特徴量の気持ち (@t_Signull) profile picture

動画像認識芸人 博士(GoPro)

Mind your own business
Joined January 2011
Photo by 特徴量の気持ち (@t_Signull)Photo by 特徴量の気持ち (@t_Signull)Photo by 特徴量の気持ち (@t_Signull)Photo by 特徴量の気持ち (@t_Signull)Photo by 特徴量の気持ち (@t_Signull)Photo by 特徴量の気持ち (@t_Signull)Photo by 特徴量の気持ち (@t_Signull)Photo by 特徴量の気持ち (@t_Signull)Photo by 特徴量の気持ち (@t_Signull)Photo by 特徴量の気持ち (@t_Signull)
特徴量の気持ち retweeted
Two years ago, we released Genesis, a universal physics engine for robotics. Today, I’m excited to announce 🍎 Eden — a robot learning framework built from the ground up for agents, unleashing full potential of Genesis. One task definition. From simulation to real robots. Sim-to-sim and sim-to-real just got easier. Coding agents build tasks 1.6–4× faster than in Isaac Lab. 🧵 1/11
45
139
33
763
117,361
特徴量の気持ち retweeted
MotoGP championship standings after GTA V's release vs. right before GTA VI. #MotoGP
15
357
45
3,661
88,391
特徴量の気持ち retweeted
LISTEN: Air traffic control audio captures the moment a nationwide ground stop is issued, halting departures across the U.S. Transportation Secretary Sean Duffy says a “communication issue impacting all Air Route Traffic Control Centers” prompted the FAA’s order. Technicians are investigating. Departing aircraft are instructed to remain grounded until further notice. International arrivals will be handled on a case-by-case basis. Download the Fox News app or visit FoxNews.com for the latest updates.
205
1,240
107
4,768
2,107,421
特徴量の気持ち retweeted
【NHKニュース速報 06:45】 アメリカ全土の空港で航空機の運航を停止 「通信の問題」 米運輸長官
6,386
991
12,290
1,582,434
特徴量の気持ち retweeted
~1 year ago: AI coding didn't work ~0.5 year ago: agentic tasks failed ~now: nobody checks code + full automation What's missing? My first (real) attempt at AI coding was mid last year, mostly playing around with Copilot. It was still very much a vibe-coding experience and not ready for serious work. People oversold it -- lots of bugs and way too many iterations to be productive. In fairness, I gave up on it quite quickly. The real game changer was Opus 4.6 -- it needed precise instructions, but its execution was on another level. If you iterated on the plan until it was well-specified, it would turn each task into pretty decent code. However, it still struggled with longer-term reasoning, and with every iteration the chance of breaking something else went up -- agentic tasks in particular mostly failed. This changed over the past few months: agentic tasks now work quite well, and I'm trusting agents with much more complicated prompts -- if the underlying methods are well known, this works remarkably well. I'm particularly stunned by how well the VLMs inspect results and propose fixes on their own; 3D modeling is a prime example here but there are many other examples. Despite that progress, there are still missing pieces: - the main bottleneck seems to be prompting and the imperfect nature of language itself, i.e., I find it quite difficult to tell agents what I actually want them to do. - ideation / brainstorming still struggles with specific solutions that aren't mainstream. Especially for research projects, agents rarely come up with good ideas and auto-research loops are mostly limited to hyperparameter optimization. Given the current insane speed of progress, I'm extremely excited about what the next year brings. I've heard so many times now that "AI can't do x" -- and now we all take this for granted. I also really don't see things slowing down, since everything keeps getting easier to try out. Really looking forward to it!
