Data Structure Display vs ConfidentLM

A novel data structure learning app, the most significant feature is that you can dynamically debug the data structure in this app, and visually observe the changes in the data structure during the operation. In this app you can learn the following data structures: 1. Linear structures, including arrays, linked lists, queues, stacks. Linear structures are the basis for other advanced data structures, as fine as advanced algorithms. 2. Tree structures, including binary tree, binary search tree, AVL tree, red-black tree, and heap. In this app, you can dynamically debug three traversals of the binary tree (including non-recursive traversal implementations), searching in the tree, balance adjustments in the AVL tree and red-black tree, and heap sorting. Give you the ability of handwritten red-black trees. 3. Graph structure, including the adjacency list storage representation of the graph structure, depth-first search and breadth-first search, finding the Euler path in the graph, topological sorting, maximum connected components, minimum spanning tree problem, and shortest single source Path problem. It also provides dynamic debugging of these classic graph algorithms. 4. The data structure introductory class will talk about the problem of the Tower of Hanoi. The algorithm that solves this problem is often recursive. This app provides dynamic debugging of the Tower of Hanoi problem, so you can no longer be confused about the recursive calls of the Tower of Hanoi.

Democratizing Education with "Self-Aware" Local AI Access to quality education should not depend on your internet connection. ConfidentLM is a research-backed educational tool designed to bring the power of Large Language Models (LLMs) to communities completely disconnected from the cloud. The Challenge: Silent Errors Local AI models are promising for offline learning, but they suffer from "hallucinations"—confidently stating incorrect facts. In an educational setting, these silent errors are dangerous for students who might unknowingly learn false information. 100% Offline: Powered by a Liquid Foundation Model (LFM2-1.2B) , this app runs locally on your device using 4-bit quantization. No data ever leaves your phone.The Solution: ConfidentLM Developed as a Stanford CS229 Machine Learning project, ConfidentLM introduces a safety layer for on-device models. Hallucination Detection: Unlike standard chatbots, ConfidentLM analyzes the model's internal "brain activity" (hidden states) to predict if an answer is likely a hallucination. Trustworthy Tutoring: By flagging unreliable answers, we create a "tutor in your pocket" that is safe enough for real-world learning. Join us in bridging the digital divide with AI that is accessible, efficient, and—most importantly—confident in its accuracy.