Hugging Face's logo
Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity
burtenshaw  new activity about 1 month ago
hf-skills/README:Update README.md
victor  new activity about 1 month ago
hf-skills/README:Update README.md
anonymousatom  authored a paper 3 months ago
IntelliAsk: Learning to Ask High-Quality Research Questions via RLVR
View all activity
Reubencf 
posted an update 5 days ago
view post
Post
2021
Millions speak Konkani. The internet barely knows it.

Today's major LLMs struggle with regional languages. They can't read, write or even recognize Konkani. So I built one that can.

Here is a working demo of the Konkani LLM I've been training. 👇

https://youtu.be/8K04ylbXh6k
mmhamdy 
posted an update 6 days ago
view post
Post
4931
It was supposed to be a failed experiment. Instead, it led to the discovery of one of the most intriguing phenomena in neural networks, simply because a researcher forgot to turn it off and left it running....for a week!

In 2022, researchers at OpenAI were studying how neural networks generalize from their training data. For this task, they were training small transformer models to perform modular arithmetic.

The thing is, neural networks are weird. When a model has an abundance of parameters (like neural nets), it can easily overfit. It essentially memorizes its training data, scoring a perfect 100% accuracy when tested on it, but remains completely clueless when faced with any new instances not present in the training set (close to 0 accuracy). It is like memorizing 1 + 2 = 3 without understanding the concept of addition, so if 2 + 3 wasn't in the training set, the model fails miserably!

Usually, when a model overfits like this, people just cut their losses, turn off the experiment, and move on with their lives.

But sometimes they forget. And that is exactly what happened to our researchers at OpenAI. A week later, they checked back in, and a miracle had happened!

They discovered Grokking (And no, this has nothing to do with xAI's Grok , the term was originally coined by sci-fi author Robert Heinlein to mean understanding something so deeply that it becomes part of you). Grokking is when a neural network suddenly and abruptly learns to generalize long after it has overfitted. Just take a look at the graph in the image below!

Spooky, right! I told you neural nets are weird!
  • 4 replies
·
mmhamdy 
posted an update 9 days ago
view post
Post
1003
Human brains don't recreate every pixel to understand the world!

Most current models in genomics, proteomics, and single-cell transcriptomics rely on generative objectives like masked language modeling or next token prediction. While effective, these architectures waste significant capacity reconstructing raw, noisy sequence details that may not carry functional biological meaning.

But a promising, more efficient alternative is emerging: Joint-Embedding Predictive Architecture (JEPA)

Originally introduced by Yann LeCun for computer vision, JEPA is a non-generative, self-supervised learning (SSL) framework. Instead of predicting raw inputs, it operates as a world model that predicts abstract semantic embeddings in latent space.

Recently, the JEPA framework (and its more efficient LeJEPA variant) has been adapted into the biological sciences to develop performing foundation models and to improve on already existing ones.

It's interesting how each adaptation modified and tailored JEPA to suit its specific biological domain, whether by experimenting with different backbones or complementing the objective with other loss terms.

For example, JEPA-DNA and ProteinJEPA used JEPA as a continual pre-training framework to enhance existing foundation models without training from scratch, while Cell-JEPA and JEPA-DNA employed a hybrid objective that combines the JEPA loss with a traditional language modeling loss.

The article below provides an overview of these implementations, along with others that came out this year. As always, your thoughts and feedback are welcome and highly appreciated!

Link to the article is in the first comment 👇
  • 3 replies
·
mmhamdy 
posted an update 17 days ago
view post
Post
131
Things rarely go as we expect!

In 2017, Google released the Transformer architecture. While it was clear the model was promising, absolutely no one (including its authors) anticipated the pervasive global revolution it would create!

The authors actually viewed the Transformer as just a stepping stone for a much more ambitious project: The MultiModel.

Their ultimate goal was to build a single deep learning architecture capable of jointly learning massive, diverse tasks across entirely different domains (in 2017). A One Model To Learn Them All.

In fact, the MultiModel paper was published in the exact same month as Attention Is All You Need!

But history had other plans. The building block eclipsed the grand design!

