FunAI

Research lab led by @y_m_asano at @utn_nuremberg. We conduct fundamental AI research and develop core technology for future Foundation Models.

[Oishi Deb @DebOishi]

Happening Now! Come to VGI workshop @CVPR in Room 703 to listen to the excellent keynote speakers: Robert Geirhos @GoogleDeepMind; @AdtRaghunathan @CSDatCMU; @mattdeitke @Meta; @y_m_asano @funailab; @alexgkendall @wayve_ai; Andrea Vedaldi; Alexei Efros; Kristen Grauman @CVPRConf

[Yuki @y_m_asano]

Looking forward to speaking here at ~11:30 room 703. Spoiler slide below 👇

[FunAI @FunAILab]

Come join us!

[Yuki @y_m_asano]

🎉[openings] I’m hiring postdoctoral researchers to join our @FunAILab at UTN through the Alexander von Humboldt Research Fellowship (@AvHStiftung), via the Henriette Herz Scouting Programme.

As a Henriette Herz Scout, I can nominate outstanding international researchers for this fellowship route. I’m especially keen to hear from candidates working on multimodal learning, video and image pretraining, and post-training.

Fellows would be hosted in our lab at UTN and work closely with us on these topics.

Key requirements:
* finished your doctoral studies less than 4 years ago or will finish in the next 6 months
* did not live/work in Germany in the last 10 years
* applications from female, trans* and/or non-binary candidates are highly encouraged!

Interested? Please send a short note with your CV, PhD year, current affiliation, 2–3 key publications, and a few lines on how your work connects.

Please share! 🔀

[FunAI @FunAILab]

Sakana means fish in Japanese.

[Yuki @y_m_asano]

Today we visited Japan's hottest AI startup @SakanaAILabs🎏🇯🇵!
We met their research scientists and discussed the implications and impact of some their works like "The AI scientist" and "Continous Thought Machines".
We presented our @FunAILab works, "Better Language Models Exhibit Higher Visual Alignment" and "Data Repetition Beats Data Scaling in Long-CoT Supervised Fine-Tuning". Got lots of cool questions and discussions! Thanks, Masanori Suganuma, @_yutaroyamada, @ciaran_regan_

[FunAI @FunAILab]

@gatheluck @noagarciad

[FunAI @FunAILab]

Today we had a joint workshop!
We got to know each other's research directions and make some personal connections!

@AIST_EN, @TUS_PR_en, @FragileGoodwill, @noagarciad

[FunAI @FunAILab]

Start of our workshop, organised by our postdoc fellow @FragileGoodwill!
Today we'll be getting to know each other's research directions and make some personal connections!

@AIST_EN, @TUS_PR_en, and @noagarciad and more: https://t.co/yDS9DCvZth

'cc @HirokatuKataoka

[FunAI @FunAILab]

The next two weeks our lab will be in.. Japan!!

We'll visit @AIST_EN, @SakanaAILabs, @WbyT_Tech, @SonyAI_global , @jouhouken (NII), @TUS_PR_en and @RIKEN_JP.

We'll report what we learn, so come with us on this journey!

[Yuki @y_m_asano]

[new CVPR'26 paper]
🔄 SSL works great when you have tons of data.
But in 3D… we don’t.
High-quality 3D scans are expensive, slow, and hard to scale. So what if we could pretrain 3D models without any real 3D scans? 1/

[Yuki @y_m_asano]

Group picture of our @ELLISforEurope @Ellis_Amsterdam Foundation Model PhD school! 👏 🎉 @CSProfKGD @cgmsnoek @robrombach @FrankRHutter @YGandelsman @eliricci_ @nuriaoliver @sainingxie @PascalMettes, @KatiaShutova Hinrich Schütze, Robert Geirhos

[FunAI @FunAILab]

In other news: Four members of the lab just finished their first marathon in Rome!! Congratulations 🎉 💪 ☀️

[Kosta Derpanis (sabbatical in Zurich) @CSProfKGD]

Spending the day in Nuremberg with @y_m_asano and his group ❤️

Missing the bus is not going to deter us, the talk must go on! 🤓

[Yuki @y_m_asano]

Happy to share what we've been cooking! 🎊🎊

Our next iteration of the ELLIS PhD school is set to be an *absolutely amazing* one with this stellar lineup of speakers. ..And we even have some more speakers to be confirmed. 👀

If you haven't yet, go apply :)

[Yuki @y_m_asano]

@FunAILab + CVMP Lab of @EddyIlg retreat: ☑.
From mountains to hackathon to good food, we've had some intense but good days with lots of new ideas 🎉.

[Yuki @y_m_asano]

Now finally accepted at @emnlpmeeting!

I think the technique and high-level ideas i) allow bidirectional attention for prompt & ii) (maybe) process input-query differently from answer generation will stick around.

[Yuki @y_m_asano]

Today we release Franca, a new vision Foundation Model that matches and sometimes outperforms DINOv2.
The data, the training code and the model weights (with intermediate checkpoints) are open-source, allowing everyone to build on this.

Methodologically, we introduce two new SSL components, one is a multi-granularity SK clustering loss that utilizes Matryoshka representations and a quick post-pretraining scheme to remove unwanted spatial biases.

This is the result of a close and fun collaboration @valeoai (in France) and @FunAILab (in Franconia)

[Ryousuke Yamada @FragileGoodwill]

Hello FunAI Lab at UTN 👋

I’m excited to start a new chapter of my research journey here in Nuremberg as a visiting postdoc.

Excited for inspiring collaborations and impactful research ahead with @y_m_asano and the amazing students😀

[Yuki @y_m_asano]

LoRA et al. enable personalised model generation and serving, which is crucial as finetuned models still outperform general ones in many tasks. However, serving a base model with many LoRAs is very inefficient! Now, there's a better way: enter Prompt Generation Networks, presented today @BMVCconf

[Adina Yakup @AdinaYakup]

Is the community trying to surprise us today? 🤯
Because these benchmark-related papers from different research labs all dropped on the Daily Papers page at once! 🎉📑https://t.co/vE0f1FcZwF

✨ LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models by Opendata lab
✨ MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models by @richardxp888
✨ MEGA-Bench: Scaling Multimodal Evaluation to over 500 Real-World Tasks by the TigerLab
✨ LiveXiv -- A Multi-Modal Live Benchmark Based on Arxiv Papers Content by @TelAvivUni @IBMResearch
✨ Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models by @PKU1898 @AlibabaGroup
✨ TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models by @MuCai7
✨ LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory by @DiWu0162 @TencentGlobal
✨ TVBench: Redesigning Video-Language Evaluation by @FunAILab
@_akhaliq

[Yuki @y_m_asano]

Today, we're introducing TVBench! 📹💬
Video-language evaluation is crucial, but are we doing it right? We find that current benchmarks fall short in testing temporal understanding. 🧵👇