Causal foundation models estimate causal effects in-context, no fine-tuning needed

Layer6 · hf · 2026-09-09

Layer6's Causal Foundation Models apply pretrained neural networks to causal inference: estimating causal effects on new datasets via in-context learning, without any fine-tuning.

The work transfers foundation models' in-context learning ability to the classic statistical problem of causal effect estimation — an exploratory direction in AI for science.

Original post →

More from Research

• Lila Sciences cofounder Ben Kompa makes MIT TR35 list for autonomous science push — tw_killian · 2026-09-09
• 100 rule-based verifiers and 300 tasks: team builds a working RL recipe for video models — DanielKhashabi · 2026-09-09
• Researchers' 2022 paper warned privacy issues like this were coming — thegautamkamath · 2026-09-09
• Local Bad Behavior In RL Doesn't Produce Emergent Misalignment, Per Hacker-Opus — 1a3orn · 2026-09-09
• Speculative thread: capability-RL-trained LLMs may learn a 'use every affordance' heuristic — 1a3orn · 2026-09-09
• Pretraining progress is mostly from data: 12x compute gains from data vs 3.7x from models — sebkrier · 2026-09-09

Research channel →