Zochi
Zochi is the first AI system capable of autonomously completing the entire scientific research process, from hypothesis generation to peer-reviewed publication, producing state-of-the-art results. Unlike prior systems limited to narrow, predefined tasks, Zochi excels in addressing research challenges at the forefront of artificial intelligence. Its effectiveness is validated by multiple peer-reviewed publications accepted at ICLR 2025 workshops, underscoring Zochi's ability to generate novel and academically rigorous contributions. Zochi identified a critical bottleneck in AI development: cross-skill interference in parameter-efficient fine-tuning. When adapting models to multiple tasks simultaneously, improvements in one skill often degrade others. To address this, Zochi developed CS-ReFT (Compositional Subspace Representation Fine-tuning), focusing on representation editing rather than weight modifications.
Learn more
scienceOS
scienceOS is an AI-powered research platform built to accelerate scientific literature workflows by giving researchers fast, reliable access to a massive database, more than 225 million research papers via a chat-based interface. The core “AI science chat” lets you ask questions, get answers grounded in published literature, and even generate tables or diagrams summarizing findings. If you upload PDFs, the “multi-PDF chat” can parse up to eight documents per session and extract key passages, figures, and tables to help you digest papers quickly; it can also generate structured summaries of papers (e.g., intro, methods, conclusions), highlighting main findings, limitations, and key data. Alongside that, scienceOS includes an AI reference manager; you can store and organize up to 4,000 PDFs or citations in a personal or shared library, import external references (e.g., from Zotero), and chat with your own collection, useful for drafting literature reviews and building bibliographies.
Learn more
PapersFlow
PapersFlow is an AI research workspace designed to help academics and researchers organize, analyze, and write scientific content within a single integrated environment. It enables users to manage paper libraries using projects, collections, and tags while running AI-powered reading workflows that generate summaries and answer questions about each paper. It supports deep literature review processes through its DeepScan capability, allowing researchers to synthesize findings across multiple sources and uncover connections more efficiently. PapersFlow also includes collaborative LaTeX writing with real-time preview so users can move seamlessly from reading papers to drafting manuscripts without switching tools. Additional capabilities such as cross-paper comparison, linked knowledge-base notes, and code discovery from research papers help streamline complex academic workflows.
Learn more
Jenni
Jenni AI is an AI-powered research and academic writing platform designed to help researchers, students, and professionals read, write, organize, and cite academic content more efficiently. The platform combines AI-assisted writing, source-grounded autocomplete, citation management, and research discovery tools into one collaborative workspace built specifically for rigorous academic workflows. Jenni AI allows users to upload PDFs, import libraries from Zotero or Mendeley, search hundreds of millions of academic papers, and generate writing suggestions directly grounded in selected research sources. Every AI-generated claim can be traced back to the exact source paragraph or page, helping users verify information and reduce the risk of unsupported statements or hallucinations. The platform also includes AI chat across research libraries, literature review support, citation generation in over 2,600 styles, collaborative editing, and peer-review analysis tools.
Learn more