deeplearning |

How I Built a 6B Image Model That Runs on a 16GB GPU (Z-Image)

How a Model Really Learns: From Loss to Learning in Machine Learning & Deep Learning

Unveiling the Hidden Geometry That Supercharges Neural Nets

Why Studying the Turing Machine Changed How I See AI And Why Every New AI Engineer Should Revisit It

Why Studying the Turing Machine Changed How I See AI And Why Every New AI Engineer Should Revisit It

Why Studying the Turing Machine Changed How I See AI And Why Every New AI Engineer Should Revisit It

Why Studying the Turing Machine Changed How I See AI And Why Every New AI Engineer Should Revisit It

Tame Your LLMs: A New Optimizer for Robust Deep Learning

Anon: The Adaptive Optimizer Bridging SGD and Adam for Peak AI Performance

Introducing PQNT — A New Power-Law Quantization Method

BATCHNORM IN LANGUAGE MODELS

Tokenization in NLP: The Foundational Step That Turns Language Into Data

Linear Algebra for AI

How Search Engines Actually Answer Your Questions

How Search Engines Actually Answer Your Questions

DragonMemory: Neural Sequence Compression for Production RAG

How I Reached 84.35% on CIFAR-100 Using ResNet-50 (PyTorch Guide)

How I Reached 84.35% on CIFAR-100 Using ResNet-50 (PyTorch Guide)

Stock Price Prediction

Stock Price Prediction

LANGUAGE MODELS USING MLP (Part 1)

Nested Learning — My Reflections on a Model That Learns How to Learn

Star Multi-Class Classification Neural Network With Pytorch

DeepWideSearch: Benchmarking Depth and Width in Agentic Information Seeking

Text or Pixels? It Takes Half: On the Token Efficiency of Visual Text Inputs inMultimodal LLMs

BIGRAM LANGUAGE MODELS USING A NEURAL NET

From Charts to Code: A Hierarchical Benchmark for Multimodal Models

ColorAgent: Building A Robust, Personalized, and Interactive OS Agent

Building an Enhanced PPO Trading Bot with Real-Time Data Sync and IBKR Integration

Building an Enhanced PPO Trading Bot with Real-Time Data Sync and IBKR Integration

OmniNWM: Omniscient Driving Navigation World Models

OmniNWM: Omniscient Driving Navigation World Models

Setting Up NVIDIA Parakeet TDT 0.6B v3 for Speech Recognition on AWS EC2 Ubuntu

FinSight: Towards Real-World Financial Deep Research

olmOCR 2: Unit Test Rewards for Document OCR

When Correct Is Not Safe: Can We Trust Functionally Correct Patches Generatedby Code Agents?

PokeeResearch: Effective Deep Research via Reinforcement Learning from AIFeedback and Robust Reasoning Scaffold

Predicting the Unpredictable: Reproducible BiLSTM Forecasting of Incident Countsin the Global Terrorism Database (GTD)

Unimedvl: Unifying Medical Multimodal Understanding And Generation ThroughObservation-Knowledge-Analysis

LLM Concepts (Explained Without Making Your Brain Hurt): What Every Developer Should Know

Chem-R: Learning to Reason as a Chemist

On Non-interactive Evaluation of Animal Communication Translators

Foundational Automatic Evaluators: Scaling Multi-Task Generative EvaluatorTraining for Reasoning-Centric Domains

Knowledge-based Visual Question Answer with Multimodal Processing, Retrieval andFiltering

Embody 3D: A Large-scale Multimodal Motion and Behavior Dataset

Distractor Injection Attacks on Large Reasoning Models: Characterization andDefense

How Machines See: The Power of Computer Vision in AI (Explained for Developers)

Constantly Improving Image Models Need Constantly Improving Benchmarks

Beyond Pipelines: A Survey of the Paradigm Shift toward Model-Native Agentic AI

ConsistEdit: Highly Consistent and Precise Training-free Visual Editing

When to Ensemble: Identifying Token-Level Points for Stable and Fast LLMEnsembling

Paper2Web: Let’s Make Your Paper Alive!

Devtool for running and benchmarking local AI

Rewiring Experts on the Fly:Continuous Rerouting for Better Online Adaptation inMixture-of-Expert models

DLER: Doing Length pEnalty Right – Incentivizing More Intelligence per Token viaReinforcement Learning

MorphoBench: A Benchmark with Difficulty Adaptive to Model Reasoning

Unlocking Out-of-Distribution Generalization in Transformers via RecursiveLatent Space Reasoning

LLMs as Scalable, General-Purpose Simulators For Evolving Digital Agent Training

Agentic Design of Compositional Machines

LiveResearchBench: A Live Benchmark for User-Centric Deep Research in the Wild