilun Zhang, Mengdi Xu, Yuejiang Liu 외 arxiv

The long-standing vision of general-purpose robots hinges on their ability to understand and act upon natural language instructions. Vision-Language-Action (VLA) models have made remarkable progress toward this goal, yet…

Instruction Following