Mengzhang Cai

Forget bigger models: massive gains in document parsing accuracy are still possible through smarter data engineering alone.

Forget scaling laws, targeted data engineering—specifically multi-stage distillation and difficulty-aware sampling—allows an 8B model to outperform larger open-source financial LLMs.

Forget simplistic synthetic data: ChartVerse generates complex charts and reliable reasoning data from scratch, enabling an 8B model to outperform its 30B teacher in chart reasoning.