ChartNet: Training Vision-Language Models to Understand Charts

ℹ️ EPISODE INFO

Released

August 6, 2026

Duration

5m

Channel

YC Root Access

Watch on YouTube

▶ Open ↗

📝 EPISODE DESCRIPTION

At our inaugural YCML at Startup School, YC Partner Ankit Gupta speaks with MIT PhD candidate Jovana Kondic about ChartNet, an open-source data generation pipeline and million-scale dataset for chart understanding. Charts require models to combine visual recognition, text understanding, and numerical reasoning. ChartNet generates diverse examples by translating charts into plotting code, augmenting that code, and rendering new images with corresponding tables, summaries, and reasoning traces. Training on ChartNet improved open-source models across a range of chart tasks and transferred to real-world benchmarks, showing how carefully structured synthetic data can give smaller models capabilities commonly associated with much larger systems. Apply to Y Combinator: https://www.ycombinator.com/apply Work at a startup: https://www.ycombinator.com/jobs

🎤 SPEAKERS

• Ankit Gupta

  host

  Host/interviewer for YC Root Access (Y Combinator), conducting the YCML interview segment.

• Jovana Kondic

  guest

  PhD candidate at MIT presenting ChartNet, a synthetic million-scale chart understanding dataset and pipeline for vision-language models.

🧾 EPISODE SUMMARY

In this episode of YC Root Access, featuring Ankit Gupta and Jovana Kondic, ChartNet: Training Vision-Language Models to Understand Charts explores chartNet generates massive synthetic chart data to boost VLM reasoning ChartNet targets chart understanding, which is hard for vision-language models because it requires accurate text reading plus numerical reasoning beyond typical natural-image perception.

🔗 RELATED EPISODES

Evaluating the Fine-Grained Planning Abilities of Web Agents

Any-Horizon Reasoning for Video Agents

LeanAgent: Lifelong Learning for Formal Theorem Proving

Zero-Shot Predictive Models for Relational Databases

Improving Small Language Model Reasoning With A* Search

Interpretability and Safety for Robot Foundation Models