Concept: Exploit
SLAWS: Spatial Locality Analysis and Workload Orchestration for Sparse Matrix Multiplication
Improving efficiency of sparse matrix multiplication through adaptive locality analysis
PAT: Accelerating LLM Decoding via P refix- A ware A t tention with Resource Efficient Multi-Tile Kernel
Accelerating language model inference by reusing shared prompt cache across concurrent requests
Proactive VM consolidation cuts energy use and SLA violations
Predicting server resource needs to cut energy costs while maintaining service quality
People’s Daily and CCTV News used different sentiment strategies on Douyin
How state media outlets frame policy messages differently on short video platforms
AI jewelry platform enabled custom design, chat, and live pricing
Bringing personalized design and AI assistance to traditional jewelry retail
