Measurement Plasticity: Sensor-Level Adaptation for Vision-Language Models
On the map: Multimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
Abstract (arXiv)
We propose Multi-View Physical-prompt (MVP) for Test-Time Adaptation (TTA), a forward-only framework that moves TTA from tokens to photons by treating the camera exposure triangle (i.e., ISO, shutter speed, and aperture) as physical prompts. At inference, MVP acquires selected multiple physical views using a source-affinity score, evaluates digitally augmented variants of each retained view and filters the lowest-entropy predictions, and aggregates predictions with 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 outperforms digital-only TTA on both Auto-Exposure and a combination with conventional sensor control. MVP remains effective under reduced parameter candidates that lower capture latency, demonstrating its practicality.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Prompt learning and adaptation of CLIP, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 20 of its 25 references that are in the map. First posted on arXiv 14 Dec 2025.
Builds on
20 of 25 references.
Closest ancestors · 11
Same direction, newest first
- 2025O-TPT: Orthogonality Constraints for Calibrating Test-time Prompt Tuning in Vision-Language Models15 Mar
- 2025DynaPrompt: Dynamic Test-Time Prompt Tuning27 Jan
- 2024Frustratingly Easy Test-Time Adaptation of Vision-Language Models28 May
- 2024On the test-time zero-shot generalization of vision-language models: Do we really need prompt learning?3 May
- 2024Efficient Test-Time Adaptation of Vision-Language Models27 Mar
- 2024C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature Dispersion21 Mar
- 2024Just Shift It: Test-Time Prototype Shifting for Zero-Shot Generalization with Vision-Language Models19 Mar
- 2023Align Your Prompts: Test-Time Prompting with Distribution Alignment for Zero-Shot Generalization2 Nov
- 2022Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models15 Sep
- 2022Conditional Prompt Learning for Vision-Language Models10 Mar
- 2021Learning to Prompt for Vision-Language Models2 Sep
Other references · 9
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,848
- 2021LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairscited by 1,544
- 2021Do Vision Transformers See Like Convolutional Neural Networks?cited by 671
- 2018Albumentations: fast and flexible image augmentationscited by 558
- 2023Towards Stable Test-Time Adaptation in Dynamic Wild Worldcited by 409
- 2024Unexplored Faces of Robustness and Out-of-Distribution: Covariate Shifts in Environment and Sensor Domainscited by 21
- 2024Historical Test-time Prompt Tuning for Vision Foundation Modelscited by 21
- 2025Adaptive Camera Sensor for Vision Modelscited by 6
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Ultra-Light Test-Time Adaptation for Vision--Language Models
- 2026Your Model Already Knows Don't Teach It, Learn to Ask It: Soft Prompting for Few-Shot Adaptation of Vision-Language Models
- 2026Majorization-Guided Test-Time Adaptation for Vision-Language Models under Modality-Specific Shift
- 2026Training-Free Test-Time Adaptation with Brownian Distance Covariance in Vision-Language Models
- 2024A Lost Opportunity for Vision-Language Models: A Comparative Study of Online Test-Time Adaptation for Vision-Language Models
- 2025D-TPT: Dimensional Entropy Maximization for Calibrating Test-Time Prompt Tuning in Vision-Language Models
- 2025Advancing Reliable Test-Time Adaptation of Vision-Language Models under Visual Variations
- 2025MINT: Memory-Infused Prompt Tuning at Test-time for CLIP