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!
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!
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? π
PiD β Pixel Diffusion Decoder Image Edit Upscale and Image Generation Upscale, an all-in-one demo, is now live on Spaces! Great improvements in realism-based image generation and editing are powered by FLUX.2-Klein, while image generation is paired with Z-Image, and upscaling is enabled by default!
I've made 8 Spaces in the Qwen-Image-Edit series, and out of them, 5 Spaces reached βSpace of the Weekβ! A few Spaces are still topping the list even after many months.
Cumulatively, the series has crossed 8.2 million+ ZeroGPU runs and nearly 4 million visitors overall.
Turns out : if we predict π earth we can save a lot of time looking for interesting things and less time looking at things that we expect to see.
Sentinel-2 imagery π°οΈbasically takes a long time to download towards earth. so our "near real time" systems are quite far from that in practical terms.
meanwhile , if we "predict" what we will see , based on what we do see , we can send down much less data in a timely way , and prioritize π‘earth-bound response .
I'm talking about illegal fishing , logging , mining or building in nature reserves , the more of that we predict early the more we're able to stop it on time.
Multimodal-Edge Demo, a node-based inference canvas demo, is now live on Spaces. It features node-based Transformers for fast inference across 10+ edge-device multimodal models on the Hub, all within a single space. The series includes models from Qwen3.5, Qwen3-VL, Gemma 4, and the LFM 2.5 VL model series, with support for reasoning and grounding tasks.
since everyone liked my previous announcement post ( https://huggingface.co/posts/Tonic/338509028435394 ) so much , i'm back with more high quality proceedural datasets in the Geospacial domain for SFT training !
Now, a collection of various compression schemes for Qwen3.6 and the abliterated version 1 of dense models is available on the Hub. Check it out via the links below. π
HY-World-2.0 β A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds is now available on Spaces, and it works both as native Gradio components and in Gradio server mode.
A new comparator on Spaces showcases Standard FLUX.2 Decoder vs. FLUX.2 Small Decoder. The Small Decoder is ~1.4Γ faster, uses ~1.4Γ less VRAM, and maintains near-identical image quality. It has ~28M parameters with narrower channels [96, 192, 384, 384] vs. [128, 256, 512, 512], and the demo supports sequence generation by running both decoders simultaneously and comparing the results side by side.
Now, a collection of various compression schemes for Gemma 4 and the abliterated version 1 of dense models is available on the Hub. Check it out via the links below. π
Now the demo for image detection based on SAM3 and Gemma-4 (*Filter) is available on Spaces, using full-fledged Transformers inference with multimodal reasoning for processed images. It also supports video segmentation (mask), video segmentation (annotation), and image click segmentation.
The demo for Image Detection (*Filter) based on SAM3 and Qwen-3.5 is now available on Hugging Face Spaces using Transformers inference, with multimodal reasoning for processed images, and it also supports video segmentation (mask), video segmentation (annotation), and image click segmentation.
Flux-Klein-KV-Edit-Consistency demo is now available on Spaces. It preserves character identity and delivers high-quality, realistic results after edits. No need for any special prompts, just upload the image, type your prompt, and get the resulting image blazing fast.
β Built with Headless Gradio, an alternative to using gr.Blocks for creating the frontend and triggering events, powered by FastAPI + Gradio. You can now design the frontend however you want, with continued support for APIs, MCP, and ZeroGPU.
β Gradio Server Mode is now available from gradio@v6.10.0.
To learn more, visit the app page or the respective model pages.
Map-Anything v1 (Universal Feed-Forward Metric 3D Reconstruction) demo is now available on Hugging Face Spaces. Built with Gradio and integrated with Rerun, it performs multi-image and video-based 3D reconstruction, depth, normal map, and interactive measurements.
The QIE-Bbox-Studio demo is now live β more precise and packed with more options. Users can manipulate images with object removal, design addition, and even move objects from one place to another, all in just 4-step fast inference.
QIE-2509-Object-Remover-Bbox-v3 is a more stable version of the Qwen Image Edit visual groundingβbased object removal model. The app was previously featured in HF Spaces of the Week and is now updated with the latest Bbox-v3 LoRA adapter.
