arXiv AI
Sensor-Language-Action Models
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Jul 2
ActivityNarrated: An Open-Ended Narrative Paradigm for Wearable Human Activity Understanding
arXiv:2604. 00767v2 Announce Type: replace Abstract: Wearable human activity recognition (HAR) has made steady progress, yet much of this progress remains grounded in fixed-window, closed-set classification benchmarks.
arXiv AI
Jun 2
Towards a General Intelligence and Interface for Wearable Health Data
arXiv:2605. 22759v2 Announce Type: replace Abstract: While ubiquitous wearable sensors capture a wealth of behavioral and physiological information, effectively transforming these signals into personalized health insights is challenging.
arXiv AI
Jun 3
ChatHealthAI: Aligning Electronic Health Record Representations with Large Language Models for Grounded Clinical Reasoning
arXiv:2606. 02802v1 Announce Type: new Abstract: Large language models (LLMs) exhibit strong natural-language reasoning abilities for clinical decision support, but struggle to effectively model structured longitudinal electronic health records (EHRs).
arXiv AI
Aug 3
SERUM: State Extraction and Refinement for User Modeling
arXiv:2607. 29181v1 Announce Type: cross Abstract: Agentic assistants capable of proactive, personalized interactions require structured models of user intent and workflow.
arXiv Computer Vision
4d ago
Grounded Human-Attributed Description and Activity Recognition in Videos
The paper introduces Grounded Human-Attributed Description and Activity Recognition (GHADAR), a task that requires describing the characteristics and activities of every person in a video given their locations. It presents a new dataset derived from AVA-Actions with open‑set captions, a method that constrains cross‑attention masks in vision‑language models to better use grounding information, and a holistic VLM‑based evaluation schema that compares concepts directly between video and predictions. Experiments show the proposed method surpasses state‑of‑the‑art VLMs and highlight limitations of existing evaluation metrics.
arXiv AI
Sep 15
Open-UniMo: Towards Unified Motion-Language Understanding and Generation in the Open World
arXiv:2609.14615v1 Announce Type: cross Abstract: Unified motion generation and understanding is crucial for embodied AI systems that can both synthesize and interpret human actions in open-world env...