Focal Interest
Focal Interest

Exploit

  1. SLAWS: Spatial Locality Analysis and Workload Orchestration for Sparse Matrix Multiplication
    SLAWS framework enhances sparse matrix multiplication by analyzing data locality patterns and orchestrating workloads adaptively, overcoming limitations of fixed-architecture accelerators.
  2. PAT: Accelerating LLM Decoding via P refix- A ware A t tention with Resource Efficient Multi-Tile Kernel
    PAT optimizes LLM decode-phase attention by exploiting shared request prefixes and adaptive kernel tiling, reducing memory bandwidth bottlenecks in multi-request serving scenarios.
  3. Proactive VM consolidation cuts energy use and SLA violations
    Framework for VM consolidation combining workload prediction and physics-constrained reinforcement learning. Achieves 23.2% energy reduction and 43.5% SLA violation reduction in cloud datacenters.
  4. People’s Daily and CCTV News used different sentiment strategies on Douyin
    Study analyzing how Chinese state media (People's Daily and CCTV News) adapt rural revitalization content on Douyin using topic modeling and sentiment analysis to reveal institutional.
  5. AI jewelry platform enabled custom design, chat, and live pricing
    Full-stack e-commerce platform integrating generative AI for custom jewelry design, conversational intelligence with live commodity pricing, and real-time market data for heritage jewelry retailers.