Seunghyuk Oh

JakeOh's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 4 papers 2 days ago

AsyncOPD: How Stale Can On-Policy Distillation Be?

Paper • 2606.24143 • Published Jun 23 • 31

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

Paper • 2606.18967 • Published Jun 17 • 24

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

Paper • 2510.04767 • Published Oct 6, 2025 • 28

Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoning

Paper • 2406.08527 • Published Jun 12, 2024 • 1

upvoted a paper 6 days ago

Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling

Paper • 2607.02980 • Published Jul 3 • 84

upvoted a paper about 1 month ago

AsyncOPD: How Stale Can On-Policy Distillation Be?

Paper • 2606.24143 • Published Jun 23 • 31

upvoted a paper about 2 months ago

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

Paper • 2606.18967 • Published Jun 17 • 24

liked a dataset 3 months ago

nvidia/SWE-Hero-openhands-trajectories

Viewer • Updated May 8 • 34.3k • 1.63k • 21

upvoted a collection 3 months ago

swe-zero-to-swe-hero

Collection

Datasets and Models for SWE-ZERO to SWE-HERO paper (https://arxiv.org/abs/2604.01496) • 3 items • Updated 15 days ago • 7

liked a dataset 3 months ago

nvidia/SWE-Zero-openhands-trajectories

Viewer • Updated May 5 • 318k • 2.47k • 18

upvoted a paper 3 months ago

RLDX-1 Technical Report

Paper • 2605.03269 • Published May 5 • 128