RoverDevKit is an open physics-based evaluator for lunar micro-rover conceptual design that runs in 30 ms and uses NSGA-II to identify mission-dependent optimal wheel configurations and binding trades.
Title resolution pending
33 Pith papers cite this work. Polarity classification is still indexing.
33
Pith papers citing it
citation-role summary
background 2
baseline 1
method 1
citation-polarity summary
representative citing papers
A co-evolutionary method evolves LLM prompts and circuits to produce 8-bit approximate multipliers with better error-area trade-offs than EvoApproxLib.
COTHROM applies a Potts Hamiltonian representation of constitutional mandates, MCMC/simulated annealing optimization, and Pareto/MCDA analysis to improve Irish constituency boundaries over existing legal ones in County Cork for proportionality and compactness across weightings.
A U-Net surrogate with multigroup attention pooling is trained on OpenMC sensitivity data and combined with gradient optimization to generate grid-based critical experiment geometries that achieve c_k values up to 0.97757 for HALEU fuel validation.
An optimization-based inverse design method discovers metainterfaces achieving custom friction laws including power laws with exponents from 2/3 to 1.35 and bilinear forms, with experimental validation for some cases.
LLMForge is a NAS framework with Infinite-Head Attention, a Forge-Former surrogate, and Forge-DSE engine that discovers hardware-specific architectures for edge language models, yielding variants with improved accuracy, energy, or latency on different substrates.
DRSR uses Quality-Diversity to produce diverse symbolic regression expressions differing in residual distributions, enabling post-search selection on synthetic and astronomical data.
DIPS fine-tunes LLMs to output ordered feasible decision vectors approximating Pareto fronts for constrained bi-objective convex problems, reaching 95-98% normalized hypervolume with 0.16s inference.
A homotopy-plus-MCMC data-generation pipeline trains a mass-conditioned diffusion model that yields 40% more feasible initial costates and a better Pareto front for multiobjective indirect low-thrust transfers than adjoint-control-transformation baselines.
GLUE orchestrates frozen pre-trained generative models into a system-level design generator that enforces feasibility, performance, and diversity, with data-driven and data-free variants benchmarked on UAV design.
Brush is a new symbolic regression method that integrates tree-like rules with function optimization, matching or beating decision trees and forests on clinical scoring tasks while producing simpler interpretable models.
A methodology is proposed to integrate Life Cycle Assessment as an additional discipline in Multidisciplinary Design Analysis and Optimization frameworks for launch vehicle eco-design, demonstrated through multi-objective optimization on an expendable launcher.
Adjusting Jansen linkage lengths within 29% yields designs that flatten stance by 28%, smooth velocity by 58%, and cut total joint wear by 56% while satisfying gait constraints.
TCP-MCP co-evolves prompts and topologies for multi-agent systems, reporting 82.66-96.61% accuracy on MMLU-Pro/MMLU/GSM8K while using up to 5.69x fewer tokens than debate baselines.
Develops a posterior-informed two-stage stochastic multi-objective optimization framework for exploration well portfolio selection under uncertainty, solved via sample average approximation and NSGA-II.
Surrogate-assisted neuroevolution produces Pareto-optimal chlorine dosing policies for water distribution systems that outperform PPO on four practical objectives.
CoCoMagic applies constrained cooperative co-evolution to metamorphic and differential testing to find up to 287% more distinct behavioral divergences in an end-to-end ADS than baseline search methods.
Describes an LLM-orchestrated workflow that trains a surrogate on CAE data (R²=0.87), runs NSGA-II optimization, generates morphed geometries, and produces 35 compliant pedestrian-protection designs in a front-bumper case study.
A framework repairs CPS requirements in Simulink by leveraging system execution data and is evaluated as effective on six real-world case studies covering 12 requirements.
Physics-informed active learning optimizes tri-gate FinFETs, identifying designs with 2x better switching efficiency and 3.3 A drive current in multi-fin setups.
A controlled benchmark for context-sensitive memory shows adaptive plasticity (especially homeostatic) enables recall under weak support, with quantum-like models preserving order sensitivity better than Markov controls but without universal advantage.
Post-selection with DL or FBF after multi-objective GP search improves test-set performance over AIC/BIC baselines on noisy synthetic and real regression tasks, while using DL directly as fitness often causes premature convergence to overly simple models.
A CNN detects 19,685 LAEs at z=2-3.5 in DESI DR1 spectra with 95% purity and completeness.
CVT archives with learned chemical embeddings improve median global hypervolume and multi-objective quality diversity in NLO molecular design compared to grid-based archives.