§ 2.1
Distributed orchestration
AHISTER, DEBOHAC, and the cluster lifecycle: distributing evolutionary search across heterogeneous compute under hierarchical capacity and budget.
Read moreResearch at Ufinq
Ufinq is the research arm behind Diafunc: a focused effort to make Symbolic AI scale. Where deep learning compresses data into millions of opaque weights, Ufinq evolves code: small, readable programs that describe how data behaves, deployable on any machine and readable line by line.
The work is organized around seven research areas, each a thread of active investigation. The corresponding publications are listed under Papers; short-form notes on individual problems live under Notes.
Symbolic AI is not a smaller deep learning. It is a different category of model, and a different research program.
Research areas
§ 2.2
Symbolic refinement
Algebraic simplification, the e-graph rewriter, and normalization: every candidate is cleaned and tuned before it enters the gene pool.
Read more§ 2.3
Constant optimization
Coordinate Descent, CMA-ES, L-BFGS, Nelder-Mead: numeric methods specialized for the constraints of symbolic regression candidates.
Read more§ 2.4
Approximate evaluation
CRESCENT: scoring a candidate on only as many rows as it takes to know whether it matters.
Read more§ 2.5
Genetic operators
How candidates are generated and recombined: mutation families, crossover families, and the adaptive selection between them.
Read more§ 2.6
Search strategies
Navigating the universal function space: branch roles, an adaptive search space, and the two diversity checks that hold populations open.
Read more§ 2.7
Compositional search
Building large models from smaller ones: surrogate-seeded starting points, automatic decomposition, and sub-searches that solve one part at a time.
Read moreOne quality, one model
The search does not commit to a model early. It keeps a Hall of Fame of the best candidates found by any branch, small blunt ones and large accurate ones alike, all ranked by a single quality value that already prices size against accuracy. When the search ends, the best of them are polished once more and screened, and one model is returned. The trade-off between accuracy and size is settled by the description-length criterion, not handed to the reader.
Research principles
Ufinq research is closed-source by default, but open in its ideas. Algorithms, designs, and empirical results are described in papers and technical reports; the productized implementation is part of the Diafunc platform. The asymmetry between reading a paper and reproducing a full distributed system is deliberate, and the direction is reversible: closed today, with the option to open components later if and when it serves the research community.
Three commitments shape what gets prioritized:
Readable modelsEvery output is readable code, not opaque weights. The result must stay readable as it scales.
Distributed by constructionAlgorithms are designed for cluster execution from day one, not single-machine prototypes retrofitted later.
Honest benchmarksEvery claim ships with a public benchmark that runs every week, with fixed configurations and published failures.
Where to read more
The full output of the research effort lives on the Papers page. Empirical evaluations are tracked under Benchmarks. For the short version of how the system works end-to-end, see Technology.