Muhammad Augi

I Learn

[Muhammad Augi @lovmamartya]

3 reason to stay alive in this fucking crazy world
1. One Piece
2. Quantum Supremacy
3. My Kid

[John Preskill @preskill]

Very articulate mathematicians pondering the future of math.
https://t.co/pnjkbX9uOm

[Chutney💥 @ChutneyXCVII]

This, Chachu and Black Tower to read weekly, I'm eating good with my new series

[light @reprompting]

reading about the the anatomy of a triton attention kernel today

https://t.co/9AiWQstLaU

[Fei-Fei Li @drfeifei]

I'm so excited that our @theworldlabs team has achieved a major milestone today! Introducing Atlas - a first of its kind multimodal world model trained from scratch! 🚀

Atlas is capable of generating frames with pixel-perfect camera control, reconstructing large scenes from as few as one single input image, simulating space-time by reframing videos, natively outputting 3D spaces from one or more input images, composing multiple posed images into a consistent 3d world, and more! This is the best camera conditioned world model ever, opening doors to many possible use cases from VFX to robotics. I'm so so so proud of our team!♥️

[Kimi.ai @Kimi_Moonshot]

Introducing 𝑨𝒕𝒕𝒆𝒏𝒕𝒊𝒐𝒏 𝑹𝒆𝒔𝒊𝒅𝒖𝒂𝒍𝒔: Rethinking depth-wise aggregation.

Residual connections have long relied on fixed, uniform accumulation. Inspired by the duality of time and depth, we introduce Attention Residuals, replacing standard depth-wise recurrence with learned, input-dependent attention over preceding layers.

🔹 Enables networks to selectively retrieve past representations, naturally mitigating dilution and hidden-state growth.
🔹 Introduces Block AttnRes, partitioning layers into compressed blocks to make cross-layer attention practical at scale.
🔹 Serves as an efficient drop-in replacement, demonstrating a 1.25x compute advantage with negligible (<2%) inference latency overhead.
🔹 Validated on the Kimi Linear architecture (48B total, 3B activated parameters), delivering consistent downstream performance gains.

🔗Full report:
https://t.co/u3EHICG05h

[Nassim Nicholas Taleb @nntaleb]

Most of what was produced in academia today is noise, some 100% (performative academia), some ~90-99% (science).

Most of what was produced by the baker today is signal.

[Omer Jacoby @jacodesby]

Apple Neural Networks are so fast that you can now build off axis projections that use glass shaders and PBR lighting

[Anemll @anemll]

This is cool.
It might be possible to completely rebuild ANE dev pipeline if we can bypass ANECompiler and CoreML/MIL architecture to map modern ML workflows onto the ANE on "bare metal" level.

https://t.co/Cb1dGsYjoy

[Dr. Ganapathi Pulipaka 🇺🇸 @gp_pulipaka]

Matrix Calculus for Machine Learning and Beyond! - Free eBook! @MIT

A Free 2025 MIT textbook by

Alan Edelman
Steven G. Johnson
Paige Bright

Connecting Matrix Calculus Directly to Modern Machine Learning.

Covers:

• Matrix + Vector Derivatives
• Jacobian + Hessian
• Matrix factorizations
• Optimization
• Reverse-Mode differentiation
• Backpropagation
• Automatic Differentiation
• Derivatives through ODE
• ML-Oriented Applications

An in depth mathematical bridge from Linear Algebra, Calculus, Optimization, Backpropagation, and Machine Learning.

#BigData #Analytics #DataScience #AI #MachineLearning #IoT #IIoT #PyTorch #Python #RStats #TensorFlow #Java #JavaScript #ReactJS #GoLang #CloudComputing #Serverless #DataScientist #Linux #Mathematics #Programming #Books #Coding #100DaysofCode

Free eBook:
https://t.co/kUEhsJSvfr

[Probably Approximately Correct @PAClearning]

Halo, untuk yang datang ke launching kelas Quant with LLM kemarin. Berikut adalah hasil dari output LLM nya:

https://t.co/kogEJRj35o

[lumxss @bkdgiffug]

剑桥这回直接扔王炸了！！

AI & ML经典教材全集直接免费开放，PDF随便下。

想学机器学习又不想被割韭菜买高价课的，这十本刷完，底子基本就硬了。

顺序从易到难排好了：

1️⃣ 《机器学习理解》——理论算法一把抓，零基础入门首选
🔗 https://t.co/fylTw37bOl
2️⃣ 《机器学习数学基础》——数学底子弱的先把这本补上
🔗 https://t.co/yykNLQmdfv

3️⃣ 《机器学习算法的数学分析》——深入数学原理
🔗 https://t.co/MEvgkXoHYy
4️⃣ 《深度学习理论原理》——搞懂DL背后的理论根基
🔗 https://t.co/ig93KOQRPn

5️⃣ 《神经网络与机器学习》——神经网络的系统讲解
🔗 https://t.co/cTMBvJz6Ny
6️⃣ 《图深度学习》——图神经网络入门必读
🔗 https://t.co/RJeCqCstml

7️⃣ 《机器学习的算法视角》——从算法角度重新理解ML
🔗 https://t.co/VT0YnKdUdO
8️⃣ 《概率论：理论与实例》——概率基础打牢
🔗 https://t.co/NqVoIZGGYg

9️⃣ 《应用概率基础》——概率论实战应用
🔗 https://t.co/FrxqQER3mQ
🔟 《高级数据分析》——数据科学进阶必备
🔗 https://t.co/Zt74B21nrf

说句实话，这些书没一本是轻松的，别指望躺着翻完。
但只要你能硬啃下来两三本，比听群里吹一年AI牛逼都管用。

[Bruce R. Fenton @GenomicSETI]

Sabina nails it here, mainstream academics have a terrible history of extraordinary claims without extraordinary evidence (even no evidence) across dark matter, string theory, universe origination and many more topics. In some cases likely worse than re Ufology or ancient aliens

[PennyLane @PennyLaneAI]

From paper to code: how quantum computing tackles vibronic dynamics! 📝💻

In our latest PennyLane demo, Emily Nobes breaks down the core concepts behind Xanadu (@XanaduAI)'s paper, "Quantum Algorithm for Vibronic Dynamics," into a digestible, executable tutorial.

Learn how quantum computing and custom quantum algorithms enable realistic quantum chemistry simulations—opening new doors for advanced materials discovery. 👇

https://t.co/ND0b9qCHCC

[Aria @ariaghora]

craaazy buka resep dapur tapi viewer cuma seginian https://t.co/J6XVmHbeLZ

[Anemll @anemll]

Just discovered that @GoogleColab enabled SSH and CLI ! It should be so much easier to use &amp; test TPUs and @nvidia RTX 6000 workflows now!

[SIAM Activity Group on Dynamical Systems @DynamicsSIAM]

Lecture notes: "Advanced Linear Algebra with Applications - Part I (Numerical linear algebra for PDEs, machine learning, and data assimilation)" [by Victorita Dolean, Jemima Tabeart]: https://t.co/o2d87SkNIp

[note: 101 pages; code available at https://t.co/Pq727t7xqD]

[MALAYSIA_JAYA @MALAYSIA_JAYA]

HARI NI NEGARA MISKIN MERDEKA

[Muhammad Augi @lovmamartya]

https://t.co/b6RXBQQoyv nonton ini dulu

[Muhammad Augi @lovmamartya]

stuck di error correction