How RAG work. by Jin Lu (428513)

“…Additionally, the integration of an LLM Code Interpreter enables the system to perform multi-step logical reasoning and execute Python code for precise calculations, significantly improving its ability to solve mathematical problems and handle complex queries. …”

OpenBookQA experimental results. by Jin Lu (428513)

“…Additionally, the integration of an LLM Code Interpreter enables the system to perform multi-step logical reasoning and execute Python code for precise calculations, significantly improving its ability to solve mathematical problems and handle complex queries. …”

AI2_ARC experimental results. by Jin Lu (428513)

“…Additionally, the integration of an LLM Code Interpreter enables the system to perform multi-step logical reasoning and execute Python code for precise calculations, significantly improving its ability to solve mathematical problems and handle complex queries. …”

TQA experimental results. by Jin Lu (428513)

“…Additionally, the integration of an LLM Code Interpreter enables the system to perform multi-step logical reasoning and execute Python code for precise calculations, significantly improving its ability to solve mathematical problems and handle complex queries. …”

E-EVAL experimental results. by Jin Lu (428513)

“…Additionally, the integration of an LLM Code Interpreter enables the system to perform multi-step logical reasoning and execute Python code for precise calculations, significantly improving its ability to solve mathematical problems and handle complex queries. …”

TQA Accuracy Comparison Chart on different LLM. by Jin Lu (428513)

“…Additionally, the integration of an LLM Code Interpreter enables the system to perform multi-step logical reasoning and execute Python code for precise calculations, significantly improving its ability to solve mathematical problems and handle complex queries. …”

ScienceQA experimental results. by Jin Lu (428513)

“…Additionally, the integration of an LLM Code Interpreter enables the system to perform multi-step logical reasoning and execute Python code for precise calculations, significantly improving its ability to solve mathematical problems and handle complex queries. …”

LBQANA python code + Merged Gene Expression Dataset from GSE10810, GSE17907, GSE20711, GSE42568, GSE45827, and GSE61304 for Breast Cancer Biomarker Discovery by M RN (9866504)

Fig 4. - mdciao: Accessible Analysis and Visualization of Molecular Dynamics Simulation Data by Guillermo Pérez-Hernández (21156182)

Overview of one by Guillermo Pérez-Hernández (21156182)

Pseudo live-stream of EEG data is generated, and a simple pick-and-place flowchart is designed for channel selection and filtering. by Gursimran Singh (575288)

Code by Baoqiang Chen (21099509)

Python implementation of a wildfire propagation example using m:n-CAk over Z and R. by Pau Fonseca i Casas (9507338)

“…</p><p dir="ltr"><br></p><p dir="ltr">## Files in the Project</p><p dir="ltr"><br></p><p dir="ltr">### Python Scripts</p><p dir="ltr">- **Wildfire_on_m_n-CAk.py**: This file contains the main code for the fire cellular automaton. …”

6. Motif Code Theory by William Terry (22279591)

“…<p dir="ltr">The Motif Code Theory (MCT) simulation code, mct_unified_code.py, is a Python 3.9 script that models the universe as a time-dependent directed multigraph G(t) = (V(t), E(t)) with N=10^7 vertices (representing quantum fields/particles) and edges (interactions). …”

Procedure for aligning the NeuroRat head model underlying the FEM simulations with the BBP circuit model. by Joseph James Tharayil (21416715)

Differences in compartment weights explain differences between EEG and ECoG. by Joseph James Tharayil (21416715)

Simplified calculation methods produce inaccurate signals. by Joseph James Tharayil (21416715)

BlueRecording simulates whisker-flick EEG. by Joseph James Tharayil (21416715)

BlueRecording simulates hippocampal LFP. by Joseph James Tharayil (21416715)

CompuCrawl: Full database and code by Richard Haans (6324669)

“…<p><br></p><p dir="ltr">This folder contains the full set of code and data for the CompuCrawl database. The database contains the archived websites of publicly traded North American firms listed in the Compustat database between 1996 and 2020—representing 11,277 firms with 86,303 firm/year observations and 1,617,675 webpages in the final cleaned and selected set.…”