Perplexity Open-Sources Bumblebee: A Read-Only Supply-Chain Scanner for Developer Endpoints
mayo 23, 2026admin NUAI,Committee,Noticias,Uncategorized(0)Attackers increasingly target the packages, editor extensions, and AI tool configs on developer machines and...
Perplexity AI Releases TransferEngine and pplx garden to Run Trillion Parameter LLMs on Existing GPU Clusters
noviembre 22, 2025admin NUAI,Committee,Noticias,Uncategorized(0)How can teams run trillion parameter language models on existing mixed GPU clusters without costly...
Perplexity AI Open-Sources Unigram Tokenizer That Achieves 5x Lower p50 Latency Than Hugging Face tokenizers Crate
mayo 28, 2026admin NUAI,Committee,Noticias,Uncategorized(0)Perplexity AI’s research team reimplemented their Unigram tokenizer from scratch in Rust and open-sourced the...
Perplexity AI Introduces Hybrid Local-Server Inference Orchestrator for Personal Computer: Automatic On-Device and Cloud Task Routing
junio 5, 2026admin NUAI,Committee,Noticias,Uncategorized(0)Perplexity AI announced what it calls the first hybrid local-server inference orchestrator at Computex 2026...
PERM: Psychology-grounded Empathetic Reward Modeling for Large Language Models
enero 19, 2026admin NUAI,Committee,Noticias,Uncategorized(0)arXiv:2601.10532v2 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly deployed in human-centric applications...
PerCoR: Evaluating Commonsense Reasoning in Persian via Multiple-Choice Sentence Completion
octubre 28, 2025admin NUAI,Committee,Noticias,Uncategorized(0)arXiv:2510.22616v1 Announce Type: new Abstract: We introduced PerCoR (Persian Commonsense Reasoning), the first large-scale Persian...
Pensieve Grader: An AI-Powered, Ready-to-Use Platform for Effortless Handwritten STEM Grading
julio 3, 2025admin NUAI,Committee,Noticias,Uncategorized(0)arXiv:2507.01431v1 Announce Type: cross Abstract: Grading handwritten, open-ended responses remains a major bottleneck in large...
PAT: Accelerating LLM Decoding via Prefix-Aware Attention with Resource Efficient Multi-Tile Kernel
diciembre 17, 2025admin NUAI,Committee,Noticias,Uncategorized(0)arXiv:2511.22333v2 Announce Type: replace-cross Abstract: LLM serving is increasingly dominated by decode attention, which is...
Partitioner Guided Modal Learning Framework
julio 17, 2025admin NUAI,Committee,Noticias,Uncategorized(0)arXiv:2507.11661v1 Announce Type: new Abstract: Multimodal learning benefits from multiple modal information, and each learned...
