Nitesh Kumar Sharma's picture

2 7 2

Nitesh Kumar Sharma

carbene101

·

95-percent-ci

AI & ML interests

LLMs, OCR

Recent Activity

upvoted a paper 27 days ago

Architecture Decoupling Is Not All You Need For Unified Multimodal Model

reacted to sergiopaniego's post with 🔥 about 1 month ago

we've just added several example scripts to TRL showing how to train models with GRPO using some of the new OpenEnv environments train a model to interact with a browser (🎮 BrowserGym Env), play Wordle (🎮 Wordle Env) and moooore! TRL (GRPO + vLLM) + OpenEnv! ⚡️ 📝 go play with them: https://github.com/huggingface/trl/tree/main/examples/scripts/openenv 📝 examples list: https://huggingface.co/docs/trl/main/en/example_overview#scripts

reacted to Kseniase's post with ❤️ about 1 month 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

carbene101 's Spaces 1

First Agent Template

Get current local time in any timezone