From Retrieved Context to Runtime Control: Adaptive Compression for Edge-based RAG Paper • 2608.19535 • Published Aug 20
Albireo: Adaptive, Energy-Efficient Inference Framework for Video Object Detection on the Edge Paper • 2609.29648 • Published Aug 29
RAGMark: A Comprehensive Framework for Benchmarking Retrieval-Augmented Generation Systems Paper • 2609.05760 • Published Sep 4
Hydra: Phase-Aware Workload Characterization of LLM Inference across Edge SoC Generations, Backends, and Quantization Levels Paper • 2608.25053 • Published Aug 25
Human Cognition in Machines: A Unified Perspective of World Models Paper • 2604.16592 • Published Apr 17
VOTE: Vision-Language-Action Optimization with Trajectory Ensemble Voting Paper • 2507.05116 • Published Jul 7, 2025