Author name cluster

Shi Wang

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.

8 papers

2 author rows

AAAI Conference 2026 Conference Paper

PathMind: A Retrieve-Prioritize-Reason Framework for Knowledge Graph Reasoning with Large Language Models

Yu Liu
Xixun Lin
Yanmin Shang
Yangxi Li
Shi Wang
Yanan Cao

Knowledge graph reasoning (KGR) is the task of inferring new knowledge by performing logical deductions on knowledge graphs. Recently, large language models (LLMs) have demonstrated remarkable performance in complex reasoning tasks. Despite promising success, current LLM-based KGR methods still face two critical limitations. First, existing methods often extract reasoning paths indiscriminately, without assessing their different importance, which may introduce irrelevant noise that misleads LLMs. Second, while some methods leverage LLMs to dynamically explore potential reasoning paths, they require high retrieval demands and frequent LLM calls. To address these limitations, we propose PathMind, a novel framework designed to enhance faithful and interpretable reasoning by selectively guiding LLMs with important reasoning paths. Specifically, PathMind follows a "Retrieve-Prioritize-Reason" paradigm. First, it retrieves a query subgraph from KG through the retrieval module. Next, it introduces a path prioritization mechanism that identifies important reasoning paths using a semantic-aware path priority function, which simultaneously considers the accumulative cost and the estimated future cost for reaching the target. Finally, PathMind generates accurate and logically consistent responses via a dual-phase training strategy, including task-specific instruction tuning and path-wise preference alignment. Extensive experiments on benchmark datasets demonstrate that PathMind consistently outperforms competitive baselines, particularly on complex reasoning tasks with fewer input tokens, by identifying essential reasoning paths.

PDF Details DOI

ICML Conference 2025 Conference Paper

ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via α-β-Divergence

Guanghui Wang 0001
Zhiyong Yang 0001
Zitai Wang
Shi Wang
Qianqian Xu 0001
Qingming Huang

Knowledge Distillation (KD) transfers knowledge from a large teacher model to a smaller student model by minimizing the divergence between their output distributions, typically using forward Kullback-Leibler divergence (FKLD) or reverse KLD (RKLD). It has become an effective training paradigm due to the broader supervision information provided by the teacher distribution compared to one-hot labels. We identify that the core challenge in KD lies in balancing two mode-concentration effects: the Hardness-Concentration effect, which refers to focusing on modes with large errors, and the Confidence-Concentration effect, which refers to focusing on modes with high student confidence. Through an analysis of how probabilities are reassigned during gradient updates, we observe that these two effects are entangled in FKLD and RKLD, but in extreme forms. Specifically, both are too weak in FKLD, causing the student to fail to concentrate on the target class. In contrast, both are too strong in RKLD, causing the student to overly emphasize the target class while ignoring the broader distributional information from the teacher. To address this imbalance, we propose ABKD, a generic framework with $\alpha$-$\beta$-divergence. Our theoretical results show that ABKD offers a smooth interpolation between FKLD and RKLD, achieving a better trade-off between these effects. Extensive experiments on 17 language/vision datasets with 12 teacher-student settings confirm its efficacy.

Details

NeurIPS Conference 2025 Conference Paper

DNA-DetectLLM: Unveiling AI-Generated Text via a DNA-Inspired Mutation-Repair Paradigm

Xiaowei Zhu
Yubing Ren
Fang Fang
Qingfeng Tan
Shi Wang
Yanan Cao

The rapid advancement of large language models (LLMs) has blurred the line between AI-generated and human-written text. This progress brings societal risks such as misinformation, authorship ambiguity, and intellectual property concerns, highlighting the urgent need for reliable AI-generated text detection methods. However, recent advances in generative language modeling have resulted in significant overlap between the feature distributions of human-written and AI-generated text, blurring classification boundaries and making accurate detection increasingly challenging. To address the above challenges, we propose a DNA-inspired perspective, leveraging a repair-based process to directly and interpretably capture the intrinsic differences between human-written and AI-generated text. Building on this perspective, we introduce DNA-DetectLLM, a zero-shot detection method for distinguishing AI-generated and human-written text. The method constructs an ideal AI-generated sequence for each input, iteratively repairs non-optimal tokens, and quantifies the cumulative repair effort as an interpretable detection signal. Empirical evaluations demonstrate that our method achieves state-of-the-art detection performance and exhibits strong robustness against various adversarial attacks and input lengths. Specifically, DNA-DetectLLM achieves relative improvements of 5. 55\% in AUROC and 2. 08\% in F1 score across multiple public benchmark datasets. Code and data are available at https: //github. com/Xiaoweizhu57/DNA-DetectLLM.

PDF Details

ICML Conference 2025 Conference Paper

MixBridge: Heterogeneous Image-to-Image Backdoor Attack through Mixture of Schrödinger Bridges

Shixi Qin
Zhiyong Yang 0001
Shilong Bao
Shi Wang
Qianqian Xu 0001
Qingming Huang

This paper focuses on implanting multiple heterogeneous backdoor triggers in bridge-based diffusion models designed for complex and arbitrary input distributions. Existing backdoor formulations mainly address single-attack scenarios and are limited to Gaussian noise input models. To fill this gap, we propose MixBridge, a novel diffusion Schrödinger bridge (DSB) framework to cater to arbitrary input distributions (taking I2I tasks as special cases). Beyond this trait, we demonstrate that backdoor triggers can be injected into MixBridge by directly training with poisoned image pairs. This eliminates the need for the cumbersome modifications to stochastic differential equations required in previous studies, providing a flexible tool to study backdoor behavior for bridge models. However, a key question arises: can a single DSB model train multiple backdoor triggers? Unfortunately, our theory shows that when attempting this, the model ends up following the geometric mean of benign and backdoored distributions, leading to performance conflict across backdoor tasks. To overcome this, we propose a Divide-and-Merge strategy to mix different bridges, where models are independently pre-trained for each specific objective (Divide) and then integrated into a unified model (Merge). In addition, a Weight Reallocation Scheme (WRS) is also designed to enhance the stealthiness of MixBridge. Empirical studies across diverse generation tasks speak to the efficacy of MixBridge. The code is available at: https: //github. com/qsx830/MixBridge.

