Tagged articles

auto-research

5 articles · Page 1 of 1
Machine Heart
Machine Heart
Aug 30, 2026 · Artificial Intelligence

How Large Discovery Models Enable AI to Design the Next Experiment

The Large Discovery Model (LDM) combines a generative foundation model with a Gaussian‑process reward model to create fast and slow learning loops that iteratively propose, evaluate, and refine experimental designs across neural‑network training, antibody engineering, and small‑molecule optimization, achieving significant performance gains over pure LLM or Bayesian‑optimization baselines.

Bayesian optimizationLarge Discovery Modelsantibody design
0 likes · 13 min read
How Large Discovery Models Enable AI to Design the Next Experiment
AI Programming Lab
AI Programming Lab
Aug 21, 2026 · Artificial Intelligence

How I Combined Claude Code and Codex to Produce an Accepted Conference Paper

The author details a step‑by‑step auto‑research workflow that uses Claude Code and Codex across multiple medical imaging challenges, from dataset preparation and model training on RTX 4090 GPUs to AI‑generated draft writing, iterative Codex review, and ultimately achieving a conference paper acceptance.

AI-assisted researchClaude CodeCodex
0 likes · 5 min read
How I Combined Claude Code and Codex to Produce an Accepted Conference Paper
Machine Heart
Machine Heart
Aug 11, 2026 · Artificial Intelligence

MLS‑Bench: A New Benchmark That Strips Away the Illusion of AI Research Gains

The MLS‑Bench benchmark introduces 140 executable research tasks across twelve ML domains to rigorously attribute performance gains to genuine method discovery rather than engineering tricks, revealing that current large‑model agents excel at component recombination but still lag in proposing truly novel, transferable algorithms.

AI research benchmarkMLS‑Benchauto-research
0 likes · 16 min read
MLS‑Bench: A New Benchmark That Strips Away the Illusion of AI Research Gains
PaperAgent
PaperAgent
May 22, 2026 · Artificial Intelligence

A Systematic Review of the Latest Auto‑Research Landscape

The article presents a four‑phase, eight‑stage systematic analysis of AI‑driven auto‑research, exposing reliability gaps, bottlenecks, and best‑practice deployment through human‑governed collaboration, while detailing benchmarks, failure modes, and architectural families.

AI research automationauto-researchevaluation benchmarks
0 likes · 11 min read
A Systematic Review of the Latest Auto‑Research Landscape