Edge Computing Comparison Hub
4 papers - avg viability 7.5
Top Papers
- LOOKAT: Lookup-Optimized Key-Attention for Memory-Efficient Transformers(9.0)
Introduce LOOKAT to significantly compress KV-cache for edge deployment without architecture changes.
- Deep Reinforcement Learning-driven Edge Offloading for Latency-constrained XR pipelines(7.0)
A deep reinforcement learning framework for optimizing edge offloading in latency-sensitive XR applications.
- Lightweight User-Personalization Method for Closed Split Computing(7.0)
SALT is a lightweight adaptation framework for enhancing user personalization in closed Split Computing systems.
- RAPID: Redundancy-Aware and Compatibility-Optimal Edge-Cloud Partitioned Inference for Diverse VLA models(7.0)
RAPID is an edge-cloud collaborative inference framework for Vision Language Action models that optimizes partitioning for real-time embodied intelligence applications.