Yang Li

Native Adaptive Solution Expansion for Diffusion-based Combinatorial Optimization

MaskCO: Masked Generation Drives Effective Representation Learning and Exploiting for Combinatorial Optimization

Invariant Predict-and-Combinatorial Optimization under Distribution Shifts

Smarter Not Harder: Generative Process Evaluation with Intrinsic-Signal Driving and Ability‑Adaptive Reward Shaping

ConRep4CO: Contrastive Representation Learning of Combinatorial Optimization Instances across Types

One Direction to Rule Them All: Toward Generalizable Solving Strategies Across Combinatorial Optimization Problems

M$^2$GenCO: Multi-task Meta Learning for Generative Combinatorial Optimization

Generation as Search Operator for Test-Time Scaling of Diffusion-based Combinatorial Optimization

StruDiCO: Structured Denoising Diffusion with Gradient-free Inference-stage Boosting for Memory and Time Efficient Combinatorial Optimization

Unify ML4TSP: Drawing Methodological Principles for TSP and Beyond from Streamlined Design Space of Learning and Search

UniCO: On Unified Combinatorial Optimization via Problem Reduction to Matrix-Encoded General TSP

Generative Modeling Reinvents Supervised Learning: Label Repurposing with Predictive Consistency Learning

COExpander: Adaptive Solution Expansion for Combinatorial Optimization

Your Consistency Model is Secretly a More Powerful Supervised Learning Paradigm for Learning Tasks with Complex Labels

Toward Learning Generalized Cross-Problem Solving Strategies for Combinatorial Optimization

Learning General Representations Across Graph Combinatorial Optimization Problems

Inv-PnCO: Invariant Predict-and-Combinatorial Optimization under Distribution Shifts