Source author record

Linlin Wang

Linlin Wang appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record

Artificial Intelligence Computation and Language Genomics math.CO math.NT math.PR nlin.SI

Catalog footprint

What is connected

6works

7topics

4close collaborators

Actions

Connect this record

Open graph Browse works

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

preprint2026arXiv

Pseudocode-Guided Structured Reasoning for Automating Reliable Inference in Vision-Language Models

Vision-Language Models (VLMs) are becoming the cornerstone of high-level reasoning for robotic automation, enabling robots to parse natural language commands and perceive their environments. However, their susceptibility to hallucinations introduces critical failures in decision-making, posing significant safety and reliability risks in physical deployments. This challenge is exacerbated by the open-ended nature of real-world tasks, where questions vary vastly in difficulty and modality, demanding robust and adaptable reasoning strategies. To tackle this, we propose the Pseudocode-guided Structured Reasoning framework (PStar), which adaptively selects structured pseudocode reasoning paths to help VLMs perform flexible and step-by-step reasoning. We first design a set of abstract reasoning functions and formulate a structured pseudocode library to represent modular reasoning strategies. Crucially, we design a Difficulty Feature Vector (DFV) that allows the model to assess question complexity and adaptively choose appropriate reasoning strategies-enhancing robustness and interpretability. Extensive experiments demonstrate that PStar significantly reduces hallucination rates, achieving state-of-the-art scores of 87.1% on POPE and 68.0% on MMStar, outperforming even GPT-4V. By providing a validated mechanism to reduce visual-language errors, PStar offers a critical step toward deploying more trustworthy and deterministic VLMs for real-world automated systems, where such errors can lead to catastrophic outcomes.

preprint2020arXiv

ECNU-SenseMaker at SemEval-2020 Task 4: Leveraging Heterogeneous Knowledge Resources for Commonsense Validation and Explanation

This paper describes our system for SemEval-2020 Task 4: Commonsense Validation and Explanation (Wang et al., 2020). We propose a novel Knowledge-enhanced Graph Attention Network (KEGAT) architecture for this task, leveraging heterogeneous knowledge from both the structured knowledge base (i.e. ConceptNet) and unstructured text to better improve the ability of a machine in commonsense understanding. This model has a powerful commonsense inference capability via utilizing suitable commonsense incorporation methods and upgraded data augmentation techniques. Besides, an internal sharing mechanism is cooperated to prohibit our model from insufficient and excessive reasoning for commonsense. As a result, this model performs quite well in both validation and explanation. For instance, it achieves state-of-the-art accuracy in the subtask called Commonsense Explanation (Multi-Choice). We officially name the system as ECNU-SenseMaker. Code is publicly available at https://github.com/ECNU-ICA/ECNU-SenseMaker.

preprint2015arXiv

Dressing by regularization to the Gerdjikov-Ivanov equation and the higher-order soliton

Higher-order solitons, as well as simple $N$-soliton solutions, of the Gerdjikov-Ivanov equation are derived by the dressing method based on the technique of regularization. By the dressing transformation for the eigenfunction associated with a seed solution, the regularity conditions of the dressed eigenfunctions are found to establish the relationship between the potential and the scattering data.

preprint2015arXiv

Pathway-based feature selection algorithms identify genes discriminating patients with multiple sclerosis apart from controls

Introduction The focus of analyzing data from microarray experiments and extracting biological insight from such data has experienced a shift from identification of individual genes in association with a phenotype to that of biological pathways or gene sets. Meanwhile, feature selection algorithm becomes imperative to cope with the high dimensional nature of many modeling tasks in bioinformatics. Many feature selection algorithms use information contained within a gene set as a biological priori, and select relevant features by incorporating such information. Thus, an integration of gene set analysis with feature selection is highly desired. Significance analysis of microarray to gene-set reduction analysis (SAM-GSR) algorithm is a novel direction of gene set analysis, aiming at further reduction of gene set into a core subset. Here, we explore the feature selection trait possessed by SAM-GSR and then modify SAM-GSR specifically to better fulfill this role. Results and Conclusions Training on a multiple sclerosis (MS) microarray data using both SAM-GSR and our modification of SAM-GSR, excellent discriminative performance on an independent test set was achieved. To conclude, absorbing biological information from a gene set may be helpful for classification and feature selection. Discussion Given the fact the complete pathway information is far from completeness, a statistical method capable of constructing biologically meaningful gene networks is in demand. The basic requirement is that interplay among genes must be taken into account.

preprint2013arXiv

Harnack inequalities for SDEs driven by cylindrical $α$-stable processes

By using the coupling argument, we establish the Harnack and log-Harnack inequalites for stochastic differential equations with non-Lipschitz drifts and driven by additive anisotropic subordinated Brownian motions (in particular, cylindrical $α$-stable processes). Moreover, the gradient estimate is also derived when the drift is Lipschitz continuous.

preprint2012arXiv

On the maximal multiplicity of long zero-sum free sequences over $C_p\oplus C_p$

In this paper, we point out that the method used in [Acta Arith. 128(2007) 245-279] can be modified slightly to obtain the following result. Let $\varepsilon \in (0,\frac 14)$ and $c>0$, and let $p$ be a sufficiently large prime depending on $\varepsilon$ and $c$. Then every zero-sumfree sequence $S$ over $C_p\oplus C_p$ of length $|S|\geq 2p-c\sqrt{p}$ contains some element at least $\lfloor p^{\frac14-\varepsilon}\rfloor$ times.