yilihsu's starred repositories
segment-anything
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
mPLUG-DocOwl
mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding
transparent-background
This is a background removing tool powered by InSPyReNet (ACCV 2022)
self-refine
LLMs can generate feedback on their work, use it to improve the output, and repeat this process iteratively.
st-annotated-text
A simple component to display annotated text in Streamlit apps.
empath-client
analyze text with empath
self-discover
Implementation of Google's SELF-DISCOVER
fine-grained-sentiment
A comparison and discussion of different NLP methods for 5-class sentiment classification on the SST-5 dataset.
rumors-api
GraphQL API server for clients like rumors-site and rumors-line-bot
SAM-remove-background
Extract objection and remove background application using Segment Anything Model(SAM).
nlp-watermarking
Robust natural language watermarking using invariant features
amrlib-models
Repository for model used in amrlib
T5-Sentinel-public
Release repo for our work "Token Prediction as Implicit Classification to Identify LLM-Generated Text"
liwc-22-cli-python
Examples of how to call the LIWC-22 CLI from a Python script
figure-captioning-challenge
Scientific Figure Captioning | SciCap Challenge
DiverseSumm
Code and data for the NAACL 2024 paper "Embrace Divergence for Richer Insights: A Multi-document Summarization Benchmark and a Case Study on Summarizing Diverse Information from News Articles"
SCU-text-evaluation
Code for Paper: On the Role of Summary Content Units in Text Summarization Evaluation
Extract-Anything
RemoveBG PLUS: Extract Anything, an AI-powered universal matting vision model, goes beyond Remove BG, marking a revolutionary shift from merely eliminating backgrounds to empowering the ability to control every pixel with ultra-high precision.