From Tokens to Photons: Test-Time Physical Prompting for Vision-Language Models
This work addresses robustness issues for VLMs in sensor-mediated environments, offering a practical solution with incremental gains over existing sensor control and TTA pipelines.
The paper tackles the problem of adapting vision-language models (VLMs) from web images to physical environments by proposing MVP, a test-time adaptation framework that uses camera exposure settings as physical prompts, resulting in up to 25.6 percentage points improvement over digital-only methods on ImageNet-ES datasets.
To extend the application of vision-language models (VLMs) from web images to sensor-mediated physical environments, we propose Multi-View Physical-prompt for Test-Time Adaptation (MVP), a forward-only framework that moves test-time adaptation (TTA) from tokens to photons by treating the camera exposure triangle--ISO, shutter speed, and aperture--as physical prompts. At inference, MVP acquires a library of physical views per scene, selects the top-k sensor settings using a source-affinity score, evaluates each retained view under lightweight digital augmentations, filters the lowest-entropy subset of augmented views, and aggregates predictions with Zero-temperature softmax (i.e., hard voting). This selection-then-vote design is simple, calibration-friendly, and requires no gradients or model modifications. On ImageNet-ES and ImageNet-ES-Diverse, MVP consistently outperforms digital-only TTA on single Auto-Exposure captures, by up to 25.6 percentage points (pp), and delivers up to 3.4 pp additional gains over pipelines that combine conventional sensor control with TTA. MVP remains effective under reduced parameter candidate sets that lower capture latency, demonstrating practicality. These results support the main claim that, beyond post-capture prompting, measurement-time control--selecting and combining real physical views--substantially improves robustness for VLMs.