8年間日本を見てきました。東大で学生も教えましたし客員准教授もやりました。日本の若いエンジニアや研究者、いろんな人とも話しました。日本に足りないのは、真なる競争です。空気を読む競争ではないです。

thrilled about this awesome initiative! super excited about reasoning models and building these datasets 🚀

SFT Memorizes, RL Generalizes arxiv.org/abs/2501.17161

always bet on people who spent their childhoods hacking video game ROMs

RL is notoriously sample inefficient. How can we scale RL on tasks much slower to simulate than rigid body physics, such as soft bodies? In our #ICLR2025 spotlight, we introduce both a new first-order RL algorithm, SAPO, and differentiable simulation platform, Rewarped. 1/n

Aerospace is a reason enough for me to switch back to mac from arch linux... this is the best tiling manager on mac os I've ever used github.com/nikitabobko/Ae…

My timeline is mixed with a lot of good news (e.g., promotion, job update) and April fool jokes since the Japanese academic year begins in April 😂

Just wrapped up the first full draft of my 🆕 Gaussian Splatting lecture 😅 Thinking of adding a voiceover … tempting 🤔

Big shoutout to Nicholas Pfaff for this incredible work! If you’re interested in scalable conditional scene generation for robotics, you should check this out! 🤖🔥

Imitation learning has a data scarcity problem. Introducing EgoDex from Apple, the largest and most diverse dataset of dexterous human manipulation to date — 829 hours of egocentric video + paired 3D hand poses across 194 tasks. Now on arxiv: arxiv.org/abs/2505.11709 (1/4)

Imagine if robots could fill in the blanks in cluttered scenes. ✨ Enter RaySt3R: a single masked RGB-D image in, complete 3D out. It infers depth, object masks, and confidence for novel views, and merges the predictions into a single point cloud. rayst3r.github.io

Presenting DemoDiffusion: An extremely simple approach enabling a pre-trained 'generalist' diffusion policy to follow a human-demonstration for a novel task during inference One-shot human imitation *without* requiring any paired human-robot data or online RL 🙂 1/n

TRI's latest Large Behavior Model (LBM) paper landed on arxiv last night! Check out our project website: toyotaresearchinstitute.github.io/lbm1/ One of our main goals for this paper was to put out a very careful and thorough study on the topic to help people understand the state of the

Because AI is an engineering discipline and not a scientific field, it's never possible to fully separate the properties of a given approach from those of its specific implementations. The artifact is the method.

同じく！米国大学院進学に興味ある人はいつでも連絡してください〜！

Happy to share that our work has been published in IEEE RA-L! 🥳 Takuro Kato, KO, Yoko Sasaki & Naoya Yokomachi: Congestion Mitigation Path Planning for Large-Scale Multi-Agent Navigation in Dense Environments 📄 ieeexplore.ieee.org/document/11122…