Focal Interest
Focal Interest

Natural Language Processing Techniques

External reference: https://openalex.org/T10181

  1. CXL-SpecKV: A Disaggregated FPGA Speculative KV-Cache for Datacenter LLM Serving
    System offloads key-value caches to remote FPGA memory using CXL interconnects, achieving 3.2× throughput gains and 2.8× memory cost reduction for datacenter LLM serving.
  2. A benchmark of expert-level academic questions to assess AI capabilities
    HLE benchmark reveals substantial gap between state-of-the-art LLMs and expert human performance on 2,500 closed-ended academic questions across mathematics, humanities, and natural sciences.