COSMOS (Cooperative Operator Specialists with Mechanism-level Operator Soft-routing) keeps four process-biased specialists active at every step and mixes them with a dense learned gate, fusing features through a small network.
Soft routing among process experts helps PDE forecasting, but gains prove seed-dependent
COSMOS continuously mixes four mechanism-biased neural operators; an 11-seed audit overturns an early win over FNO and shows learned routing does not match true physical mixtures.
Big Tech
Anupam Rawat · Manikandan Padmanaban · Jagabondhu Hazra
Indian Institute of Technology Bombay · IBM Research
Research Digest··3 min read
The authors propose COSMOS, a neural operator that densely mixes four process-biased specialists with a learned continuous gate instead of sparse top-K expert selection.
Why this paper
From IBM Research and Indian Institute of Technology Bombay · Part of Mixture-of-Experts Specialization, now 4 papers
In one line
Dense soft routing yields 2.2 times lower rollout error than hard top-1 routing on a compositional PDE benchmark.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ✓Limitations stated by the authors
- ✓Reports numbers on named benchmarks
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§