Machine Learning

273 articles in this category (Page 2 of 12)

AI NewsAgentic AIMachine Learning

Building Multi-Agent AI Workflows for Advanced Systems Biology Simulations

Develop a multi-agent AI pipeline using GPT-4o-mini to model gene networks, predict protein interactions, and optimize metabolic flux with unified LLM-driven synthesis.

May 2, 2026

AI NewsMachine LearningEngineering

Calculating Local LLM VRAM Requirements to Prevent GPU Out-of-Memory Errors

Master the mathematics of LLM VRAM consumption, from the 2-byte-per-parameter baseline to KV cache overhead and 4-bit quantization savings.

May 2, 2026

AI NewsAgentic AIMachine Learning

Meta Autodata: Agentic Framework for High-Quality Training Data Creation

Meta AI introduces Autodata, an agentic framework that enables autonomous data creation, increasing performance gaps between model solvers from 1.9% to 34%.

May 1, 2026

AI NewsAI InfrastructureMachine Learning

Qwen-Scope: Open-Source Sparse AutoEncoders for LLM Interpretability and Steering

Qwen AI releases Qwen-Scope, an open-source suite of 14 Sparse AutoEncoders (SAEs) for Qwen3/3.5 models, enabling inference-time steering and benchmark analysis without model runs.

May 1, 2026

AI NewsMachine LearningAI

Transformer Output Selection: Softmax and Fully Connected Layer Integration

Learn how Transformer decoders transform terminal residual values into vocabulary-mapped outputs using fully connected layers and softmax for token prediction.

May 1, 2026

AI NewsMachine LearningSoftware Engineering

Inside OpenAI's Parameter Golf: Training High-Performance LLMs in 10 Minutes

OpenAI's Parameter Golf challenge requires training a 16MB language model in 10 minutes, with top developers reaching 1.0810 bits-per-byte.

May 1, 2026

AI NewsArtificial IntelligenceMachine Learning

AI-Driven ML: Automating Time-Series Forecasting with Anton

MindsDB introduces Anton, an open-source AI agent that automates the end-to-end ML lifecycle, achieving a 14.6% MAPE on demand forecasting within minutes.

Apr 30, 2026

AI NewsAI InfrastructureMachine Learning

FlashQLA: High-Performance Linear Attention Library for NVIDIA Hopper GPUs

The Qwen Team has released FlashQLA, a linear attention kernel library achieving up to 3x speedup on NVIDIA Hopper GPUs for Gated Delta Network architectures.

Apr 29, 2026

AI NewsMachine LearningSoftware Engineering

OpenAI Privacy Filter: Building a Production PII Redaction Pipeline

Learn to implement a production-grade PII detection pipeline using the OpenAI Privacy Filter to automatically identify and redact sensitive data like API keys and personal addresses.

Apr 29, 2026

AI NewsComputer VisionMachine Learning

Best of WACV 2026: Advances in Zero-Shot Sampling and OOD Detection

Join Voxel51 on April 30 for the Best of WACV 2026 virtual event featuring four technical talks on subspace sampling and MLLM robustness.

Apr 28, 2026

AI NewsAgentic AIMachine Learning

Optimizing Long-Term Memory Retrieval with Reinforcement Learning for LLM Agents

Build a PPO-trained RL agent that optimizes long-term memory retrieval for LLMs, outperforming standard cosine similarity in complex QA tasks.

Apr 27, 2026

AI NewsMachine LearningSoftware Engineering

RMS Normalisation and Residual Connections: Stabilizing Deep Neural Networks

Stabilize deep networks by preventing activation drift and vanishing gradients using RMSNorm and residual connections for efficient training.

Apr 27, 2026

AI NewsMachine LearningComputer Vision

Meta AI Sapiens2: Scaling Human-Centric Vision Models to 5B Parameters and 4K Resolution

Meta AI's Sapiens2 scales to 5B parameters and 1B images, achieving 82.3 mAP in pose estimation and 82.5 mIoU in segmentation across 1K and 4K resolutions.

Apr 27, 2026

AI NewsLarge Language ModelMachine Learning

Talkie-1930: A 13B Vintage LLM Trained Exclusively on Pre-1931 Data

Researchers released Talkie-1930, a 13B parameter open-weight LLM trained on 260 billion tokens of pre-1931 text to eliminate benchmark contamination and research historical reasoning.

Apr 27, 2026

AI NewsArtificial IntelligenceMachine Learning

Optimizing CJK Text Wrapping with BudouX Machine Learning Parsers

Learn to implement BudouX for phrase-aware line breaking in Japanese, Chinese, and Thai, utilizing lightweight ML models to process text at speeds exceeding 1,000k chars/sec.

Apr 26, 2026

AI NewsMachine LearningWeb Development

Local Browser-Based AI: Running Neural Networks for Audio Stem Separation

Stem separation moves to the edge as Demucs v4 runs in a browser tab via ONNX and WASM, processing a 4-minute song locally in 3-5 minutes.

Apr 24, 2026

AI NewsMachine LearningSoftware Engineering

Implementing Microsoft’s OpenMementos: Trace Analysis and Context Compression for LLMs

Implement Microsoft’s OpenMementos dataset to achieve ~6× token compression in reasoning traces for efficient LLM fine-tuning and inference.

Apr 24, 2026

AI NewsMachine LearningSoftware Engineering

Mastering OpenMythos: Implementing Recurrent-Depth Transformers with MLA and MoE

OpenMythos enables deeper reasoning via recurrent computation, allowing Multi-Head Latent Attention (MLA) to achieve significantly smaller KV-cache footprints than GQA.

Apr 23, 2026

AI NewsAI InfrastructureMachine Learning

Google DeepMind’s Decoupled DiLoCo: Scaling AI Training with 88% Goodput and Asynchronous Fault Tolerance

Google DeepMind's Decoupled DiLoCo achieves 88% goodput under high hardware failure rates and reduces inter-datacenter bandwidth from 198 Gbps to 0.84 Gbps.

Apr 23, 2026

AI NewsAgentic AIMachine Learning

Qwen3.6-27B: Dense 27B Model Outperforms 397B MoE in Agentic Coding

Alibaba releases Qwen3.6-27B, a dense model achieving 77.2 on SWE-bench Verified and outperforming the 397B MoE on repository-level reasoning.

Apr 22, 2026

AI NewsMachine LearningSoftware Development

Building a Character-Level Tokenizer for MicroGPT

Build a character-level tokenizer with a synthetic BOS token, creating a vocabulary of 27 tokens to convert text into integer IDs for machine learning.

Apr 22, 2026

AI NewsMachine LearningTutorials

Building Conditional Bayesian Hyperparameter Optimization Pipelines with Hyperopt and TPE

Implement a production-grade Bayesian optimization pipeline using Hyperopt and TPE to dynamically switch model families with early stopping and ROC-AUC evaluation.

Apr 21, 2026

AI NewsAgentic AIMachine Learning

Hugging Face Launches ml-intern: Automating LLM Post-Training Workflows

Hugging Face's ml-intern automates LLM post-training, boosting Qwen3-1.7B's GPQA score from 10% to 32% in under 10 hours.

Apr 21, 2026

AI NewsAI SecurityMachine Learning

Secure LLM Agents with Two-Stage Prompt Injection Detection

ZooClaw releases a specialized prompt injection detection API using a two-stage architecture to protect agentic workflows. The system achieves a 0.972 F1 score in English benchmarks, significantly outperforming GPT-4o, and provides sub-10ms latency for 95 percent of production traffic.

Apr 20, 2026