🧠 Machine Learning - hop1.ng.1357 · Scour

Grow and mow: interpretable models with boosting, symbolic regression and e-graphs ⚙️MLOps

mchav.github.io·1d·Hacker News

Sparse Bayesian Learning Algorithms Revisited: From Learning Majorizers to Structured Algorithmic Learning using Neural Networks ⚗️Knowledge Distillation

arxiv.org·4d

milanm/AutoGrad-Engine: A complete GPT language model (training and inference) in ~600 lines of pure C#, zero dependencies 🤖LLM

github.com·18h·Hacker News

Where AI Will and Won’t Replace Us 🔍AI Interpretability

deadneurons.substack.com·2d·Substack

Inference Arena – new benchmark of local inference and training ⚙️MLOps

kvark.github.io·4d·Hacker News

Show HN: Train ML models for 80% less by always picking the cheapest Spot region 🔢BitNet

spotroute.co·2d·Hacker News

Safeguarded AI 🛡️AI Safety

aria.org.uk·2d·Hacker News

Show HN: Pre-training, fine-tuning, and evals platform ⚙️MLOps

oumi.ai·6d·Hacker News

benchmarking inference of popular models on consumer hardware ⚙️MLOps

inferena.tech·5d·Hacker News

LLM inference engine from scratch in C++ ✨LLMs

anirudhsathiya.com·4d·Hacker News

Do RL on a model with your vector db ⚙️MLOps

cgft.io·3d·Hacker News

Sparse-Aware Neural Networks for Nonlinear Functionals: Mitigating the Exponential Dependence on Dimension 🔍AI Interpretability

arxiv.org·1d

Scientific Knowledge-driven Decoding Constraints Improving the Reliability of LLMs ⚙️MLOps

arxiv.org·1d

techascent/tech.ml.dataset: A Clojure high performance data processing system ⚙️MLOps

github.com·4d·Hacker News

Efficient Quantization of Mixture-of-Experts with Theoretical Generalization Guarantees 🔢BitNet

arxiv.org·1d

ertis-research/kafka-ml: Kafka-ML: connecting the data stream with ML/AI frameworks (now TensorFlow and PyTorch!) ⚙️MLOps

github.com·3d·Hacker News

OmniTabBench: Mapping the Empirical Frontiers of GBDTs, Neural Networks, and Foundation Models for Tabular Data at Scale 🤖LLM

arxiv.org·1d

Epistemic Blinding: An Inference-Time Protocol for Auditing Prior Contamination in LLM-Assisted Analysis 🤖LLM

arxiv.org·2d

Prune-Quantize-Distill: An Ordered Pipeline for Efficient Neural Network Compression 🔢BitNet

arxiv.org·2d

LLM Evaluation as Tensor Completion: Low Rank Structure and Semiparametric Efficiency 🤖LLM

arxiv.org·2d

Loading more...