Yichen Feng

Master Student @UW

[Yichen Feng @YichenFeng_]

Excited to share our latest benchmark; we're really proud of what the team has built!

[Zhangchen Xu @zhangchen_xu]

🚀 We built Visual Aesthetic Benchmark (VAB). Arena is alive here: https://t.co/GKSvoJ5jAk

Aesthetic judgment is one of the hardest ceilings for AI to crack right now. Not generating images, but truly understanding what “looks good.”

We hand-curated 400 sets of artist works (fine art, photography, and illustration), featuring 2000+ hours of brand-new commissioned data created specifically for this benchmark — all grounded in 13K+ domain expert judgments across 7 core aesthetic dimensions (composition, lighting, technique, expression…) to ensure rigorous evaluation in highly subjective domains.

We asked 20+ frontier AI models to judge visual aesthetics (fine art, photography, illustration) against domain experts.
Frontier models are really not good at it yet.
Best model, Claude Sonnet 4.6 hit 26.5%. Human experts: 68.9%.

> Blog: https://t.co/XvEgwkmRqr
> Leaderboard: https://t.co/BEsHCgTmjC

[Yichen Feng @YichenFeng_]

@my_cat_can_code Sounds awesome, can’t wait to meet you all! 🙌

[Yichen Feng @YichenFeng_]

Our new work BadScientist honored with the Best Paper Award at Agents4Science 🏆.

Many thanks to the organizers and reviewers for the recognition — and I’d love to hear your thoughts or feedback!

[Fengqing Jiang @fengqing_jiang]

“Research on AI, by AI, for AI and all, shall not perish from the scientific community.”

Thrilled to share our new work BadScientist—honored with the Best Paper Award at Agents4Science 🏆.

[Yichen Feng @YichenFeng_]

Excited to share VisualSphinx! 660K logic puzzles that actually teach VLMs to visually reason. All open-sourced! 🚀

[Zhangchen Xu @zhangchen_xu]

🧩 VLMs can finally solve logic puzzles! We created VisualSphinx - a 660K synthetic vision logic dataset that boosts vision logical reasoning by 15-35% with RL. Full pipeline from 4K seed problems → 660K multimodal puzzles, all open-sourced! ✨

Website: https://t.co/aUgj1Tjcv7