NovaSky's picture

2 5 2

NovaSky

NovaSkyAI

·

AI & ML interests

None yet

Recent Activity

upvoted a paper about 7 hours ago

Jet-RL: Enabling On-Policy FP8 Reinforcement Learning with Unified Training and Rollout Precision Flow

published a model 2 months ago

NovaSky-AI/SA-SWE-32B

updated a dataset 2 months ago

NovaSky-AI/DeepResearch-Data

View all activity

Organizations

upvoted a paper about 7 hours ago

Jet-RL: Enabling On-Policy FP8 Reinforcement Learning with Unified Training and Rollout Precision Flow

Paper • 2601.14243 • Published 6 days ago • 9

upvoted a collection 9 months ago

SkyRL-Agent-v0

6 items • Updated May 7, 2025 • 5

upvoted 2 papers 11 months ago

S*: Test Time Scaling for Code Generation

Paper • 2502.14382 • Published Feb 20, 2025 • 63

The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks

Paper • 2502.08235 • Published Feb 12, 2025 • 59

upvoted a paper 12 months ago

LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!

Paper • 2502.07374 • Published Feb 11, 2025 • 40