🧠 Machine Learning - hop1.ng.1357 · Scour

Machine Learning Visualized – Machine Learning Visualized 🔍AI Interpretability

ml-visualized.com·6d·Hacker News

Training Machine Learning Models on Encrypted Data: A Privacy-Preserving Framework using Homomorphic Encryption 🔐Cryptography

AI could help human scientists pick promising research topics 🧭Content Discovery

physicsworld.com·9h·Hacker News

Stripe: Radar Technical Guide 🔐Hardware Security

stripe.com·2d·Hacker News

What are embeddings? ✨LLMs

vickiboykis.com·4d

ABTdomain/dksplit: DKSplit - fast word segmentation for Python. Split domain names and concatenated strings into words using BiLSTM-CRF + ONNX Runtime. 🎖Text Quality Models

github.com·1d·Hacker News

Hyper Input Convex Neural Networks for Shape Constrained Learning and Optimal Transport 🔢BitNet

A Primer on LLM Post-Training 🤖LLM

pytorch.org·2d·Hacker News

a real, long term use of ML and AI that matters 🎯Alignment Research

brain-regeneration.com·6d·Hacker News

facebookresearch/sapiens2: [ICLR 26] 1K resolution vision transformers pretrained on 1B human images. ⚡Edge AI

deepseek-ai/DeepSeek-V4-Flash ⚙️MLOps

huggingface.co·6d·Hacker News

Do Larger Models Really Win in Drug Discovery? A Benchmark Assessment of Model Scaling in AI-Driven Molecular Property and Activity Prediction ⚙️MLOps

Which one is more important: more parameters or more computation? (2021) 💭Reasoning Models

parl.ai·6d·Hacker News

epscylonb/1386.ai.rocm: A lightweight transformer language model built from scratch in PyTorch, trained on a single consumer GPU with a full pipeline for data processing, pretraining, and instruction tuning. ⚙️MLOps

github.com·2d·Hacker News

Deep-testing: the case of dependence detection ⚙️MLOps

What I learned asking 11 AI models to grade each other's AI predictions 🛡️AI Security

·6d·Hacker News

vLLM-Lens: Fast Interpretability Tooling That Scales to Trillion-Parameter Models ⚙️MLOps

lesswrong.com·6d

MoRFI: Monotonic Sparse Autoencoder Feature Identification 🤖LLM

Monitoring LLM behavior: Drift, retries, and refusal patterns 🛡️AI Safety

venturebeat.com·5d·Hacker News

SciHorizon-DataEVA: An Agentic System for AI-Readiness Evaluation of Heterogeneous Scientific Data 🕹️Agentic AI

Log in to enable infinite scrolling