Trained on 1B+ Jets: OmniLearned Upgrades Foundation Models for Particle Physics
burny_tech · x · 2026-10-25
OmniLearned: Major Upgrade to a Jet Physics Foundation Model
arXiv 2510.24066 (published in Phys. Rev. D) presents a major upgrade of the OmniLearn foundation model, now framed as OmniLearned, with three new elements:
- Architecture & training: updated model architecture and training procedure
- Scale: trained on over one billion jets
- Open ecosystem: well-documented software for accessing all datasets and models
Validated on three representative tasks:
- Top-quark jet tagging on the community Delphes-based benchmark
- b-tagging with full ATLAS simulation
- Anomaly detection on CMS experimental data
OmniLearned achieves state-of-the-art on all three, expanding the discovery potential of past, current, and future collider experiments. Authors include Wahid Bhimji, Vinicius Mikuni, and Benjamin Nachman.
More from Research
- New AI contracting research: agents negotiate badly under uncertainty and deliberately break deals — xuanalogue · 2026-10-25
- EMNLP paper introduces Concept-Targeted Attribution, tracing the circuits behind linear probes — ZhijingJin · 2026-10-25
- bbtree claims fastest concurrent btree: 5x faster than std BTreeMap single-threaded — tianyin_xu · 2026-10-25
- Covert channel math: 128-bit secret leaks in 13s, 1TB weights take centuries — vishalmisra · 2026-10-25
- CultureScore, a cultural evaluation benchmark, to be presented at EMNLP 2026 — pliang279 · 2026-10-25
- Why Formal Verification Is Exploding Now: Proofs Get Cheaper, Exploits Costlier — burny_tech · 2026-10-25