Seunghyuk Oh

JakeOh

furiosa-ai-dev

·

https://seunghyukoh.com

AI & ML interests

None yet

Recent Activity

authored a paper 21 days ago

AsyncOPD: How Stale Can On-Policy Distillation Be?

authored a paper 21 days ago

EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts

authored a paper 21 days ago

ParallelBench: Understanding the Trade-offs of Parallel Decoding in Diffusion LLMs

View all activity

Organizations

JakeOh 's datasets 39

JakeOh/iself-gsm8k-multiturn-llama1b

Viewer • Updated Dec 19, 2024 • 1.32k • 19 • 1

JakeOh/iself-baseline_preferences-gsm8k-llama1b

Viewer • Updated Dec 19, 2024 • 3.94k • 17

JakeOh/iself-gsm8k-strict_reset-llama1b

Viewer • Updated Dec 19, 2024 • 1.32k • 20

JakeOh/iself-preferences_gt-gsm8k-llama1b

Viewer • Updated Dec 19, 2024 • 8.79k • 29

JakeOh/iself-gsm8k-llama1b

Viewer • Updated Dec 19, 2024 • 8.79k • 19

JakeOh/iself-gsm8k-llama1b-8seeds

Viewer • Updated Dec 19, 2024 • 70.3k • 25

JakeOh/iself-sft_gt-gsm8k-llama1b

Viewer • Updated Dec 18, 2024 • 59.6k • 15

JakeOh/iself-preferences-gsm8k-llama1b

Viewer • Updated Dec 18, 2024 • 48.3k • 22

JakeOh/iself-sft-gsm8k-llama1b

Viewer • Updated Dec 18, 2024 • 59.6k • 19