Ku Onoda

Master’s Student @ Matsuo-Iwasawa Lab, The University of Tokyo | Reinforcement Learning & Generative Models

[Ku Onoda @Ku_Onoda]

Can a better harness, not better weights, close the gap to frontier image models?
On multi-reference image generation, a 4B model becomes competitive with Nano Banana Pro.

A really fun project co-led with @shimao0114 🚀

[Yuta Oshima @shimao0114]

Our new preprint on harness optimization for image generation agents is out 🎉

A small open 4B model, competitive with Nano Banana Pro on multi-reference image generation — with no fine-tuning, just a better harness.

Harness optimization (letting a coding agent rewrite the code around a model) works well where answers can be checked, like code and math. Image generation relies on a noisy AI judge instead, and one lucky score can mislead the search.

AutoRef handles this with beam search: it keeps several promising harnesses instead of picking just one.

One discovered harness:
1️⃣ makes FLUX.2 [klein] 4B competitive with Nano Banana Pro
2️⃣ still works with a different number of reference images (searched with 4, works with 3–5)
3️⃣ works as-is on other image generation models, including a larger one (FLUX.2 [klein] 9B) and a different family (Qwen-Image)

Paper: https://t.co/DYZxg7PJct
Code: https://t.co/oiP8KO1XLT

w/ @Ku_Onoda @yusuke_iwasawa_ @szk_masa @ymatsuo @frt03_

[Ku Onoda @Ku_Onoda]

9/9 Grateful to my collaborators @PaavoParmas, @frt03_, @nissymori1, @shimao0114, @ishohei220, and @ymatsuo for making this work possible!

See the contribution statement in the attached image.

[Ku Onoda @Ku_Onoda]

1/9 🎉 Our paper "Multi-Axis Max@K Reinforcement Learning for Representative Diversity in Text-to-Image Generation" was accepted at #WACV2027 in Round 1!

An RL post-training method for generative models: we train sets of images to cover multiple target modes, letting different images represent different possibilities.

[Ku Onoda @Ku_Onoda]

8/9 See also very similar concurrent work by
@AntChen_ et al.: ROSA https://t.co/Mfa4ESn0P8
@RyanBoldi, @ishapuri101 et al.: VPO https://t.co/looZbxlNRr

[Third Intelligence @third_i_inc]

Third Intelligenceでは、遍在型AGIの実現に向けた研究の一環として、ARC-AGI-3（AA3）のコンペティションに参加しています。AA3は、AIが未知の課題に対して人間のように適応する能力を評価する、推論ベンチマークです。

私たちは、Beyond Transformerに向けた独自のアルゴリズム開発を研究の主軸としながら、そのサブトラックとしてAA3に挑戦し、現在、Leaderboardで2位にランクインしています。

今回のAA3では、個々の課題に特化し��テクニックではなく、未知の環境から構造やルールを捉え、それをもとに試行錯誤しながら次の行動を選択していく、より汎用的なアプローチを試しています。

※Kaggleのコンペティション規約に基づき、具体的な手法については、所定のマイルストーン到達またはコンペティション終了まで公開を控えています。

ARC-AGI-3 Leaderboard：
https://t.co/cGtZ8OLEFp

[Ku Onoda @Ku_Onoda]

Presenting our work today at #ICLR2026! 🚀🇧🇷

Better policy gradients for differentiable simulators. Come say hi!

Paper: https://t.co/Y05FYDYIUV

⏰ 10:30 AM – 1:00 PM
📍 Pavilion 4, Poster 4504