Top papers
- LOOKAT: Lookup-Optimized Key-Attention for Memory-Efficient Transformers(9.0)
- Deep Reinforcement Learning-driven Edge Offloading for Latency-constrained XR pipelines(7.0)
- Lightweight User-Personalization Method for Closed Split Computing(7.0)
- RAPID: Redundancy-Aware and Compatibility-Optimal Edge-Cloud Partitioned Inference for Diverse VLA models(7.0)