mlsanityData to 14 Oct 2026

SitLLM: Large Language Models for Sitting Posture Health Understanding via Pressure Sensor Data

arXiv 2509.12994 ↗First posted 16 Sep 2025cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Poor sitting posture is a critical yet often overlooked factor contributing to long-term musculoskeletal disorders and physiological dysfunctions. Existing sitting posture monitoring systems, although leveraging visual, IMU, or pressure-based modalities, often suffer from coarse-grained recognition and lack the semantic expressiveness necessary for personalized feedback. In this paper, we propose SitLLM, a lightweight multimodal framework that integrates flexible pressure sensing with large language models (LLMs) to enable fine-grained posture understanding and personalized health-oriented response generation. SitLLM comprises three key components: (1) a textitGaussian-Robust Sensor Embedding Module that partitions pressure maps into spatial patches and injects local noise perturbations for robust feature extraction; (2) a textitPrompt-Driven Cross-Modal Alignment Module that reprograms sensor embeddings into the LLM's semantic space via multi-head cross-attention using the pre-trained vocabulary embeddings; and (3) a textitMulti-Context Prompt Module that fuses feature-level, structure-level, statistical-level, and semantic-level contextual information to guide instruction comprehension.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 16 of its 37 references that are in the map. First posted on arXiv 16 Sep 2025.

Builds on

16 of 37 references.

References · 16

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  3. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  4. 2022Large Language Models Encode Clinical Knowledgecited by 1,830
  5. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,463
  6. 2023LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Daycited by 1,305
  7. 2023Capabilities of GPT-4 on Medical Challenge Problemscited by 638
  8. 2023Med-Flamingo: a Multimodal Medical Few-shot Learnercited by 392
  9. 2024On-Device Language Models: A Comprehensive Reviewcited by 104
  10. 2023HuatuoGPT-II, One-stage Training for Medical Adaption of LLMscited by 92
  11. 2023DISC-MedLLM: Bridging General Large Language Models and Real-World Medical Consultationcited by 90
  12. 2024SensorLLM: Aligning Large Language Models with Motion Sensors for Human Activity Recognitioncited by 38
4 more
  1. 2020Bodies at Rest: 3D Human Pose and Shape Estimation from a Pressure Image using Synthetic Datacited by 34
  2. 2022COCOA: Cross Modality Contrastive Learning for Sensor Datacited by 21
  3. 2024Sensor2Text: Enabling Natural Language Interactions for Daily Activity Tracking Using Wearable Sensorscited by 9
  4. 2022Posture Prediction for Healthy Sitting using a Smart Chaircited by 1

Built on by

Not cited yet.