Every change we have logged at Perplexity AI, newest first, each with the page Perplexity AI published as the receipt and a plain statement of what it means for you.
16 items. Back to 7 Jul 2026. Research. Updated 3 Nov 2026.
The newest change logged at Perplexity AI is Perplexity AI Researchers Detail LoRA Recipe For Converting Four Language Models To Diffusion, dated 30 Oct 2026.
Written from the newest item on this page and from the ledger rows behind it. Newest event .
Where Perplexity AI stands, and what we hold on itPerplexity plans and pricesevery company
A paper associated with Perplexity AI describes BYOD, a LoRA-only method that converts standard autoregressive language models into diffusion language models without full retraining.
A new arXiv paper proposes a message-passing method for compressing large language model weights, the kind of efficiency work that underlies answer engines like Perplexity AI.
A new paper on compressing large models for edge devices matters to Perplexity AI and any company whose answer engine has to run inference away from a data center.
A new arXiv paper proposes training language models to reward meaning rather than exact wording, a shift relevant to answer engines like Perplexity.
A new arXiv paper tests KV-cache compression on a tiny on-device model and shows the perplexity metric, the word behind Perplexity AI's name, hides real quality losses that a new test catches.
Researchers tied to Perplexity AI's orbit published a paper describing Next-Concept Modeling, a coarse-to-fine method that generates text far faster than diffusion language models.
A new paper proposes a hypergraph defense for federated large language models, the kind of collaborative training an answer engine like Perplexity AI could one day rely on.
A paper measures candidate masking strategies by their Perplexity score, among other metrics, and finds the winner flips entirely once a Chinese BERT model shrinks to under nine million parameters.
A UK research team built OncoNoteBERT for oncology notes, a reminder that general tools like Perplexity's answer engine are not tuned for clinical text.
Filed here under Perplexity AI, a paper posted October 12, 2026 gives ResonatorLM style sequence models a readout phase that reads the current token instead of a fixed per-head setting.
A new paper describes attention manifolds, a technique that edits how transformer models route information, with relevance for answer engines like Perplexity.
A new knowledge graph based evaluation framework tests whether large language models genuinely understand context, a question that bears directly on answer engines such as Perplexity.
A new paper indexed alongside Perplexity AI's research tracking replaces some attention layers in small language models only when accuracy checks pass.
A single-author arXiv paper tests layer-skipping for efficient inference, the kind of cost problem answer engines like Perplexity AI's face at scale.
Researchers built NepLEGiT, a compact Nepali legal language model, a project relevant to how Perplexity and other answer engines might one day serve underserved languages.
A new arXiv paper details a reversible subword tokenizer that could interest search tools like Perplexity, which parses messy web text into answers.
Items here are written from Perplexity AI's own announcements, documentation and price pages, never from another publisher, and every item carries both the day it happened and the day we published it. How this page is made. Published by Kawsar. RSS feed for Perplexity AI alone.
