Katy Pak

embodied ai

[Dr.Jingle @drjingle]

罗老师总是直达事物的本质

[Katy Pak @PakKaty51306]

@zsl1880553 @wangbuai 错误的那是外公

[Katy Pak @PakKaty51306]

@YangG753781 @giantcutie666 男的赚的更多，男清本大模型

[Katy Pak @PakKaty51306]

@NewYoungpo @giantcutie666 男的工资更高

[Katy Pak @PakKaty51306]

@NotPrimadonna @muf82264 @giantcutie666 四篇A青云感觉有点勉强

[Katy Pak @PakKaty51306]

@luliniiii @yantanzhang 可是第二个女生不也是想睡么，没看懂你的意思

[Katy Pak @PakKaty51306]

@yantanzhang @ajshdhwiwnhs 哈哈哈说得好

[Haofei Xu @haofeixu]

Does 3D reconstruction have to be complex?

We answer this question with PointDiT (#ICML2026): a minimalist pixel-space Diffusion Transformer without bells and whistles.

We show that a plain ViT can estimate dense 3D point maps by operating directly on raw patches. No hybrid ViT+Conv architectures, no lossy VAEs, no complicated training losses. (1/5) 🧵👇

[Katy Pak @PakKaty51306]

@mofrymatic @mirrash7 for egohumandata

[Katy Pak @PakKaty51306]

@NFSC_Kagami @XiaoKooeye @wjf110 @grok 现在ai都用全世界的数据做训练的

[Airmodeling @airmodel00]

MediaPipe Hand Landmarker를 테스트해 봤는데,

구글은 진짜 미친놈이 맞습니다.
CPU만으로 이 정도 성능이 나온다고?

엄청 가볍고 손 추적도 상당히 잘 됩니다.

물론 손이 겹치거나 가려지면 추적이 흔들리긴 하지만
이건 다른 모델들도 비슷한 문제라 크게 단점은 아닌 것 같네요.

정말 인상적입니다.

[Katy Pak @PakKaty51306]

@airmodel00 这个能比hawor好么

[Katy Pak @PakKaty51306]

@LVTGW666 信都不要信，我男大在学校谈，我和她一个月就花AA花了一万多了

[Sharpa @SharpaRobotics]

Robots need to feel the world to operate in it.

Most manipulation policies today are tactile-blind. They either cannot interpret high-frequency tactile signals or treat them as a static channel. And the field lacks enough touch-rich datasets to train tactile-reactive policies at scale.

T-Rex was built to answer both. @Dantong_Niu and team, advised by @DrJimFan, @drfeifei, @JitendraMalikCV, @pabbeel @trevordarrell have tested whether a robot policy can react to high-frequency tactile signals the way human hands do, without giving up the generalization power of modern VLAs.

The result: 65% average success rate across 12 real-world tasks. +30 absolute points over the strongest baseline. In one year, tactile VLAs have gone from promising to outperforming non-tactile baselines like pi0.5 on dexterous tasks.

#Robotics #SharpaWave #Sharpa #EmbodiedAI #DexterousManipulation #TactileSensing #RobotLearning

Project link: https://t.co/1D7fCFHEZV

[ブルーアーカイブ公式 @Blue_ArchiveJP]

💎ブルアカプレゼントキャンペーン💎

春原シュン(水着)役 #伊藤静 さんのサイン入り色紙を抽選で1名様にプレゼント！

🔹応募方法
@Blue_ArchiveJP をフォロー！
このツイートをRT🔁で応募！

🔹締め切り
2026年6月28日(日)23:59まで

#ブルアカ

[Katy Pak @PakKaty51306]

@TequilaLost2734 @QifengZhai @DB_Commander 不不不，她显然没有发售，笑死

[Katy Pak @PakKaty51306]

@Cheerme22391029 @anblk984 山路两公里追一头野猪姐妹

[Katy Pak @PakKaty51306]

@bryanwangxin @yibingsg 她是怕遗产不给她吧，她又不是給谢霆锋跪的

[Diksha 🌸 @DikshaYrrr]

Gen-Z parents 💀

[Jenny Pan @jenpan_]

Robots need memory to handle complex, multi-step tasks. Can we design an effective method for this?

We propose MemER, a hierarchical VLA policy that learns what visual frames to remember across multiple long-horizon tasks, enabling memory-aware manipulation.

(1/5)