Activity counts measure attention, not model quality. Missing counts are unknown. Publication status follows the linked source; a listed venue alone does not confirm peer review.
VITAL adds a separate physiological pathway and structured numerical alignment to a vision-language model so it can estimate heart rate from face video while keeping general visual skills (arXiv:2610.19052). Code is promised, not yet released.
- Form factor
- camera_rppg
- Year
- 2026
- Type
- Task model
- Modalities
- Not reported
- Form factor
- Camera rPPG
- Parameters
- Not reported
- Architecture
- Not reported
- Venue
- Not reported
- Year
- 2026
- DOI
- Not reported
- Code
- Not reported
- Weights
- Not reported
- Licence
- Not reported
- Caveats
- Not reported
- Datasets
- Not reported
- Added
- Not reported
- Updated
- Oct 26, 2026
Abstract
Video-based remote physiological measurement (RPM) has broad applications, while Vision-Language Models (VLMs) provide a promising opportunity to enable end-to-end physiological monitoring for future human-aware intelligent systems. However, existing RPM methods rely on task-specific models and cannot be seamlessly integrated with the multimodal understanding and interaction capabilities of VLMs. We revisit RPM with VLMs and provide empirical evidence for two major bottlenecks: generic visual semantic representations fail to preserve fine-grained physiological cues; while discrete token prediction in autoregressive generation is inherently misaligned with continuous numerical measurement. To address these challenges, we propose VITAL (Visual-physiological Token Alignment for Language Models), a visual-physiological token alignment framework for RPM and preserving general vision tasks. VITAL retains the original visual pathway for semantic understanding and introduces an independent physiological pathway to jointly model semantic and physiological information. Moreover, we propose a structured numerical alignment approach to improve the reliability of generative heart rate estimation by enhancing numerical relationship modeling. Extensive experiments show that VITAL improves cross-domain estimation performance on multiple rPPG datasets while preserving the general visual understanding capability of VLMs, demonstrating its effectiveness as a unified visual-physiological model. Code will be released.
Verbatim fromarXiv· arXiv metadata (abstracts are released under CC0)
How it works
- Approach
- rppg · model · vlm · llm · pointer
Datasets
Cite
APA
Yang, X., Zhang, Z., Fan, Y., Tang, D., Liu, Z., He, D., Wu, K., & Wang, J. (2026). Why Do VLMs Fail at Remote Physiological Measurement? Rethinking with Physiological Grounding and Numerical Alignment (VITAL). arXiv 2610.19052. https://arxiv.org/abs/2610.19052
BibTeX
@misc{yang2026vlms,
title = {{Why Do VLMs Fail at Remote Physiological Measurement? Rethinking with Physiological Grounding and Numerical Alignment (VITAL)}},
author = {Yang, Xiao and Zhang, Zekun and Fan, Yuxuan and Tang, Duoxun and Liu, Ziyang and He, Dengbo and Wu, Kaishun and Wang, Jiyao},
year = {2026},
howpublished = {arXiv 2610.19052},
eprint = {2610.19052},
archivePrefix = {arXiv}
}Built from the hub record. Check it against the publisher before submitting.
History
Record updated