15 citations · 20 across the 15 of their papers we have counts for
15 papers
Hidden Decoding at Scale: Latent Computation Scaling for Large Language Models
Aiwei Liu, Cheng Shi, Chuhan Wu +44
Scaling Large Language Models (LLMs) has been driven mainly by enlarging the Transformer backbone, but for an already-strong model this requires another round of costly pretraining…
Automated Optimization Modeling via a Localizable Error-Driven Perspective
Weiting Liu, Han Wu, Yufei Kuang +4
Automated optimization modeling via Large Language Models (LLMs) has emerged as a promising approach to assist complex human decision-making. While post-training has become a pivot…
OptiTree: Hierarchical Thoughts Generation with Tree Search for LLM Optimization Modeling
Haoyang Liu, Jie Wang, Yuyang Cai +3
Optimization modeling is one of the most crucial but technical parts of operations research (OR). To automate the modeling process, existing works have leveraged large language mod…
Advancing Symbolic Discovery on Unsupervised Data: A Pre-training Framework for Non-degenerate Implicit Equation Discovery
Kuang Yufei, Wang Jie, Huang Haotong +5
Symbolic regression (SR) -- which learns symbolic equations to describe the underlying relation from input-output pairs -- is widely used for scientific discovery. However, a rich…
Enhancing Character-Level Understanding in LLMs through Token Internal Structure Learning
Zhu Xu, Zhiqiang Zhao, Zihan Zhang +6
Tokenization methods like Byte-Pair Encoding (BPE) enhance computational efficiency in large language models (LLMs) but often obscure internal character structures within tokens. T…
MILP-StuDio: MILP Instance Generation via Block Structure Decomposition
Haoyang Liu, Jie Wang, Wanbo Zhang +6
Mixed-integer linear programming (MILP) is one of the most popular mathematical formulations with numerous applications. In practice, improving the performance of MILP solvers ofte…
Deep Symbolic Optimization for Combinatorial Optimization: Accelerating Node Selection by Discovering Potential Heuristics
Hongyu Liu, Haoyang Liu, Yufei Kuang +2
Combinatorial optimization (CO) is one of the most fundamental mathematical models in real-world applications. Traditional CO solvers, such as Branch-and-Bound (B&B) solvers, heavi…
Robust Deep Reinforcement Learning with Adaptive Adversarial Perturbations in Action Space
Qianmei Liu, Yufei Kuang, Jie Wang
Deep reinforcement learning (DRL) algorithms can suffer from modeling errors between the simulation and the real world. Many studies use adversarial learning to generate perturbati…
Learning to Cut via Hierarchical Sequence/Set Model for Efficient Mixed-Integer Programming
Jie Wang, Zhihai Wang, Xijun Li +7
Cutting planes (cuts) play an important role in solving mixed-integer linear programs (MILPs), which formulate many important real-world applications. Cut selection heavily depends…
Machine Learning Insides OptVerse AI Solver: Design Principles and Applications
Xijun Li, Fangzhou Zhu, Hui-Ling Zhen +23
In an era of digital ubiquity, efficient resource management and decision-making are paramount across numerous industries. To this end, we present a comprehensive study on the inte…
State Sequences Prediction via Fourier Transform for Representation Learning
Mingxuan Ye, Yufei Kuang, Jie Wang +4
While deep reinforcement learning (RL) has been demonstrated effective in solving complex control tasks, sample efficiency remains a key challenge due to the large amounts of data…
Accelerate Presolve in Large-Scale Linear Programming via Reinforcement Learning
Yufei Kuang, Xijun Li, Jie Wang +7
Large-scale LP problems from industry usually contain much redundancy that severely hurts the efficiency and reliability of solving LPs, making presolve (i.e., the problem simplifi…
Promoting Generalization for Exact Solvers via Adversarial Instance Augmentation
Haoyang Liu, Yufei Kuang, Jie Wang +3
Machine learning has been successfully applied to improve the efficiency of Mixed-Integer Linear Programming (MILP) solvers. However, the learning-based solvers often suffer from s…
Learning Cut Selection for Mixed-Integer Linear Programming via Hierarchical Sequence Model
Zhihai Wang, Xijun Li, Jie Wang +5
Cutting planes (cuts) are important for solving mixed-integer linear programs (MILPs), which formulate a wide range of important real-world applications. Cut selection -- which aim…
Learning Robust Policy against Disturbance in Transition Dynamics via State-Conservative Policy Optimization
Yufei Kuang, Miao Lu, Jie Wang +3
Deep reinforcement learning algorithms can perform poorly in real-world tasks due to the discrepancy between source and target environments. This discrepancy is commonly viewed as…