Picture for Tatsuya Harada

Tatsuya Harada

DistML.js: Installation-free Distributed Deep Learning Framework for Web Browsers

Add code
Jul 01, 2024
Figure 1 for DistML.js: Installation-free Distributed Deep Learning Framework for Web Browsers
Figure 2 for DistML.js: Installation-free Distributed Deep Learning Framework for Web Browsers
Figure 3 for DistML.js: Installation-free Distributed Deep Learning Framework for Web Browsers
Viaarxiv icon

Style-NeRF2NeRF: 3D Style Transfer From Style-Aligned Multi-View Images

Add code
Jun 19, 2024
Viaarxiv icon

Discovering Multiple Solutions from a Single Task in Offline Reinforcement Learning

Add code
Jun 10, 2024
Viaarxiv icon

Stabilizing Extreme Q-learning by Maclaurin Expansion

Add code
Jun 07, 2024
Viaarxiv icon

MaGRITTe: Manipulative and Generative 3D Realization from Image, Topview and Text

Add code
Mar 30, 2024
Viaarxiv icon

Find n' Propagate: Open-Vocabulary 3D Object Detection in Urban Environments

Add code
Mar 20, 2024
Figure 1 for Find n' Propagate: Open-Vocabulary 3D Object Detection in Urban Environments
Figure 2 for Find n' Propagate: Open-Vocabulary 3D Object Detection in Urban Environments
Viaarxiv icon

HyperVQ: MLR-based Vector Quantization in Hyperbolic Space

Add code
Mar 18, 2024
Figure 1 for HyperVQ: MLR-based Vector Quantization in Hyperbolic Space
Figure 2 for HyperVQ: MLR-based Vector Quantization in Hyperbolic Space
Figure 3 for HyperVQ: MLR-based Vector Quantization in Hyperbolic Space
Figure 4 for HyperVQ: MLR-based Vector Quantization in Hyperbolic Space
Viaarxiv icon

Symmetric Q-learning: Reducing Skewness of Bellman Error in Online Reinforcement Learning

Add code
Mar 12, 2024
Figure 1 for Symmetric Q-learning: Reducing Skewness of Bellman Error in Online Reinforcement Learning
Figure 2 for Symmetric Q-learning: Reducing Skewness of Bellman Error in Online Reinforcement Learning
Figure 3 for Symmetric Q-learning: Reducing Skewness of Bellman Error in Online Reinforcement Learning
Figure 4 for Symmetric Q-learning: Reducing Skewness of Bellman Error in Online Reinforcement Learning
Viaarxiv icon

Robustifying a Policy in Multi-Agent RL with Diverse Cooperative Behavior and Adversarial Style Sampling for Assistive Tasks

Add code
Mar 01, 2024
Figure 1 for Robustifying a Policy in Multi-Agent RL with Diverse Cooperative Behavior and Adversarial Style Sampling for Assistive Tasks
Figure 2 for Robustifying a Policy in Multi-Agent RL with Diverse Cooperative Behavior and Adversarial Style Sampling for Assistive Tasks
Figure 3 for Robustifying a Policy in Multi-Agent RL with Diverse Cooperative Behavior and Adversarial Style Sampling for Assistive Tasks
Figure 4 for Robustifying a Policy in Multi-Agent RL with Diverse Cooperative Behavior and Adversarial Style Sampling for Assistive Tasks
Viaarxiv icon

Advancing Large Multi-modal Models with Explicit Chain-of-Reasoning and Visual Question Generation

Add code
Jan 18, 2024
Viaarxiv icon