A harness for AI agents enabled construction of a Rust library with 100+ problem types and 200+ reduction rules for NP-hard problems in three months.
Parallelizing the dual revised simplex method,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
Open-source neural network iris matchers (TripletIris using batch-hard triplet loss and ArcIris using ArcFace loss) plus compliant C++ implementations of HDBIF and CRYPTS are released, evaluated on IREX X and eight academic datasets, and accompanied by segmentation tools to lower entry barriers for
SPARK is a sparsity-aware near-cache ILP accelerator that reuses L1 cache structures to deliver up to 15x speedup and 152x energy reduction versus CPUs on sparse MIPLIB workloads with 1.4% area overhead.
citing papers explorer
-
Problem Reductions at Scale: Agentic Integration of Computationally Hard Problems
A harness for AI agents enabled construction of a Rust library with 100+ problem types and 200+ reduction rules for NP-hard problems in three months.
-
Lowering the Barrier to IREX Participation: Open-Source Algorithms, Toolkit, and Benchmarking for Iris Recognition
Open-source neural network iris matchers (TripletIris using batch-hard triplet loss and ArcIris using ArcFace loss) plus compliant C++ implementations of HDBIF and CRYPTS are released, evaluated on IREX X and eight academic datasets, and accompanied by segmentation tools to lower entry barriers for
-
A comprehensive study on ILP acceleration accounting for sparsity, area, energy, data movement using near-memory architecture
SPARK is a sparsity-aware near-cache ILP accelerator that reuses L1 cache structures to deliver up to 15x speedup and 152x energy reduction versus CPUs on sparse MIPLIB workloads with 1.4% area overhead.