Gusti Triandi Winata's picture

1 7 15

Gusti Triandi Winata

sanggusti

·

https://sanggusti.tech

AI & ML interests

MLSys, RL/SSL, Applied ML

Recent Activity

upvoted a collection 2 days ago

Meta's Llama 3.2 multimodal models

upvoted a collection 2 days ago

Meta's Llama 3.2 language models & evals

liked a Space about 1 month ago

radames/nginx-gradio-reverse-proxy

View all activity

Organizations

sanggusti's activity

upvoted 2 collections 2 days ago

Meta's Llama 3.2 multimodal models

5 items • Updated Dec 13, 2024 • 32

Meta's Llama 3.2 language models & evals

14 items • Updated Dec 13, 2024 • 159

upvoted a paper 6 months ago

M-RewardBench: Evaluating Reward Models in Multilingual Settings

Paper • 2410.15522 • Published Oct 20, 2024 • 12

upvoted a collection 6 months ago

Multilingual RewardBench (M-RewardBench)

Multilingual Reward Model Evaluation Dataset and Results • 3 items • Updated Mar 5 • 4

upvoted an article 8 months ago

Article

Scaling robotics datasets with video encoding

Aug 27, 2024

• 40

upvoted 2 articles 10 months ago

Article

Putting RL back in RLHF

Jun 12, 2024

• 87

Article

Illustrating Reinforcement Learning from Human Feedback (RLHF)

Dec 9, 2022

• 237