Feng Li

Research Scientist @GoogleDeepMind | Ex-intern @MetaAI (FAIR), @MSFTResearch, @ByteDanceTalk, @IDEACVR

[Feng Li @FengLiust]

I’ll be attending #CVPR2026 and will be at the Google booth on the morning of June 5. If you’d like to chat about research or anything interesting, feel free to set up a coffee chat☕️ or catch me at the booth!

[Feng Li @FengLiust]

@atasteoff congrats！

[Feng Li @FengLiust]

@xiaolonw @Meta Congrats!

[Yongyuan Liang @cheryyun_l]

We will present ROVER at #ICLR2026. Our poster session is at Pavilion 4 P4-#3016 on Fri, Apr 24th, 3:15 p.m. - 5:45 p.m. BRT. If you're interested in unified multimodal models, omnimodal generation and cross-modal reasoning, please check it out! I'd be happy to discuss our work remotely🥰

[Feng Li @FengLiust]

@baifeng_shi Wow Using Bagel in VLA!

[Feng Li @FengLiust]

@YifeiZhou02 Congrats Yifei!

[Feng Li @FengLiust]

@Red_Xiao_ Congrats!

[Feng Li @FengLiust]

@loganthorneloe @GoogleDeepMind Thanks Logan!

[Feng Li @FengLiust]

Thrilled to share that I’ve joined @GoogleDeepMind as a Research Scientist.

Excited for what’s ahead and the amazing people I’ll get to work with. 🚀

I am based in Kirkland, happy to meet old and new friends here (Feel free to ping me over WeChat or email)!

[Feng Li @FengLiust]

@xinyzng @GoogleDeepMind Thanks Xinyu!

[Feng Li @FengLiust]

@purshow04 @GoogleDeepMind Thanks Yuwei!

[Feng Li @FengLiust]

@JeffDean @GoogleDeepMind Thanks Jeff!🫡

[Feng Li @FengLiust]

@MuCai7 @GoogleDeepMind Thanks Mu!

[Feng Li @FengLiust]

@ai_andrew @GoogleDeepMind Thanks Andrew!

[Feng Li @FengLiust]

@runsen_xu @GoogleDeepMind Thanks Runsen!

[Feng Li @FengLiust]

@LearnAI_MJ @GoogleDeepMind It is in Washington near Seattle lol

[Feng Li @FengLiust]

@xyz2maureen Huge congratulations xueyan! All the best on your new adventure.

[Yongyuan Liang @cheryyun_l]

Unified multimodal models can generate text and images, but can they truly reason across modalities? 🎨
Introducing ROVER, the first benchmark that evaluates reciprocal cross-modal reasoning in unified models, the next frontier of omnimodal intelligence.

🌐 Project: https://t.co/qA5EPaK5s7
📄 Paper: https://t.co/UjLGs3ZFel
📂 Benchmark: https://t.co/2oyk8SyYOo

[Feng Li @FengLiust]

@jw2yang4ai @MSFTResearch @CVPR @AIatMeta Congrats Jianwei! So grateful for your mentorship at MSR and looking forward to your next exciting work!

[Haoqi Fan @HaoqiFan]

🚀 BAGEL — the Unified Multimodal Model with emergent capabilities and production-ready performance — is finally live!

Dive in here:
👉 https://t.co/smEMEK1jMn