BloGDiT introduces blocked Gibbs-style denoising in diffusion transformers to enable large targeted edits for constraint satisfaction and optimization, matching or exceeding prior methods on Sudoku, graph coloring, MIS, and MaxCut.
Difusco: Graph-based diffusion solvers for combinatorial optimization.Advances in neural information processing systems, 36:3706–3731
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5verdicts
UNVERDICTED 5representative citing papers
NCP trains a neural network to predict certificate-level dual prices for CO problems, enabling structured primal recovery with a local second-order error guarantee when consistency holds.
GOAL uses conditioned diffusion on relational graphs with typed edges to produce feasible multi-objective solutions for scheduling problems, reporting 100% feasibility and sub-0.2% MAPE on FSP, JSP, and FJSP up to 20 jobs.
CCEM parameterizes compositional energy factors with input-convex neural networks and optimizes over a convex relaxation to enable deterministic scaling from small to large combinatorial reasoning instances.
GaiaFlow combines semantic-guided diffusion tuning with early-exit and quantization methods to lower carbon emissions in neural information retrieval while maintaining competitive effectiveness.
citing papers explorer
-
Blocked Gibbs meets Diffusion Transformers: Unsupervised Learning for Constraint Optimization
BloGDiT introduces blocked Gibbs-style denoising in diffusion transformers to enable large targeted edits for constraint satisfaction and optimization, matching or exceeding prior methods on Sudoku, graph coloring, MIS, and MaxCut.
-
Neural Certificate Pricing for Combinatorial Optimization Problems
NCP trains a neural network to predict certificate-level dual prices for CO problems, enabling structured primal recovery with a local second-order error guarantee when consistency holds.
-
GOAL: Graph-based Objective-Aligned Diffusion Solvers for Dynamic Multi-Objective Optimization
GOAL uses conditioned diffusion on relational graphs with typed edges to produce feasible multi-objective solutions for scheduling problems, reporting 100% feasibility and sub-0.2% MAPE on FSP, JSP, and FJSP up to 20 jobs.
-
Convex Compositional Reasoning Models
CCEM parameterizes compositional energy factors with input-convex neural networks and optimizes over a convex relaxation to enable deterministic scaling from small to large combinatorial reasoning instances.
-
GaiaFlow: Semantic-Guided Diffusion Tuning for Carbon-Frugal Search
GaiaFlow combines semantic-guided diffusion tuning with early-exit and quantization methods to lower carbon emissions in neural information retrieval while maintaining competitive effectiveness.