Welcome to Chicago Human+AI Lab (CHAI)!
Our goal is to build the best AI for humans. We are most interested in the following applications (ordered randomly):
We are always looking for motivated postdocs, PhD students, and undergraduates who are interested in NLP, data science, computational social science, or machine learning! Please read this FAQ if you are interested.
Schedule and Syllabus for Human-Centered Machine learning.
This is the official repository for HypoGeniC (Hypothesis Generation in Context) and HypoRefine, which are automated, data-driven tools that leverage large language models to generate hypothesis fo…
Active Example Selection for In-Context Learning (EMNLP'22)
Introduces hybrid spectral operators (HSOs) that combine continuous and discrete spectral properties, proving their spectrum can be decomposed into continuous and discrete parts with specific lattice structure properties.
Establishes theoretical upper bounds on the probability of generating novel mathematical structures using entropy and topological invariants of the solution space.
Proves that spectral graph neural networks can approximate any arithmetic function with guaranteed precision and numerical stability bounds.
Introduces quantum-persistent homology rings (QPHRs) and proves a fundamental inequality relating their dimension to quantum Betti numbers, providing a new framework for analyzing quantum systems through topological features.
Proves that neural networks can discover mathematical patterns with an optimal convergence rate of O(1/√n) under epsilon-regularity conditions, providing the first theoretical framework for automated mathematical discovery.
Proves that automated geometric theorem discovery requires O(n^3 log n) computational resources to find theorems of length n with high probability, establishing the first rigorous complexity bounds for this problem.
Proves stability bounds for persistent homology when computed on metric spaces that change continuously over time, showing that small changes in the underlying metric lead to controlled changes in the topological features.
Combines topological data analysis with dynamical systems theory by extending persistence diagrams to include Lyapunov exponents and stability measures, enabling better analysis of complex dynamical systems.
Introduces a new class of operators that generalize Fibonacci sequences to Hilbert spaces, showing they possess fractal-like spectral properties with applications to quantum systems.
This organization has no public members. You must be a member to see who’s a part of this organization.
Loading…
Loading…
