Author name cluster

Xia Jiang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

2 author rows

EAAI Journal 2025 Journal Article

A Multi-Scale Sparse Channel Transformer Network for image reconstruction of astronomical bright source contamination

Yajuan Zhang
Congcong Shen
Xia Jiang
Bo Qiu
Ali Luo
Fuji Ren
Yuanlu Chen

Bright source contamination has long been a challenging issue in the field of image processing, particularly in applications such as astronomical observations, satellite imaging, and nighttime surveillance. To address this issue, this paper proposes a novel Multi-Scale Sparse Channel Transformer Network (MSCformer) aimed at achieving high-quality image reconstruction under the influence of bright source contamination. The network integrates a Top-k Sparse Attention mechanism with a Channel Attention module, enabling selective focus on the most informative features and adaptive weight allocation across channels. Additionally, a Multi-Scale Dual-Gate Feedforward Network is designed to further enhance the expression of valuable features while suppressing redundant information. Experimental results demonstrate that the proposed method exhibits outstanding performance in practical applications on the Sloan Digital Sky Survey (SDSS) photometric image dataset. Compared to existing state-of-the-art techniques, MSCformer achieves significant performance improvements, with a Peak Signal-to-Noise Ratio (PSNR) of 45. 093 decibel(dB), a Structural Similarity Index Measure(SSIM) of 0. 978, and a Pixel Average Absolute Error (PAAE) of 0. 675. This not only significantly enhances the removal of bright source contamination in the field of astronomy but also provides important reference value for subsequent research in related domains.

Details DOI

ICLR Conference 2025 Conference Paper

DRoC: Elevating Large Language Models for Complex Vehicle Routing via Decomposed Retrieval of Constraints

Xia Jiang
Yaoxin Wu
Chenhao Zhang
Yingqian Zhang 0001

This paper proposes Decomposed Retrieval of Constraints (DRoC), a novel framework aimed at enhancing large language models (LLMs) in exploiting solvers to tackle vehicle routing problems (VRPs) with intricate constraints. While LLMs have shown promise in solving simple VRPs, their potential in addressing complex VRP variants is still suppressed, due to the limited embedded internal knowledge that is required to accurately reflect diverse VRP constraints. Our approach mitigates the issue by integrating external knowledge via a novel retrieval-augmented generation (RAG) approach. More specifically, the DRoC decomposes VRP constraints, externally retrieves information relevant to each constraint, and synergistically combines internal and external knowledge to benefit the program generation for solving VRPs. The DRoC also allows LLMs to dynamically select between RAG and self-debugging mechanisms, thereby optimizing program generation without the need for additional training. Experiments across 48 VRP variants exhibit the superiority of DRoC, with significant improvements in the accuracy rate and runtime error rate delivered by the generated programs. The DRoC framework has the potential to elevate LLM performance in complex optimization tasks, fostering the applicability of LLMs in industries such as transportation and logistics.

Details

NeurIPS Conference 2025 Conference Paper

Large Language Models as End-to-end Combinatorial Optimization Solvers

Xia Jiang
Yaoxin Wu
Minshuo Li
Zhiguang Cao
Yingqian Zhang

Combinatorial optimization (CO) problems, central to decision-making scenarios like logistics and manufacturing, are traditionally solved using problem-specific algorithms requiring significant domain expertise. While large language models (LLMs) have shown promise in automating CO problem solving, existing approaches rely on intermediate steps such as code generation or solver invocation, limiting their generality and accessibility. This paper introduces a novel framework that empowers LLMs to serve as end-to-end CO solvers by directly mapping natural language problem descriptions to solutions. We propose a two-stage training strategy: supervised fine-tuning (SFT) imparts LLMs with solution construction patterns from domain-specific solvers, while a feasibility-and-optimality-aware reinforcement learning (FOARL) process explicitly mitigates constraint violations and refines solution quality. Evaluation across seven NP-hard CO problems shows that our method achieves a high feasibility rate and reduces the average optimality gap to 1. 03–8. 20% by tuning a 7B-parameter LLM, surpassing both general-purpose LLMs (e. g. , GPT-4o), reasoning models (e. g. , DeepSeek-R1), and domain-specific heuristics. Our method establishes a unified language-based pipeline for CO without extensive code execution or manual architectural adjustments for different problems, offering a general and language-driven alternative to traditional solver design while maintaining relative feasibility guarantees.

