- The MultiModel paper: https://arxiv.org/abs/1706.05137
- The story behind Attention Is All You Need: https://surfingmanifolds.substack.com/p/pandemonium-the-transformers-story
Mohammed Hamdy
mmhamdy
AI & ML interests
AI4Sci | NLP | Reinforcement Learning
Recent Activity
repliedto their post 3 days ago
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? 😀 posted an update 3 days ago
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? 😀Organizations
replied to their post 3 days ago
posted an update 3 days ago
Post
79
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? 😀
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
posted an update 5 months ago
Post
3179
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
Here's a nice short summary from Gemini
upvoted an article 6 months ago
Article
Continuous batching from first principles
- +1
ror, ArthurZ, mcpotato
• • 397 reacted to Kseniase's post with ❤️ 7 months ago
Post
6498
12 Types of JEPA
Since Yann LeCun together with Randall Balestriero released a new paper on JEPA (Joint-Embedding Predictive Architecture), laying out its theory and introducing an efficient practical version called LeJEPA, we figured you might need even more JEPA. Here are 7 recent JEPA variants plus 5 iconic ones:
1. LeJEPA → LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics (2511.08544)
Explains a full theory for JEPAs, defining the “ideal” JEPA embedding as an isotropic Gaussian, and proposes the SIGReg objective to push JEPA toward this ideal, resulting in practical LeJEPA
2. JEPA-T → JEPA-T: Joint-Embedding Predictive Architecture with Text Fusion for Image Generation (2510.00974)
A text-to-image model that tokenizes images and captions with a joint predictive Transformer, enhances fusion with cross-attention and text embeddings before training loss, and generates images by iteratively denoising visual tokens conditioned on text
3. Text-JEPA → Speaking in Words, Thinking in Logic: A Dual-Process Framework in QA Systems (2507.20491)
Converts natural language into first-order logic, with a Z3 solver handling reasoning, enabling efficient, explainable QA with far lower compute than large LLMs
4. N-JEPA (Noise-based JEPA) → Improving Joint Embedding Predictive Architecture with Diffusion Noise (2507.15216)
Connects self-supervised learning with diffusion-style noise by using noise-based masking and multi-level schedules, especially improving visual classification
5. SparseJEPA → SparseJEPA: Sparse Representation Learning of Joint Embedding Predictive Architectures (2504.16140)
Adds sparse representation learning to make embeddings more interpretable and efficient. It groups latent variables by shared semantic structure using a sparsity penalty while preserving accuracy
6. TS-JEPA (Time Series JEPA) → Joint Embeddings Go Temporal (2509.25449)
Adapts JEPA to time-series by learning latent self-supervised representations and predicting future latents for robustness to noise and confounders
Read further below ↓
It you like it, also subscribe to the Turing Post: https://www.turingpost.com/subscribe
Since Yann LeCun together with Randall Balestriero released a new paper on JEPA (Joint-Embedding Predictive Architecture), laying out its theory and introducing an efficient practical version called LeJEPA, we figured you might need even more JEPA. Here are 7 recent JEPA variants plus 5 iconic ones:
1. LeJEPA → LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics (2511.08544)
Explains a full theory for JEPAs, defining the “ideal” JEPA embedding as an isotropic Gaussian, and proposes the SIGReg objective to push JEPA toward this ideal, resulting in practical LeJEPA
2. JEPA-T → JEPA-T: Joint-Embedding Predictive Architecture with Text Fusion for Image Generation (2510.00974)
A text-to-image model that tokenizes images and captions with a joint predictive Transformer, enhances fusion with cross-attention and text embeddings before training loss, and generates images by iteratively denoising visual tokens conditioned on text
3. Text-JEPA → Speaking in Words, Thinking in Logic: A Dual-Process Framework in QA Systems (2507.20491)
Converts natural language into first-order logic, with a Z3 solver handling reasoning, enabling efficient, explainable QA with far lower compute than large LLMs
4. N-JEPA (Noise-based JEPA) → Improving Joint Embedding Predictive Architecture with Diffusion Noise (2507.15216)
Connects self-supervised learning with diffusion-style noise by using noise-based masking and multi-level schedules, especially improving visual classification
5. SparseJEPA → SparseJEPA: Sparse Representation Learning of Joint Embedding Predictive Architectures (2504.16140)
Adds sparse representation learning to make embeddings more interpretable and efficient. It groups latent variables by shared semantic structure using a sparsity penalty while preserving accuracy
6. TS-JEPA (Time Series JEPA) → Joint Embeddings Go Temporal (2509.25449)
Adapts JEPA to time-series by learning latent self-supervised representations and predicting future latents for robustness to noise and confounders
Read further below ↓
It you like it, also subscribe to the Turing Post: https://www.turingpost.com/subscribe
- 1 reply
liked a
Space 7 months ago
upvoted 2
articles 7 months ago
Article
Promoter-GPT: Writing DNA Instructions with Language Models
hugging-science
• • 25 Article
Scaling Test-Time Compute to Achieve Gold Medal at IOI 2025 with Open-Weight Models
nvidia
• • 19 liked a
dataset 8 months ago
published an article 8 months ago
Article
The Next Frontier: Large Language Models In Biology
mmhamdy
• • 5 liked 3
Spaces 8 months ago
published a
Space 8 months ago
reacted to AdinaY's post with 🔥 8 months ago
Post
3544
BAAI has released ROME🔥 evaluating 30+ large reasoning models on text & visual reasoning
FlagEval Findings Report: A Preliminary Evaluation of Large Reasoning Models on Automatically Verifiable Textual and Visual Questions (2509.17177)
✨Tests visual reasoning, not just recognition
✨Covers capability × alignment × safety × efficiency
✨More transparent & reliable (less data contamination)
✨Helps make real-world deployment choices
FlagEval Findings Report: A Preliminary Evaluation of Large Reasoning Models on Automatically Verifiable Textual and Visual Questions (2509.17177)
✨Tests visual reasoning, not just recognition
✨Covers capability × alignment × safety × efficiency
✨More transparent & reliable (less data contamination)
✨Helps make real-world deployment choices
updated a
Space 8 months ago
published a
Space 8 months ago
liked a
model 10 months ago
upvoted an article 11 months ago
Article
FineWeb-C: A Community-Driven Dataset for Educational Quality Annotations in 122 Languages
davanstrien
• • 35 liked a
dataset 12 months ago