Research map / Vision-language and multimodal / Cross-modal learning
PhysLLM: Harnessing Large Language Models for Cross-Modal Remote Physiological Sensing
Yiping Xie, Bo Zhao, Mingtong Dai, Jian-Ping Zhou, Yue Sun, Tao Tan, Weicheng Xie, Linlin Shen, Zitong YU
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add LLM (PhysLLM) to PhysNet-based rPPG | PhysNet · UBFC-rPPG | MAE: 2.95 -> 0.21 | Improved |
| add LLM (PhysLLM) vs RhythmFormer | RhythmFormer · PURE | MAE: 0.27 -> 0.17 | Improved |
| PhysLLM vs best baseline on BUAA | PhysFormer · BUAA | MAE: 8.46 -> 6.48 | Improved |
| PhysLLM vs best baseline on MMPD | RhythmFormer · MMPD | MAE: 4.69 -> 4.36 | Improved |
| add DDS (dual-domain stationary) module (ablation) | PhysLLM · UBFC-rPPG | MAE: 0.25 -> 0.21 | Improved |
| add Vision Aggregator (ablation) | PhysLLM · UBFC-rPPG | MAE: 0.34 -> 0.21 | Improved |
| add Text Prototype Guidance (ablation) | PhysLLM · UBFC-rPPG | MAE: 0.27 -> 0.21 | Improved |
| add adaptive prompt learning (ablation) | PhysLLM · UBFC-rPPG | MAE: 1.31 -> 0.21 | Improved |
| add Vision cue to prompt (Vision+Task vs Stats+Task) (ablation) | PhysLLM · UBFC-rPPG | MAE: 0.61 -> 0.43 | Improved |
| replace pretrained LLM with Sundial temporal transformer (ablation) | PhysLLM · PURE | MAE: 0.17 -> 3.22 | Hurt |
| swap DeepSeek for GPT2 or BERT (ablation) | PhysLLM · UBFC-rPPG | MAE: 0.21 -> 0.19 | No clear effect |
| PhysLLM under varied lighting and skin tones | RhythmFormer · MMPD natural light | MAE: 5.65 -> 3.45 | Improved |
Closest papers by meaning
- PhysMLE: Generalizable and Priors-Inclusive Multi-Task Remote Physiological Measurement (TPAMI 2025 · similarity 0.90)
- FreqPhys: Repurposing Implicit Physiological Frequency Prior for Robust Remote Photoplethysmography (ECCV 2026 · similarity 0.89)
- Bi-TTA: Bidirectional Test-Time Adapter for Remote Physiological Measurement (ECCV 2024 · similarity 0.89)
- Remote Photoplethysmography in Real-World and Extreme Lighting Scenarios (CVPR 2025 · similarity 0.89)
- PhysDiff: Physiology-based Dynamicity Disentangled Diffusion Model for Remote Physiological Measurement (AAAI 2025 · similarity 0.88)
- RhythmMamba: Fast, Lightweight, and Accurate Remote Physiological Measurement (AAAI 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