PDF Details

AIIM Journal 2017 Journal Article

An algorithm for direct causal learning of influences on patient outcomes

Chandramouli Rathnam
Sanghoon Lee
Xia Jiang

Objective This study aims at developing and introducing a new algorithm, called direct causal learner (DCL), for learning the direct causal influences of a single target. We applied it to both simulated and real clinical and genome wide association study (GWAS) datasets and compared its performance to classic causal learning algorithms. Method The DCL algorithm learns the causes of a single target from passive data using Bayesian-scoring, instead of using independence checks, and a novel deletion algorithm. We generate 14, 400 simulated datasets and measure the number of datasets for which DCL correctly and partially predicts the direct causes. We then compare its performance with the constraint-based path consistency (PC) and conservative PC (CPC) algorithms, the Bayesian-score based fast greedy search (FGS) algorithm, and the partial ancestral graphs algorithm fast causal inference (FCI). In addition, we extend our comparison of all five algorithms to both a real GWAS dataset and real breast cancer datasets over various time-points in order to observe how effective they are at predicting the causal influences of Alzheimer’s disease and breast cancer survival. Results DCL consistently outperforms FGS, PC, CPC, and FCI in discovering the parents of the target for the datasets simulated using a simple network. Overall, DCL predicts significantly more datasets correctly (McNemar’s test significance: p<<0. 0001) than any of the other algorithms for these network types. For example, when assessing overall performance (simple and complex network results combined), DCL correctly predicts approximately 1400 more datasets than the top FGS method, 1600 more datasets than the top CPC method, 4500 more datasets than the top PC method, and 5600 more datasets than the top FCI method. Although FGS did correctly predict more datasets than DCL for the complex networks, and DCL correctly predicted only a few more datasets than CPC for these networks, there is no significant difference in performance between these three algorithms for this network type. However, when we use a more continuous measure of accuracy, we find that all the DCL methods are able to better partially predict more direct causes than FGS and CPC for the complex networks. In addition, DCL consistently had faster runtimes than the other algorithms. In the application to the real datasets, DCL identified rs6784615, located on the NISCH gene, and rs10824310, located on the PRKG1 gene, as direct causes of late onset Alzheimer’s disease (LOAD) development. In addition, DCL identified ER category as a direct predictor of breast cancer mortality within 5 years, and HER2 status as a direct predictor of 10-year breast cancer mortality. These predictors have been identified in previous studies to have a direct causal relationship with their respective phenotypes, supporting the predictive power of DCL. When the other algorithms discovered predictors from the real datasets, these predictors were either also found by DCL or could not be supported by previous studies. Conclusion Our results show that DCL outperforms FGS, PC, CPC, and FCI in almost every case, demonstrating its potential to advance causal learning. Furthermore, our DCL algorithm effectively identifies direct causes in the LOAD and Metabric GWAS datasets, which indicates its potential for clinical applications.

Details DOI

AAAI Conference 2006 Conference Paper

A Bayesian Network for Outbreak Detection and Prediction

Xia Jiang

Health care officials are increasingly concerned with knowing early whether an outbreak of a particular disease is unfolding. We often have daily counts of some variable that are indicative of the number of individuals in a given community becoming sick each day with a particular disease. By monitoring these daily counts we can possibly detect an outbreak in an early stage. A number of classical time-series methods have been applied to outbreak detection based on monitoring daily counts of some variables. These classical methods only give us an alert as to whether there may be an outbreak. They do not predict properties of the outbreak such as its size, duration, and how far we are into the outbreak. Knowing the probable values of these variables can help guide us to a cost-effective decision that maximizes expected utility. Bayesian networks have become one of the most prominent architectures for reasoning under uncertainty in artificial intelligence. We present an intelligent system, implemented using a Bayesian network, which not only detects an outbreak, but predicts its size and duration, and estimates how far we are into the outbreak. We show results of investigating the performance of the system using simulated outbreaks based on real outbreak data. These results indicate that the system shows promise of being able to predict properties of an outbreak.

PDF Details