Tilak Marupilla

Explorer | Embedded Systems | Signal processing | Deep Learning (just really trying to learn)

[Kirk Borne @KirkDBorne]

MIT Advanced Data Structures course: https://t.co/EQtAOIndPI

Video lectures, lecture notes, problem sets, GitHub, and more

[Ram Singh Verma @RamSingh_369]

MIT professor Patrick Winston literally gave a 1-hour masterclass on communication that teaches you how to speak better than most schools ever could.

[Anatoli Kopadze @AnatoliKopadze]

Anthropic engineers just showed how they build a full app from scratch, using a loop of agents.

40 minutes from the team behind Claude Code.

They used three agents: one to plan, one to build, one to judge, cycling until the app actually works.

The winners won't have the smartest model, they'll have the best loop.

Watch it, then read the full guide on how to actually use loops below.

[Anuj @anujcodes_21]

🚨Anthropic just showed a 24-minute workshop on how to actually do prompts for Claude.

Taught by the people who built it.

Free. No registration. No paywall.

I've seen $300 courses that don't cover what they teach in the first 8 minutes.

Watch it and bookmark it now!

[attentionmech @attentionmech]

strudel is best merge of audio, visual and programming i have seen so far.

(day 2ish of learning strudel to generate sound)

[Oz @oznova_]

Structure: https://t.co/gTDP5LkxzV
Competition info: https://t.co/CflixlvsNy

[Alex Mordvintsev @zzznah]

Working on the new simulator. I just wanted to see what Atari2600 fetching data from ROM looks like at CMOS FET level
(@tinytapeout TT09 Atari circuit by @__ReJ__)

[Clément Verrier @cjpgverrier]

I've finally decided to spend some time studying @__tinygrad__ codebase. I've been impressed by the elegance of their pattern matcher, so I wrote some notes and turned them into a tuto: https://t.co/6uwEJU99iR
The more I read the code, the more I think it's the future of software: anti-bloating and very close to the hardware.

[Chester @chesterzelaya]

a guy on youtube built an IR sensor + receiver that could reconstruct conversations from the captured microscopic vibrations on a window

apparently it's an old trick, but there's something beautiful about capturing information through odd setups (e.g vision through wifi)

[Vicharak @Vicharak_In]

Learning FPGAs is cheaper than your @netflix subscription now.

[Dorsa @dorsar]

New fastest shortest-path algorithm in 41 years!
Tsinghua researchers broke Dijkstra’s 1984 “sorting barrier,” achieving O(m log^(2/3) n) time. This means faster route planning, less traffic, cheaper deliveries, and more efficient networks - and a CS curriculum revamp =)

[Vision Transformers @vitransformer]

New blog post: We've never enjoyed working on Kernels more than this.

We have some very fast AI-generated kernels with a simple multi-agent system. They're running close to or even surpassing Pytorch shipped kernels.
(1/6)

[🔗 link in final post]

[Asankhaya Sharma @asankhaya]

🧵1/12 Just used OpenEvolve to automatically discover GPU kernels that beat expert baselines!

12.5% average performance improvement in transformer attention, with 106% peak speedup 🚀

[Asankhaya Sharma @asankhaya]

Another inference time scaling technique from @SakanaAILabs to improve model accuracy. Would be awesome to build it try it with optillm - https://t.co/p7B40LSFOX

[Makora @makora_ai]

Introducing MakoGenerate, a CUDA-writing AI agent.

We're excited to make the research preview of MakoGenerate available today, completely free.

[ℏεsam @Hesamation]

A 680-page interactive book on computer science algorithms

This might be the sickest book i’ve seen in a long time!

22 chapters, 300+ interactive visuals, 250+ code snippets that can be edited and run + problems and solutions for practice.

honestly this is 90% of a CS degree.

[MrNeRF @janusch_patas]

WeatherEdit: Controllable Weather Editing with 4D Gaussian Field

Contributions:
1. Based on our analysis of weather editing characteristics, we introduce WeatherEdit, a comprehensive and efficient framework for realistic and controllable weather generation. Compared with existing methods that focus on either background editing or static weather effects, a progressive 2D-to-4D transformation process in WeatherEdit enhances adaptability across a wider range of scenarios.

2. We introduce an all-in-one adapter to enable a diffusion model for multi-weather (snowy, rainy, and fog) synthesis, along with a Temporal-View attention to ensure consistent editing across multi-frame and multi-view.

3. We design a 4D Gaussian field for weather particle modeling, enabling plausible simulation of raindrops, snowflakes, and fog with controllable severity.

4. We demonstrate WeatherEdit’s effectiveness in generating realistic, consistent, and controllable weather effects in 3D driving scenes, showcasing its applicability to real-world scenarios.

[Tivadar Danka @TivadarDanka]

The single most undervalued fact of linear algebra: matrices are graphs, and graphs are matrices.

Encoding matrices as graphs is a cheat code, making complex behavior simple to study.

Let me show you how!

[el.cine @EHuanglu]

omg.. this cant be real

China’s 4DV AI just dropped 4D Gaussian Splatting, you can turn 2D video into 4D with sound..

imagine.. we will be able to change camera angle, zoom in/out while watching movies

5 examples:

[Turing Post (Ksenia Se) @TheTuringPost]

12 Foundational AI Model Types

▪️ LLM
▪️ SLM
▪️ VLM
▪️ MLLM
▪️ LAM
▪️ LRM
▪️ MoE
▪️ SSM
▪️ RNN
▪️ CNN
▪️ SAM
▪️ LNN

Save the list and check this out for explanations and links to the useful resources: https://t.co/B0EBRRJmnG