Mohammed Hamdy's picture

Open to Collab

Mohammed Hamdy

mmhamdy

hugging-science

·

AI & ML interests

TechBio | AI4Sci | NLP | Reinforcement Learning

Recent Activity

posted an update 13 days ago

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

upvoted an article 2 months ago

Continuous batching from first principles

reacted to Kseniase's post with ❤️ 2 months ago

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 → https://huggingface.co/papers/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 → https://huggingface.co/papers/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 → https://huggingface.co/papers/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) → https://huggingface.co/papers/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 → https://huggingface.co/papers/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) → https://huggingface.co/papers/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

View all activity

Organizations

mmhamdy 's Spaces 4

BioLLM Story

Create and render documents with code and text using Quarto

Speech To Speech Translation

Automatic Speech Recognition

Music Genre Classifier