Naoya Takahashi

Sr. Staff Research Scientist @SonyAI, PhD in Computer Science, Visiting Researcher @ETH_en Zürich. Multimodal AI (Vision, Audio), Robotics 🇨🇭🇯🇵

[Naoya Takahashi @zuNaoya]

I'm incredibly thrilled to share that our project on competitive robot table tennis, Ace, has been published today on the cover of @Nature

[Sony AI @SonyAI_global]

For 40+ years, building a robot that could rally with an elite human table tennis player at full speed was an unsolved problem. Sony AI's Ace research project set out to change that—and the results are now accepted for publication in @Nature and featured on the cover.

[Naoya Takahashi @zuNaoya]

Curious to see how much more competitive our table tennis robot Ace has become since the #Nature paper? Check out the latest match results against 9 professional players — including two-time Olympic medalist and 2017 World No. 5 Miu Hirano.

[Sony AI @SonyAI_global]

Since our @Nature paper, #Ace won against seven pro table tennis players, including two-time Olympic silver medalist Miu Hirano, and world No. 26 @KiharaMiyuu. Learn how improvements across #RL, hardware, #perception, and more helped close the gap: https://t.co/giu7Rj9Yxy

[Naoya Takahashi @zuNaoya]

She will cover our perception system that can measure the spin of high-speed, unaltered ball from a distance using event camera and active tracking.

[Naoya Takahashi @zuNaoya]

Attending CVPR and interested in physical AI, perception, event cameras, or table tennis? 🏓Stop by the Sony booth (#329) to meet Asude Aydin from my team! She will be presenting our recent #Nature paper on the first table tennis robot capable of beating professional players.🔥

[Naoya Takahashi @zuNaoya]

大変分かりやすい解説動画をありがとうございます！

[伊藤条太 @ItoJota1964]

ソニーAIロボットは如何にして卓球エリートに勝ったのか　論文から読み解くAIの潜在能力 https://t.co/orIIpPMCoI @YouTubeより

[Naoya Takahashi @zuNaoya]

Low latency perception, agile robot HW, and dynamic control enable Ace to return the ball even when it suddenly changes its flight trajectory at net contact. Check out our project page for more details.https://t.co/GT10H368Ak

[Sony AI @SonyAI_global]

What happens when a ball hits the net? In table tennis, net contact creates unpredictable trajectories. For Ace, Sony AI's physical AI research system, these rare events were one of the hardest real-world conditions to address.

[Naoya Takahashi @zuNaoya]

Check out the story behind our work on the first table tennis robot that compete with professional players under the official rules.
Incredibly proud of being a part of this project.
https://t.co/xgsElkd5Xx

[朝日新聞(asahi shimbun） @asahi]

AIロボット、卓球で人間に勝つ　全国大会選手と対戦、ソニーが開発 https://t.co/EFLuQJG1a3

ソニーAIなどの研究チームは、卓球の国内トップクラスの選手にも勝てるAI（人工知能）ロボットを開発した。8関節の腕でラケットを操り、スピンやネットインにも対応。

[Naoya Takahashi @zuNaoya]

We believe this is an important step towards fast and safe human-robot interaction in a dynamic environment.
It has been a privilege to lead the development of the advanced perception system and physics models for simulation.

[Naoya Takahashi @zuNaoya]

I'm incredibly thrilled to share that our project on competitive robot table tennis, Ace, has been published today on the cover of @Nature

[Sony AI @SonyAI_global]

For 40+ years, building a robot that could rally with an elite human table tennis player at full speed was an unsolved problem. Sony AI's Ace research project set out to change that—and the results are now accepted for publication in @Nature and featured on the cover.

[Naoya Takahashi @zuNaoya]

Ace outplayed several professional and elite players in table tennis for the first time, demonstrating very fast and robust perception, control, and robot hardware.

Project page: https://t.co/GT10H368Ak
Paper: https://t.co/kq5XyGH3V1

[Sony AI @SonyAI_global]

For 40+ years, building a robot that could rally with an elite human table tennis player at full speed was an unsolved problem. Sony AI's Ace research project set out to change that—and the results are now accepted for publication in @Nature and featured on the cover.

[Sony AI @SonyAI_global]

💫Proud to share that #FHIBE has been featured on the cover of @Nature. The issue spotlights images from our globally diverse, consent-driven dataset designed to benchmark fairness in AI. Read the full feature via Nature: https://t.co/QEW0gFf6oh

[Naoya Takahashi @zuNaoya]

Code: https://t.co/5ZUtgS8G1q

[Naoya Takahashi @zuNaoya]

Our paper titled "SilentCipher: Deep Audio Watermarking" got accepted in @ISCAInterspeech 2024. Watermarking signal introduced by SilentCipher is inaudible even in challenging band-limited and silent regions, yet is robust to variety of distortions.
https://t.co/p5RHt0kvnA

[Naoya Takahashi @zuNaoya]

@iclr_conf @eunsolc @katjahofmann @liu_mingyu @nanjiang_cs @guennemann @optiML @tkipf @CevherLIONS ヒキワリ納��

[DeepAI @DeepAI]

��� Lowkey Goated When Spatial Recordings Is The Vibe! 🎧 Check out this audio-visual dataset of real scenes with spatiotemporal annotations from @zuNaoya, Kazuki Shimada et al. 🔗 https://t.co/93gz2Aowj6 #SoundEvents

[Naoya Takahashi @zuNaoya]

We are presenting our text-query sound separation paper @iclr_conf on 3rd May. If you're around & interested in audio, SSL, multi-modal learning, CLIP, etc., please come to our booth at poster see soon 6, #27.

[Hao-Wen (Herman) Dong 董皓文 @hermanhwdong]

Happy to share that I will be presenting our sound separation paper at @iclr_conf in Kigali! 🥳

In this work, we proposed the first text-queried universal sound separation model that can be trained using only unlabeled noisy videos! 🤩

#ICLR2023

https://t.co/oWehiAS50Y

[Naoya Takahashi @zuNaoya]

Happy to share that our paper on diffusion-based singing voice vocoder got accepted to #ICASSP2023.
Demo: https://t.co/eocDGQpPU8

[AK @_akhaliq]

Hierarchical Diffusion Models for Singing Voice Neural Vocoder
abs: https://t.co/6qMgPGZeH5

[Naoya Takahashi @zuNaoya]

Excited to announce that 3 papers got accepted at #ICASSP2023 🥳.
Many thanks to wonderful co-authors.

[AI技術最新情報メディア | AI-SCHOLAR @ai_scholar]

D3Netは高密度な推定タスク、つまり入力画像の次元と同じ次元の推定が必要なセマンティックセグメンテーションや音源分離などのタスクに焦点を当てたネットワークです。
https://t.co/stgGHR9cBY