Yuki Nakata (chikuwait) @chiku_wait - Twitter Profile

@tess_taiwan ニセコはアンヌプリが比較的安めですが、宿代とか総額で高い＆混雑があるので、ニセコにこだわりが無いなら旭川エリアのぴっぷ・カムイはコスパ良いです！リゾート系ならトマムとか。高いですが、トマムに滞在する海外の方はそこまで滑らない＆道民でも行きにくい陸の孤島なので、意外と空いてます〜

1

0

133

Yuki Nakata (chikuwait) @chiku_wait

7 days ago

日本語、台湾華語、英語の辞書を買った。2カ国語を同時に勉強している身としては大変便利

0

5

0

185

Yuki Nakata (chikuwait) @chiku_wait

7 days ago

@tess_taiwan 家の近くに深夜まで営業するスキー場があって、仕事終わりのジム代わりです🏋️‍♂️ 休日はニセコやトマム、富良野など...楽しい生活です😌

1

0

121

Yuki Nakata (chikuwait) @chiku_wait

7 days ago

台湾に行きたいわん...🫠

0

3

0

146

chiku_wait retweeted

Sakana AI

@SakanaAILabs

10 days ago

Introducing DiffusionBlocks: Block-wise Neural Network Training via Diffusion Interpretation https://t.co/c9AvsRKybj What if we didn’t have to hold an entire neural network in memory to train it? Standard neural net training optimizes all parameters jointly. As a result, the memory required during training grows linearly with the depth of the network. In our #ICLR2026 paper, we propose DiffusionBlocks, a principled framework to train networks one block at a time, drastically reducing memory requirements while matching end-to-end performance. With DiffusionBlocks, we split the network into blocks and train them one at a time, so you only need memory for a single block. How? We explicitly assign each block a role: to move the representation a little closer to the target than the block before it did. That role turns out to be precisely what a diffusion model does, step by step. Each block only needs to optimize its own objective and can be trained independently. We validated this across five different architectures: • ViT • DiT • Masked diffusion • Autoregressive transformers • Recurrent-depth transformers In each case, performance is competitive with end-to-end training while using a fraction of the memory. This perspective also extends naturally to recurrent-depth (Looped) transformers, which apply the same network iteratively and normally require expensive backpropagation through time (BPTT). Viewed through DiffusionBlocks, we can replace those multiple iterations with a single forward pass during training. Read our paper and code, to learn more. Paper: https://t.co/CRj96VGYQn GitHub: https://t.co/eNW0K9Xh8E 🐟

55

2K

365

2K

854K

chiku_wait retweeted

CNCF

@CloudNativeFdn

16 days ago

@opentelemetry is officially a CNCF graduated project! 🎓🎉 OpenTelemetry has become the trusted de facto observability standard, backed by 12,000+ contributors from 2,800+ organizations and helping teams gain better visibility across distributed systems. Congrats to this incredible community! Read more about the milestone here: https://t.co/j8HCwF32GL

CloudNativeFdn's tweet photo. @opentelemetry is officially a CNCF graduated project! 🎓🎉

OpenTelemetry has become the trusted de facto observability standard, backed by 12,000+ contributors from 2,800+ organizations and helping teams gain better visibility across distributed systems.

Congrats to this incredible community! Read more about the milestone here: https://t.co/j8HCwF32GL

2

248

66

24

35K

chiku_wait retweeted

Hirofumi Tsuruta @tsurubee3

15 days ago

Today at #MLSys2026, I will be presenting our work on "SAKURAONE: An Open Ethernet-Based AI HPC System and Its Observed Workload Dynamics in a Single-Tenant LLM Development Environment." Join us at Poster Session 3 (Thu 21 May, 6:00pm~8:00pm). Paper: https://t.co/LdJeUtlrBz