Mingyang Song's picture

In a Training Loop 🔄

9 9 19

Mingyang Song

Nickyang

·

nick7nlp

AI & ML interests

LRMs, Long-Context LLMs, LLM Judges, Many-Shot ICL

Recent Activity

upvoted a collection about 1 month ago

updated a model 3 months ago

Nickyang/ConciseR-Zero-7B-Preview

liked a Space 3 months ago

tencent/Hunyuan-MT-7B

View all activity

Organizations

None yet

authored 2 papers 7 months ago

SSR-Zero: Simple Self-Rewarding Reinforcement Learning for Machine Translation

Paper • 2505.16637 • Published May 22

Walk Before You Run! Concise LLM Reasoning via Reinforcement Learning

Paper • 2505.21178 • Published May 27 • 6

authored 3 papers 8 months ago

SS-Bench: A Benchmark for Social Story Generation and Evaluation

Paper • 2406.15695 • Published Jun 22, 2024

Can Many-Shot In-Context Learning Help Long-Context LLM Judges? See More, Judge Better!

Paper • 2406.11629 • Published Jun 17, 2024 • 1

FastCuRL: Curriculum Reinforcement Learning with Progressive Context Extension for Efficient Training R1-like Reasoning Models

Paper • 2503.17287 • Published Mar 21 • 11