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.
pymoo: Multi-Objective Optimization in Python,
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
DORA is an instruction-based DNN accelerator architecture with a two-stage compilation framework that delivers stable efficiency across varied workloads and up to 5x throughput gains versus prior accelerators on FPGA.
New cycle-consistent optimization, task vector theory, singular vector decompositions, adaptive routing, and efficient evolutionary search provide foundations for merging neural network weights across tasks.
A hybrid optimization framework using maximal disjoint ball decomposition and interior point methods achieves over 10% improvement and 0.6-2% accuracy relative to ground truth on spatial packaging benchmarks.
An integrated optimization approach using MIQP for packing, bi-level assignment for placement, constraint programming for scheduling, and conflict-resolution routing enables scalable daily operations for personalized pharmaceutical production on planar systems.
A research roadmap analyzing the current state of search-based software engineering with foundation models, outlining challenges and directions across three integration aspects.
citing papers explorer
-
GLUE: Coordinating Pre-Trained Generative Models for System-Level Design
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.
-
DORA: Dataflow-Instruction Orchestration Architecture for DNN Acceleration
DORA is an instruction-based DNN accelerator architecture with a two-stage compilation framework that delivers stable efficiency across varied workloads and up to 5x throughput gains versus prior accelerators on FPGA.
-
Model Merging: Foundations and Algorithms
New cycle-consistent optimization, task vector theory, singular vector decompositions, adaptive routing, and efficient evolutionary search provide foundations for merging neural network weights across tasks.
-
A Hybrid Optimization Framework for Spatial Packaging of Interconnected Systems
A hybrid optimization framework using maximal disjoint ball decomposition and interior point methods achieves over 10% improvement and 0.6-2% accuracy relative to ground truth on spatial packaging benchmarks.
-
Integrated packing, placement, scheduling, and routing of personalized production: a pharmaceutical Industry 4.0 use-case with a planar transport system
An integrated optimization approach using MIQP for packing, bi-level assignment for placement, constraint programming for scheduling, and conflict-resolution routing enables scalable daily operations for personalized pharmaceutical production on planar systems.
-
Search-Based Software Engineering and AI Foundation Models: Current Landscape and Future Roadmap
A research roadmap analyzing the current state of search-based software engineering with foundation models, outlining challenges and directions across three integration aspects.