⚛️ Dr. Walid Soula ⚛️

Applied AI Scientist | Bridging Research and Market Strategy

[Tom Dörr @tom_doerr]

User-friendly ROS framework for autonomous PX4 drones

https://t.co/u3Nafbh6XB

[Sadao Tokuyama @tokufxug]

GIS×BIM×XR：次世代デジタルツイン

GISの広域コンテキストとBIMの精緻な設計データをXRで統合。

現実を写し取るReality Mappingを基盤に、設計と現状を同一空間で比較・分析可能にする。

単なる視覚化を超え、信頼性の高いデータに基づいた意思決定を支援するデジタルツイン基盤。

[Tech with Mak @techNmak]

Imagine trying to teach someone how to swim just by letting them read books about water.
That is how we have been training AI on physics, using text descriptions.

To really learn, you need to get in the water.

"The Well" is that water.

Polymathic AI has released a massive 15TB open-source library of physics simulations. It allows AI models to experience physical phenomena directly.

Instead of reading about a supernova, the model processes the actual data of the explosion. Instead of reading about aerodynamics, it analyzes the fluid flow.

This moves us from [Generative AI] (making things up) to [Scientific AI] (discovering truth).

A huge step forward for open science.

GitHub Repo: https://t.co/xgUdqncyRH

[Will Eastcott @willeastcott]

4D Gaussian Splatting on the web just leveled up. ✨

Announcing the integration of @gracia_vr with the open-source @PlayCanvas Engine. 🧵

[Avi Chawla @_avichawla]

I have been fine-tuning LLMs for over 2 years now!

Here are the top 5 LLM fine-tuning techniques, explained with visuals:

First of all, what's so different about LLM finetuning?

Traditional fine‑tuning is impractical for LLMs (billions of params; 100s GB).

Since this kind of compute isn't accessible to everyone, parameter-efficient finetuning (PEFT) came into existence.

Before we go into details of each technique, here's some background that will help you better understand these techniques:

LLM weights are matrices of numbers adjusted during finetuning.

Most PEFT techniques involve finding a lower-rank adaptation of these matrices, a smaller-dimensional matrix that can still represent the information stored in the original.

Now with a basic understanding of the rank of a matrix, we're in a good position to understand the different finetuning techniques.

(refer to the image below for a visual explanation of each technique)

1) LoRA

- Add two low-rank trainable matrices, A and B, alongside weight matrices.
- Instead of fine-tuning W, adjust the updates in these low-rank matrices.

Even for the largest of LLMs, LoRA matrices take up a few MBs of memory.

2) LoRA-FA

While LoRA significantly decreases the total trainable parameters, it requires substantial activation memory to update the low-rank weights.

LoRA-FA (FA stands for Frozen-A) freezes matrix A and only updates matrix B.

3) VeRA

- In LoRA, low-rank matrices A and B are unique for each layer.
- In VeRA, A and B are frozen, random, and shared across all layers.
- Instead, it learns layer-specific scaling VECTORS (b and d) instead.

4) Delta-LoRA

- It tunes the matrix W as well, but not in the traditional way.
- Here, the difference (or delta) between the product of matrices A and B in two consecutive training steps is added to W.

5) LoRA+

- In LoRA, both matrices A and B are updated with the same learning rate.
- Authors of LoRA+ found that setting a higher learning rate for matrix B results in better convergence.
____
Find me → @_avichawla
Every day, I share tutorials and insights on DS, ML, LLMs, and RAGs.

[SkalskiP @skalskip92]

RF-DETR is the best open-source detector for aerial and drone footage

link: https://t.co/6tF4mhWkCA

[⚛️ Dr. Walid Soula ⚛️ @vagnagun]

https://t.co/d0RWu96YvO

[Maziyar PANAHI @MaziyarPanahi]

we are so back! 🔥

[Tom Dörr @tom_doerr]

Agents simulate medical specialists for diagnostics

https://t.co/2uvmgZMQ45

[Tom Dörr @tom_doerr]

Automates Instagram activity via ADB without root

https://t.co/153NMSwFhl

[Pau Labarta Bajo @paulabartabajo_]

60-minute deep dive on how to fine-tune a Small Language Model for browser control

Enjoy ↓
https://t.co/QPyw01ptqt

[Tom Dörr @tom_doerr]

AI vision for camera streams

https://t.co/6qbAv9yfPo

[Tom Dörr @tom_doerr]

List of forensics analysis tools

https://t.co/C0tF78Bl42

[Tom Dörr @tom_doerr]

List of tools for enhancing social media experiences

https://t.co/p6V7gYM5AZ

[GitHub Projects Community @GithubProjects]

Turn any PDF or image document into structured data for your AI.

[GitHub Projects Community @GithubProjects]

Clone and recreate any website as a modern React app in seconds.

[Tom Dörr @tom_doerr]

Desktop AI assistant with RAG, vision, and voice

https://t.co/t6RqclCfMm

[GitHub Projects Community @GithubProjects]

Track your website visitors with just a favicon.

[Min Choi @minchoi]

Qwen Image Edit w/ Camera Control is wild 🤯

Quickly rotate the camera, switch between bird's eye and worm's eye views using just clicks.

Here's how plus 7 wild examples:👇

[Akshay 🚀 @akshay_pachaar]

Everyone is sleeping on this new OCR model!

Datalab's Chandra topped independent benchmarks and beat the previously best dots-ocr.

- Support for 40+ languages
- Handles text, tables, formulas seamlessly

I tested on Ramanujan's handwritten letter from 1913.

100% open-source.