SynthLabs

AI & ML interests

Scaling up good synthetic reasoning. Post-training and synthetic data research lab.

Recent Activity

violetxi  authored a paper about 1 month ago

ResearchCodeBench: Benchmarking LLMs on Implementing Novel Machine Learning Research Code

violetxi  authored a paper about 1 month ago

Just Enough Thinking: Efficient Reasoning with Adaptive Length Penalties Reinforcement Learning

violetxi  authored a paper about 1 month ago

LitBench: A Benchmark and Dataset for Reliable Evaluation of Creative Writing

View all activity

Team members 18