Lan Feng

PhD candidate @ EPFL | MS @ ETH Zurich | Data-Centric methods for CV, LLM and Autonomous Driving

[Lan Feng @LanFeng491270]

@Letian_Wang_6 @GoogleDeepMind Amazing!

[Letian Wang @Letian_Wang_6]

Can video generation models do for vision what LLMs did for language?

Introducing GenCeption from @GoogleDeepMind: one feed-forward video model for various vision tasks — SOTA, data-efficient, and emerging behaviors (ECCV 2026)

🌐 https://t.co/3rwVgTolZz

(1/8)

[Fan Nie @FanNie1208]

✨Thrilled to share that "#TAROT: Targeted Data Selection via Optimal Transport" has been accepted to #ICML25! 🎉

We introduce a general data selection framework that can also determine the optimal selection ratio, effective across diverse domains (e.g., AD, LLMs, and CV).