projects
code of my research, coursework, side projects, etc.
packages/open-source projects
-
MagicBench: A Deception-Sensitive Cognitive Benchmark for LLMsThe first deception-sensitive cognitive benchmark for large language models, testing adversarial reasoning, metacognition, theory of mind, and causal inference through magic-trick understanding.
-
HarborHarbor is a framework for evaluating and optimizing agents and models in container environments.
-
Adversarial Robustness Toolbox (ART)ART provides tools that enable developers and researchers to evaluate, defend, certify and verify Machine Learning models and applications against the adversarial threats.
courseworks
coding basics
| Year | Name | Description | Link |
|---|---|---|---|
| 2020 | Coding Competition Solving List | This repository contains problems I completed in these years. |