Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.14070 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918500837097472 |
|---|---|
| author | Keya, Mahmuda Pillai, Sneh Yuan, Jiawei Zeng, Kai Jiao, Long |
| author_facet | Keya, Mahmuda Pillai, Sneh Yuan, Jiawei Zeng, Kai Jiao, Long |
| contents | There is growing interest in enabling wireless sensing systems to interpret human motion from unsegmented wireless signals; however, existing CSI-based applications rely heavily on accurate signal segmentation and predefined action labels, limiting their applicability in zero-shot scenarios. We present WirelessSenseLLM, a language-driven framework that leverages large language models (LLMs) to enable zero-shot human motion understanding from unsegmented Wi-Fi Channel State Information (CSI). To bridge the modality gap between time-series CSI and discrete language representations, we introduce a CSI-to-Language Adapter and a cross-modal projection mechanism that maps CSI features into a language-aligned semantic space. This design enables the generation of fine-grained natural language descriptions of sequential and overlapping human motions, supporting downstream reasoning without segmented training data. We address two core technical challenges: modality mismatch between CSI features and language embeddings, and overlapping actions in unsegmented CSI streams. Extensive experiments demonstrate strong performance in zero-shot action understanding (92% accuracy and 91% F1-score), language-based reasoning quality (30% factual and 15% reasoning improvements), and multi-person motion explanation with an average 12.33% improvement over prior methods. These results highlight WirelessSenseLLM's effectiveness for robust and interpretable human motion understanding from CSI signals. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_14070 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | WirelessSenseLLM: Zero-Shot Human Activity Understanding by Bridging Wireless Signals and Human Language Keya, Mahmuda Pillai, Sneh Yuan, Jiawei Zeng, Kai Jiao, Long Networking and Internet Architecture There is growing interest in enabling wireless sensing systems to interpret human motion from unsegmented wireless signals; however, existing CSI-based applications rely heavily on accurate signal segmentation and predefined action labels, limiting their applicability in zero-shot scenarios. We present WirelessSenseLLM, a language-driven framework that leverages large language models (LLMs) to enable zero-shot human motion understanding from unsegmented Wi-Fi Channel State Information (CSI). To bridge the modality gap between time-series CSI and discrete language representations, we introduce a CSI-to-Language Adapter and a cross-modal projection mechanism that maps CSI features into a language-aligned semantic space. This design enables the generation of fine-grained natural language descriptions of sequential and overlapping human motions, supporting downstream reasoning without segmented training data. We address two core technical challenges: modality mismatch between CSI features and language embeddings, and overlapping actions in unsegmented CSI streams. Extensive experiments demonstrate strong performance in zero-shot action understanding (92% accuracy and 91% F1-score), language-based reasoning quality (30% factual and 15% reasoning improvements), and multi-person motion explanation with an average 12.33% improvement over prior methods. These results highlight WirelessSenseLLM's effectiveness for robust and interpretable human motion understanding from CSI signals. |
| title | WirelessSenseLLM: Zero-Shot Human Activity Understanding by Bridging Wireless Signals and Human Language |
| topic | Networking and Internet Architecture |
| url | https://arxiv.org/abs/2605.14070 |