Picture for Toshiki Kataoka

Toshiki Kataoka

Preferred Elements, Inc.

Entropy Controllable Direct Preference Optimization

Add code
Nov 12, 2024
Figure 1 for Entropy Controllable Direct Preference Optimization
Figure 2 for Entropy Controllable Direct Preference Optimization
Figure 3 for Entropy Controllable Direct Preference Optimization
Figure 4 for Entropy Controllable Direct Preference Optimization
Viaarxiv icon

PLaMo-100B: A Ground-Up Language Model Designed for Japanese Proficiency

Add code
Oct 10, 2024
Figure 1 for PLaMo-100B: A Ground-Up Language Model Designed for Japanese Proficiency
Figure 2 for PLaMo-100B: A Ground-Up Language Model Designed for Japanese Proficiency
Figure 3 for PLaMo-100B: A Ground-Up Language Model Designed for Japanese Proficiency
Figure 4 for PLaMo-100B: A Ground-Up Language Model Designed for Japanese Proficiency
Viaarxiv icon

ChainerRL: A Deep Reinforcement Learning Library

Add code
Dec 09, 2019
Figure 1 for ChainerRL: A Deep Reinforcement Learning Library
Figure 2 for ChainerRL: A Deep Reinforcement Learning Library
Figure 3 for ChainerRL: A Deep Reinforcement Learning Library
Figure 4 for ChainerRL: A Deep Reinforcement Learning Library
Viaarxiv icon

Spectral Normalization for Generative Adversarial Networks

Add code
Feb 16, 2018
Figure 1 for Spectral Normalization for Generative Adversarial Networks
Figure 2 for Spectral Normalization for Generative Adversarial Networks
Figure 3 for Spectral Normalization for Generative Adversarial Networks
Figure 4 for Spectral Normalization for Generative Adversarial Networks
Viaarxiv icon