s1wase Profile Banner
Shun Iwase Profile
Shun Iwase

@s1wase

Followers
983
Following
10K
Media
107
Statuses
3K

Love research and climbing / Ph.D. student @CMU_Robotics

Mountain View, CA
Joined July 2014
Don't wanna be here? Send us removal request.
@s1wase
Shun Iwase
11 days
RT @mangahomanga: Presenting DemoDiffusion: An extremely simple approach enabling a pre-trained 'generalist' diffusion policy to follow a h….
0
47
0
@s1wase
Shun Iwase
28 days
(4/4 🧵) I’ll also be on the job market starting this October—happy to connect and chat about opportunities.
0
0
3
@s1wase
Shun Iwase
28 days
(3/4 🧵) If you're interested in our work, please swing by our poster session at 3 p.m. on Saturday, June 14! We're happy to discuss zero-shot 3D reconsturction, grasp pose prediction and beyond!.
1
0
1
@s1wase
Shun Iwase
28 days
(2/4 🧵) This project is a wonderful collaboration with TRI and Woven by Toyota! Huge thanks for the support that made this research possible! 📷.@ZakharovSergeyN @mzubairirshad @robo_kat @vitorguizilini @RaresAmbrus @kkitani.
1
0
0
@s1wase
Shun Iwase
28 days
#CVPR2025 starts in two days, and can’t wait to share our new work! 🎉 We present ZeroGrasp, a unified framework for 3D reconstruction and grasp prediction that generalizes to unseen objects. Paper📄: Webpage🌐:(1/4 🧵)
2
12
52
@s1wase
Shun Iwase
1 month
RT @BDuisterhof: Imagine if robots could fill in the blanks in cluttered scenes. ✨ Enter RaySt3R: a single masked RGB-D image in, complete….
0
52
0
@s1wase
Shun Iwase
2 months
RT @ryan_hoque: Imitation learning has a data scarcity problem. Introducing EgoDex from Apple, the largest and most diverse dataset of de….
0
95
0
@s1wase
Shun Iwase
2 months
Big shoutout to @NicholasEPfaff for this incredible work! If you’re interested in scalable conditional scene generation for robotics, you should check this out! 🤖🔥.
@NicholasEPfaff
Nicholas Pfaff
2 months
Want to scale robot data with simulation, but don’t know how to get large numbers of realistic, diverse, and task-relevant scenes?. Our solution:.➊ Pretrain on broad procedural scene data.➋ Steer generation toward downstream objectives. 🌐 🧵1/8
1
3
10
@s1wase
Shun Iwase
3 months
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 😂.
0
0
10
@s1wase
Shun Iwase
3 months
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.
0
0
4
@s1wase
Shun Iwase
4 months
RT @etaoxing: RL is notoriously sample inefficient. How can we scale RL on tasks much slower to simulate than rigid body physics, such as s….
0
63
0
@s1wase
Shun Iwase
4 months
RT @yongyuanxi: always bet on people who spent their childhoods hacking video game ROMs.
0
1
0
@s1wase
Shun Iwase
5 months
RT @hillbig: SFT Memorizes, RL Generalizes
0
3
0
@s1wase
Shun Iwase
5 months
RT @sedrickkeh2: thrilled about this awesome initiative! super excited about reasoning models and building these datasets 🚀.
0
2
0
@s1wase
Shun Iwase
5 months
RT @shanegJP: 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。.
0
420
0
@s1wase
Shun Iwase
5 months
タリンまた行きたいなー.
@_kei18
Keisuke Okumura
5 months
初めてヨーロッパに来たときは20代前半で、SIと一緒にヘルシンキ🇫🇮→タリン🇪🇪→ベルリン🇩🇪→プラハ🇨🇿→ミュンヘン🇩🇪と回ったのだけど、それから数年をヨーロッパで過ごすことになるとは思ってなかった、感傷に耽る旅先.
1
0
1
@s1wase
Shun Iwase
6 months
Does #CVPR2025 have a clear policy on concurrent work? An ECCV '24 paper which was published a month and half before the CVPR dealine could be considered concurrent? I know ICLR has explicit guidelines, but I couldn’t find anything similar for CVPR.
1
0
4
@s1wase
Shun Iwase
7 months
Regarding the MS robotics program at CMU, students typically have a good chance to get some sort of financial support since it’s a research-based program. It’s not guaranteed and I agree that the fees are quite expensive though.
@shishirny
Shishir Kolathaya
7 months
I was just going through the MS robotics programs in the USA, and was utterly shocked by the fees that the students have to pay. Some are shown below. All are in INR. UMich: 76 lakhs.CMU: 1 crore.UPenn: 75 lakhs.Georgia Tech: 63 lakhs.Oregon State: 61 lakhs. 1/5.
0
0
6
@s1wase
Shun Iwase
7 months
RT @jbhuang0604: The slide is bad, her response to an audience is even worse…. “Maybe there is one, maybe they are common, who knows what.….
0
21
0
@s1wase
Shun Iwase
7 months
RT @zhengyiluo: As I was developing the SMPL Humanoid (the one used here), this was the type of result I dreaming about. Mind-blowing res….
0
11
0