INAR-VL routes 36% of visual question answering requests to the edge using lightweight complexity signals, cutting latency 24% and energy 26% while retaining 97% of cloud accuracy.
Empowering large language models to edge intelligence: A survey of edge efficient llms and techniques,
3 Pith papers cite this work, alongside 24 external citations. Polarity classification is still indexing.
3
Pith papers citing it
24
external citations · external index
years
2026 3verdicts
UNVERDICTED 3representative citing papers
VFR-LLM combines small LLMs with symbolic verification and solving to reach 0.983 and 0.933 accuracy on precedence and logical deduction tasks using one model call versus lower results from self-consistency baselines.
A literature survey of AI-IoT-Robotics integration synthesizes pairwise work, identifies gaps in full three-way systems, and proposes a modular hybrid SLM-LLM architecture for connected robotics.
citing papers explorer
-
INAR-VL: Input-Aware Routing for Edge-Cloud Vision-Language Inference
INAR-VL routes 36% of visual question answering requests to the edge using lightweight complexity signals, cutting latency 24% and energy 26% while retaining 97% of cloud accuracy.
-
Resource-Aware Neuro-Symbolic Reasoning for Local Small Language Models
VFR-LLM combines small LLMs with symbolic verification and solving to reach 0.983 and 0.933 accuracy on precedence and logical deduction tasks using one model call versus lower results from self-consistency baselines.
-
AI-IoT-Robotics Integration: Survey of Frameworks, Emerging Trends, and the Path Toward Connected Robotics
A literature survey of AI-IoT-Robotics integration synthesizes pairwise work, identifies gaps in full three-way systems, and proposes a modular hybrid SLM-LLM architecture for connected robotics.