CyberAgent AI Lab's repositories
SuperNormal
[CVPR 2024] Official implementation of "SuperNormal: Neural Surface Reconstruction via Multi-View Normal Integration"
pointcloud2gazebo
pointcloud2gazebo is a package that allows you to create a Gazebo World from a 3D point cloud.
nav2-keepout-zone-map-creator
nav2-keepout-zone-map-creator is a tool that allows you to create a Keepout Zone map from an Occupancy Grid Map and 3D point cloud.
text2palette
Implementation of "Multimodal Color Recommendation for Vector Graphic Documents" ACM MM'23
filtered-dpo
Introducing Filtered Direct Preference Optimization (fDPO) that enhances language model alignment with human preferences by discarding lower-quality samples compared to those generated by the learning model
regularized-bon
Code of "Regularized Best-of-N Sampling to Mitigate Reward Hacking for Language Model Alignment" (2024).
cropping-design-constraints
codes for evaluating image cropping under design constraints
mbr-anomaly
Code for "On the True Distribution Approximation of Minimum Bayes-Risk Decoding," NAACL 2024
adaptive-mbr
Code of "Hyperparameter-Free Approach for Faster Minimum Bayes Risk Decoding" 2024
annotation-efficient-po
Code of "Annotation-Efficient Preference Optimization for Language Model Alignment"
diverse-mbr
Code of "Generating Diverse and High-Quality Texts by Minimum Bayes Risk Decoding" 2024
model-based-mbr
Code of "Model-Based Minimum Bayes Risk Decoding" 2024
tdc-typography-generation
This repository contains codes for https://arxiv.org/abs/2309.02099
AdTEC
The AdTEC dataset is designed to evaluate the quality of ad texts from multiple aspects, considering practical advertising operations.
dte-ml-adjustment
Code for "Estimating Distributional Treatment Effects in Randomized Experiments: Machine Learning for Variance Reduction"
learning_games_with-memory_asymmetry
Codes for Memory Asymmetry Creates Heteroclinic Orbits to Nash Equilibrium in Learning in Zero-Sum Games
posthoc-control-moe
[TACL 2024] Code of "Not Eliminate but Aggregate: Post-Hoc Control over Mixture-of-Experts to Address Shortcut Shifts in Natural Language Understanding"