16
9
109
7,967
特徴量の気持ち retweeted
プロンプト 「青いキューブをボックスに入れて」 等倍速再生でみるとこれぐらい時間がかかる
Fable5.2 DirectでSO-101動作 IKベースのRoboハーネスをFable5.2が自作してくれて(2時間ほど)、自然言語で汎用的に動作するようになった。
1
24
6
154
28,069
特徴量の気持ち retweeted
arXiv submissions are skyrocketing 42K new papers in October. Up 81% since January and nearly double the monthly volume at the end of 2024 Pangram analysis coming soon 👀
12
65
18
488
48,548
特徴量の気持ち retweeted
Meet GR00T 2, our new generation of world-action models (WAMs): it imagines how the physical world will unfold and generates the actions that get it there. One model runs on parallel grippers, dexterous hands, and humanoids. research.nvidia.com/labs/gea…
70
205
85
1,478
124,097
特徴量の気持ち retweeted
CoRL is like Costco but with egocentric data samples.
8
2
2
132
6,432
Noetra株式会社のエンジニアによるテックブログを開設しました。 NoetraのAI基盤モデル開発に関する取り組みや成果をはじめ、開発現場での試行錯誤や工夫などを、開発者の視点から分かりやすく発信していきます。 zenn.dev/p/noetra_techblog #Noetra
43
4
201
23,974
特徴量の気持ち retweeted
FUN. UNLIMITED. | GSX-10R The all-new GSX-10R, unveiled at #EICMA2026 #Suzuki #GSX10R
16
562
166
2,449
152,686
特徴量の気持ち retweeted
i've reproduced the results from the MIT blog post today on weight-space programming. but one additional result i have to add: this is a new, step-change emerging capability that's appeared in just the latest set of models.
218
804
272
7,818
606,359
特徴量の気持ち retweeted
We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math. It directly changed only 0.016% of weights, fixing 0.8B's reasoning loops & improving math up to 6x and even instruction following 3x, without gradients or training. We call this Weight-Space Programming: frontier LLMs can now natively read/write neural network weights! 🧵 Blog: rikiyat.github.io/blog/weigh…
Readers added context they thought people might want to know
LLM was given weights explicitly as text in prompt and used code/forward passes (per authors' logs) to ablate Qwen looping direction, a known thinking-mode issue per model card. Primarily fixed repetition in that mode, not general 'natively' improving weights/math. rikiyat.github.io/blog/weight-sp… github.com/RikiyaT/lm_und… huggingface.co/Qwen/Qwen3.5-0… huggingface.co/RikiyaT/Qwen3.…
2,367
7,257
5,753
55,946
10,059,030
特徴量の気持ち retweeted
【献本御礼】『マルチモーダルモデル入門』(栗田修平・品川政太朗・柳凜太郎・塩野大輝・高道慎之介・仁泉大輔・中村友彦・八木拓真・篠原崇之 著、技術評論社)をご献本いただきました。ありがとうございます! 各種モダリティに関して、近年の基盤モデルの発展がまとめられている感があり、自分の専門から少し離れたところの知識を得るのにもいい感じですね。 Transformer と LLM の基礎から、Vision and Language(LLaVA など)、音声・音楽・可聴音一般、動画、3次元データ、そして NExT-GPT のようなオムニモーダルモデルまで、とても幅広い内容が書かれています。 若手・中堅の実力派揃いの執筆陣で、モデルもデータセットも網羅的にまとめられていて、一冊、研究室、オフィスか自室にでも置いておいて、ちょっと「あれどうだっけ? 何があるっけ?」って時に取り出すのにも良さそうですね。 こういう網羅的なまとめ本を出すのは僕は苦手なので、頭が下がる思います🙇‍♂️。 link.amazon/B0dj7Q2B2
8
36
2,903
What a ride it's been 🤘 You've done Australia proud, Jack. All the best for the next chapter 🩵
12
288
12
3,007
26,640
2026 MFJ全日本ロードレース選手権シリーズ 第7戦 第58回 MFJグランプリ スーパーバイクレース in 鈴鹿 JSB1000クラス 決勝Race2 優勝は[1]中須賀 克行選手🏆 現役最後のレースを優勝し、有終の美を飾りました。 ナカスガサーンカッコ良すぎるよ…😭 #MFJGP #JRR #全日本ロードレース
7
584
67
2,685
69,364