Zelin Tan

Artemis0430

·

tanzelin430

AI & ML interests

Agent&RL&mlsys

Recent Activity

liked a dataset 2 days ago

Artemis0430/skilleval-v1

commentedon a paper 14 days ago

Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy

new activity 14 days ago

Artemis0430/skilleval-v1:Add task_categories to dataset card

View all activity

Organizations

None yet

authored a paper 15 days ago

SKT: Skill-Use Training at Scale via Verified Synthetic Data Generation

Paper • 2608.02287 • Published 17 days ago • 31

submitted a paper to Daily Papers 15 days ago

SKT: Skill-Use Training at Scale via Verified Synthetic Data Generation

Paper • 2608.02287 • Published 17 days ago • 31

authored a paper about 2 months ago

Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent

Paper • 2606.30616 • Published Jun 29 • 103

authored a paper 4 months ago

Stabilizing Rubric Integration Training via Decoupled Advantage Normalization

Paper • 2603.26535 • Published Mar 27 • 4

authored a paper 8 months ago

Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning

Paper • 2509.25300 • Published Sep 29, 2025 • 8

authored a paper 12 months ago

The Landscape of Agentic Reinforcement Learning for LLMs: A Survey

Paper • 2509.02547 • Published Sep 2, 2025 • 239