Market Price Simulator

Scite is an AI research assistant that provides answers backed by scientific citations. It draws from a large database of full-text articles, including paywalled sources. The tool helps researchers explore topics, build reference lists, and verify claims. Scite also offers customizable settings and filters to refine research output.

Mnemosphere is an advanced AI research workspace designed for intellectually ambitious individuals, researchers, and academics. It offers a unique multi-model chat environment, allowing users to interact with and compare outputs from various frontier large language models simultaneously. Key capabilities include instant mind map generation for complex topics, facilitating deeper understanding and organization of information. This platform is ideal for those who need to manage messy research, accelerate knowledge discovery, and gain comprehensive insights by leveraging the strengths of different AI models. Mnemosphere aims to provide a sophisticated tool for navigating and synthesizing vast amounts of information, making it an invaluable asset for serious intellectual inquiry and academic pursuits.

Qeios is an open science platform that provides free, rapid, and transparent open access publishing. It offers unbiased open peer review for researchers. Qeios connects AI labs and startups with specialized experts for evaluations and collaborations. Qeios Quorum assists with human evaluations, RLHF, and high-impact collaborations.

REP is an ipython-based environment designed for conducting data-driven research. It emphasizes consistency and reproducibility in machine learning experiments. REP provides a toolbox for data scientists and machine learning engineers to streamline their research workflows. It is an open-source tool.

rome is a tool for locating and editing factual associations in GPT models. It implements Rank-One Model Editing (ROME) on auto-regressive transformers. The tool currently supports OpenAI's GPT-2 XL (1.5B) and EleutherAI's GPT-J (6B). It is designed for GPU-only operation.

SSL4MIS (Semi Supervised Learning for Medical Image Segmentation) is a collection of literature reviews and code implementations. It focuses on semi-supervised learning techniques applied to medical image segmentation. The tool supports research and development in medical AI. It includes resources for active learning and domain adaptation.