So, have you heard about the MultiModel before? 😀
  • 1 reply
·
Reubencf 
posted an update 27 days ago
view post
Post
4693
I have improved my Portfolio please do check it out
Reubencf/Portfolio
  • 6 replies
·
burtenshaw 
in hf-skills/README about 1 month ago

Update README.md
#1 opened about 1 month ago by
victor
victor 
in hf-skills/README about 1 month ago

Update README.md
#1 opened about 1 month ago by
victor
Reubencf 
authored a paper 3 months ago
Nymbo 
posted an update 3 months ago
view post
Post
7398
We should really have a release date range slider on the /models page. Tired of "trending/most downloaded" being the best way to sort and still seeing models from 2023 on the first page just because they're embedded in enterprise pipelines and get downloaded repeatedly. "Recently Created/Recently Updated" don't solve the discovery problem considering the amount of noise to sift through.

Slight caveat: Trending actually does have some recency bias, but it's not strong/precise enough.
  • 3 replies
·
Reubencf 
posted an update 3 months ago
view post
Post
2821
🚀 I am thrilled to announce the release of a new Konkani LLM!

We've seen some fantastic results for both translation and transliteration tasks, and I'm excited to share this progress with the community.

📖 Read the launch article and see the results: https://huggingface.co/blog/Reubencf/konkani-llm
🤖 Explore the model and collection:
konkani

I would love to hear your feedback or see what you build with it! #Konkani #LLM #NLP #HuggingFace #IndicNLP #Konkani
burtenshaw 
updated a model 5 months ago
burtenshaw 
published a model 5 months ago
Reubencf 
posted an update 5 months ago
Reubencf 
posted an update 5 months ago
view post
Post
1905
Now Live: The Reubencf/Nano_Banana_Editor now includes 10 free requests/day! 🍌 I'm personally sponsoring these credits to help make open AI accessible to all.
(Note: Limits are subject to change based on funding).

Enjoy !
mmhamdy 
posted an update 5 months ago
view post
Post
3186
The new DeepSeek Engram paper is super fun! It also integrates mHC, and I suspect they're probably releasing all these papers to make the V4 report of reasonable length😄

Here's a nice short summary from Gemini
Akhil-Theerthala 
submitted a paper to Daily Papers 5 months ago
Akhil-Theerthala 
authored a paper 5 months ago
Nymbo 
posted an update 5 months ago
view post
Post
3445
Genuine recommendation: You should really use this AutoHotKey macro. Save the file as macros.ahk and run it. Before sending a prompt to your coding agent, press Ctrl + Alt + 1 and paste your prompt to any regular chatbot. Then send the output to the agent. This is the actual, boring, real way to "10x your prompting". Use the other number keys to avoid repeating yourself over and over again. I use this macro prolly 100-200 times per day. AutoHotKey isn't as new or hype as a lot of other workflows, but there's a reason it's still widely used after 17 years. Don't overcomplicate it.

; Requires AutoHotkey v1.1+

; All macros are `Ctrl + Alt + <variable>`

^!1::
    Send, Please help me more clearly articulate what I mean with this message (write the message in a code block):
return

^!2::
    Send, Please make the following changes:
return

^!3::
    Send, It seems you got cut off by the maximum response limit. Please continue by picking up where you left off.
return


In my experience the past few months, Ctrl + Alt + 1 works best with Instruct models (non-thinking). Reasoning causes some models to ramble and miss the point. I've just been using GPT-5.x for this.
Akhil-Theerthala 
posted an update 5 months ago
view post
Post
488
Is it better to show a model too many images once (Diversity), or extract as much information from a small set of images?

I have always wanted to do an ablation study on this and recently I got the chance to do exactly that. Why? In applied domains like robotics, manufacturing, or banking, we rarely have the luxury of internet-scale diverse image datasets. We are often "Data Poor" in terms of diversity but "Data Rich" in depth.

The takeaway? Density is efficient for facts but dangerous for reasoning (logical collapse) if you don't have larger scale data.

More details:
https://huggingface.co/blog/Akhil-Theerthala/diversity-density-for-vision-language-models
  • 1 reply
·
Reubencf 
posted an update 5 months ago
view post
Post
3235
Happy New Year 2026
i have planned to build many things this year , most of them will be cheaper or free alternative's to paid products

i am looking forward to release some useful spaces ✌️ Stay Tuned !