https://research.perplexity.ai/ https://research.perplexity.ai/404 https://research.perplexity.ai/articles https://research.perplexity.ai/articles/pplx-embed-state-of-the-art-embedding-models-for-web-scale-retrieval https://research.perplexity.ai/articles/evaluating-deep-research-performance-in-the-wild-with-the-draco-benchmark https://research.perplexity.ai/articles/browsesafe https://research.perplexity.ai/articles/rdma-point-to-point-communication-for-llm-systems https://research.perplexity.ai/articles/enabling-trillion-parameter-models-on-aws-efa https://research.perplexity.ai/articles/architecting-and-evaluating-an-ai-first-search-api https://research.perplexity.ai/articles/weight-transfer-for-rl-post-training-in-under-2-seconds https://research.perplexity.ai/articles/gpt-oss-on-day-0 https://research.perplexity.ai/articles/disaggregated-prefill-and-decode https://research.perplexity.ai/articles/accelerating-sonar-through-speculation https://research.perplexity.ai/articles/rl-training-for-math-reasoning https://research.perplexity.ai/articles/lower-latency-and-higher-throughput-with-multi-node-deepseek-deployment https://research.perplexity.ai/articles/efficient-and-portable-mixture-of-experts-communication https://research.perplexity.ai/articles/high-performance-gpu-memory-transfer-on-aws-sagemaker-hyperpod