Research

Two stacks of four browser-page views represent an attacked page and its clean twin, with the injection present only in the attacked stack.
ResearchNov 2, 2026BrowseSafe++: Building stronger defenses against real-world prompt injectionAn open benchmark and two lightweight detectors for browser agents.
  1. Oct 21, 2026A good teacher meets the student where they areA new self-distillation method that jointly trains teacher and student to improve model performance and training efficiency on complex reasoning and agentic tasks.
  2. Oct 12, 2026Building shared workspaces for people and agentsHow Perplexity Projects keep long-running work persistent, concurrent, and traceable.
  3. Oct 7, 2026Multimodal embeddings beyond a single vectorA new family of late-interaction models for text and image retrieval, with a shared embedding space across model sizes.

All publications

  1. BrowseSafe++: Building stronger defenses against real-world prompt injection
  2. A good teacher meets the student where they are
  3. Building shared workspaces for people and agents
  4. Multimodal embeddings beyond a single vector
  5. Contextual embedding beyond the gold passage
  6. Photon: Building a retrieval and ranking engine from scratch
  7. Escaping SPACE: Part I
  8. Learning from real-world experience
  9. CobbleDB: Rebuilding AI search storage for lower latency and cost
  10. Q2D-Web: Evaluating first-stage retrievers at scale