LLaVA-series researcher reflects on 8-year journey from Didi intern to VLM builder
liuziwei7 · x · 2026-09-20
Researcher Brian Bo Li shares that his work has joined the CS-xxx course series. He started learning AI via the same series during a Didi internship eight years ago, began his PhD in 2022, trained vision-language models with Chunyuan Li in 2023, and joined the LLaVA-series development in 2024. He says he'll focus on shipping better models going forward.
More from Companies & People
- Taylor Lorenz flips: X is better than ever, everyone came crawling back — elonmusk · 2026-09-20
- Blogger: 'Autonomous' AI Agent Hype Distracts From What Are Plain Felonies — mjdramstead · 2026-09-20
- How much math do AI engineers actually need vs AI researchers? — ashishllm · 2026-09-20
- Cisco: 85% of companies test AI agents, only 5% deploy in production — emmanuelvivier · 2026-09-20
- Microsoft publishes MAI model code of conduct putting human control above autonomy — emmanuelvivier · 2026-09-20
- RL environment companies now outsource QC to third parties at $50k/month each — himanshustwts · 2026-09-20