ScAle: Attention Head Scaling as a Minimal Adapter for Spatial Reasoning in Vision–Language Models
- 12 September 2026
- book chapter
- Published by Springer Nature
- p. 76-92
Abstract
No abstract availableKeywords
All Related Versions
This publication has 27 references indexed in Scilit:
- Cross-Platform Scaling of Vision-Language-Action Models from Edge to Cloud GPUs2026
- QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the Edge2025
- Numerical Pruning for Efficient Autoregressive ModelsProceedings of the AAAI Conference on Artificial Intelligence, 2025
- LazyDiT: Lazy Learning for the Acceleration of Diffusion TransformersProceedings of the AAAI Conference on Artificial Intelligence, 2025
- Pruning then Reweighting: Towards Data-Efficient Training of Diffusion Models2025
- SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities2024
- Pruning Parameterization with Bi-level Optimization for Efficient Semantic Segmentation on the Edge2023
- Evaluating Object Hallucination in Large Vision-Language Models2023
- CoCoPIECommunications of the ACM, 2021
- Prefix-Tuning: Optimizing Continuous Prompts for Generation2021