Article

HAR-Agent: Multilingual Multimodal Activity Recognition via Knowledge-Distilled LLM Reasoning

2026-03-31

Abstract excerpt

We present HAR-Agent, a multilingual multimodal human activity recognition system that unifies visual, audio, and text perception through a common textual representation, with a large language model serving as the central decision-maker. We build a multimodal agent architecture and systematically compare 17 model configurations-varying parameter count from 1.5 billion to 72 billion and training method between inst...

Topics

Open a Topic to create a Post that cites this publication.

Uncategorized literature

Identifiers and source

Literature Corpus work: 35e1e52f-a3ff-566c-b409-0f004085e952
DOI: 10.22541/au.177499021.11495152/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

HAR-Agent: Multilingual Multimodal Activity Recognition via Knowledge-Distilled LLM ReasoningDOI 10.22541/au.177499021.11495152/v1Read

Beyond Words: The Evolution of Large Language Models in Context-AwareSemantic proximity Read

A Survey on Post-Training of Multimodal Large Language ModelsSemantic proximity Read

Benchmarking Open-ended Audio Dialogue Understanding for Large Audio-Language ModelsSemantic proximity Read

XTinyHAR: A Tiny Inertial Transformer for Human Activity Recognition via Multimodal Knowledge Distillation and Explainable AISemantic proximity Read

Scaffolding Students-AI Dialogue: A Framework for Safe Educational InteractionsSemantic proximity Read

GenReasoner: Generative Visual Agent PlanningSemantic proximity Read

A Comparative Survey of Large Language Models: Foundation, Instruction-Tuned, and Multimodal VariantsSemantic proximity Read

Efficient and Responsible Transformer Based Conversational Agents for Emotionally Supportive DialogueSemantic proximity Read

Basics of Large Language Models - transformers to LLMsSemantic proximity Read

A Survey on the Evolution and Future Directions of Intelligent Voice Assistants: Advances, Drawbacks, and Motivations for Next-Generation SystemsSemantic proximity Read

Reasoning in Large Language Models: From Chain-of-Thought to Massively Decomposed Agentic ProcessesSemantic proximity Read

Toward Human-Aligned, Modular, and Emotion-Aware Multi-Agent Systems: A Systematic Literature ReviewSemantic proximity Read