WenyiWU0111
Follow
Stars
Official repo for the #tidytuesday project
Stanford NLP Python library for understanding and improving PyTorch models via interventions
Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vectors
[NeurIPS 2024 Spotlight] Code and data for the paper "Finding Transformer Circuits with Edge Pruning".
FastVideo is a lightweight framework for accelerating large video diffusion models.
Conversational Health Agents: A Personalized LLM-powered Agent Framework
DSPy: The framework for programming—not prompting—language models
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
Causal discovery algorithms and tools for implementing new ones
Experimental library integrating LLM capabilities to support causal analyses
Source code for Twitter's Recommendation Algorithm
LAVIS - A One-stop Library for Language-Vision Intelligence
Mono repo for the PhD course AI for Business Research (DSME 6635, S24)
Emotions recognition from audio signal using OpenSmile, PCA and set of classifiers from Scikit-learn library
codes for the paper Deep Learning Based Casual Inference for Combinatorial Experiments
DoubleML - Double Machine Learning in Python
Use advanced feature engineering strategies and select best features from your data set with a single line of code. Created by Ram Seshadri. Collaborators welcome.
Recommendation System using ML and DL
This list of writing prompts covers a range of topics and tasks, including brainstorming research ideas, improving language and style, conducting literature reviews, and developing research plans.
Code and notebooks for my Medium blog posts
nl-causal: nonlinear causal inference based on IV regression in Python
Python implementation of the original R sensemakr package: https://github.com/carloscinelli/sensemakr
A Python package for causal inference using Synthetic Controls
cem is a lightweight library for performing coarsened exact matching (CEM). CEM is a modern matching technique useful for causal inference on observational data.