Details

NeurIPS Conference 2025 Conference Paper

SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines

Xeron Du
Yifan Yao
Kaijing Ma
Bingli Wang
Tianyu Zheng
Minghao Liu
Yiming Liang
Xiaolong Jin

Large language models (LLMs) have demonstrated remarkable proficiency in mainstream academic disciplines such as mathematics, physics, and computer science. However, human knowledge encompasses over 200 specialized disciplines, far exceeding the scope of existing benchmarks. The capabilities of LLMs in many of these specialized fields-particularly in light industry, agriculture, and service-oriented disciplines-remain inadequately evaluated. To address this gap, we present SuperGPQA, a comprehensive benchmark that evaluates graduate-level knowledge and reasoning capabilities across 285 disciplines. Our benchmark employs a novel Human-LLM collaborative filtering mechanism to eliminate trivial or ambiguous questions through iterative refinement based on both LLM responses and expert feedback. Our experimental results reveal significant room for improvement in the performance of current state-of-the-art LLMs across diverse knowledge domains (e. g. , the reasoning-focused model Gemini-2. 5-Pro achieved the highest accuracy of 63. 56% on SuperGPQA), highlighting the considerable gap between current model capabilities and artificial general intelligence. Additionally, we present comprehensive insights from our management of a large-scale annotation process, involving over 80 expert annotators and an interactive Human-LLM collaborative system, offering valuable methodological guidance for future research initiatives of comparable scope.

PDF Details

EAAI Journal 2023 Journal Article

A sketch semantic segmentation method based on point-segment level interaction

Shihui Zhang
Lei Wang
Xueqiang Han
Shi Wang

Sketch semantic segmentation is a basic computer vision task, which poses great challenges due to the abstraction of sketches and different drawing styles. In this paper, we propose a sketch semantic segmentation method based on point-segment level interaction. Specifically, an enhanced local feature aggregation (ELFA) module is developed based on two kinds of distance information between the neighboring points/segments (NPs/NSs) and the corresponding center points/segments (CPs/CSs). The ELFA module not only extracts local features adequately, but also takes into account the different effects of the NPs/NSs on the corresponding CPs/CSs. Based on the ELFA module, a point-level branch and a segment-level branch are established to encode the semantics of sketches from a point level and a segment level respectively, which makes the features extracted from the point-level branch complementary to those extracted from the segment-level branch. Further, a point-segment level interaction (PSLI) module is designed to interchange the information of the two levels and to reduce the losing of some important semantic details caused by feature selection of multiple stages. The PSLI module can be placed in several stages, which is beneficial to retain and utilize the useful details. Finally, point-level features and segment-level features are fused to obtain the semantic segmentation result. Extensive experiments on SPG and SketchSeg-150K show that the proposed method achieves state-of-the-art performance.

Details DOI

NeurIPS Conference 2023 Conference Paper

MARBLE: Music Audio Representation Benchmark for Universal Evaluation

Ruibin Yuan
Yinghao Ma
Yizhi Li
Ge Zhang
Xingran Chen
Hanzhi Yin
zhuo le
Yiqi Liu

In the era of extensive intersection between art and Artificial Intelligence (AI), such as image generation and fiction co-creation, AI for music remains relatively nascent, particularly in music understanding. This is evident in the limited work on deep music representations, the scarcity of large-scale datasets, and the absence of a universal and community-driven benchmark. To address this issue, we introduce the Music Audio Representation Benchmark for universaL Evaluation, termed MARBLE. It aims to provide a benchmark for various Music Information Retrieval (MIR) tasks by defining a comprehensive taxonomy with four hierarchy levels, including acoustic, performance, score, and high-level description. We then establish a unified protocol based on 18 tasks on 12 public-available datasets, providing a fair and standard assessment of representations of all open-sourced pre-trained models developed on music recordings as baselines. Besides, MARBLE offers an easy-to-use, extendable, and reproducible suite for the community, with a clear statement on copyright issues on datasets. Results suggest recently proposed large-scale pre-trained musical language models perform the best in most tasks, with room for further improvement. The leaderboard and toolkit repository are published to promote future music AI research.

PDF Details

AAAI Conference 2021 Conference Paper

Flexible Non-Autoregressive Extractive Summarization with Threshold: How to Extract a Non-Fixed Number of Summary Sentences

Ruipeng Jia
Yanan Cao
Haichao Shi
Fang Fang
Pengfei Yin
Shi Wang

Sentence-level extractive summarization is a fundamental yet challenging task, and recent powerful approaches prefer to pick sentences sorted by the predicted probabilities until the length limit is reached, a. k. a. “Top-K Strategy”. This length limit is fixed based on the validation set, resulting in the lack of flexibility. In this work, we propose a more flexible and accurate non-autoregressive method for single document extractive summarization, extracting a non-fixed number of summary sentences without the sorting step. We call our approach ThresSum as it picks sentences simultaneously and individually from the source document when the predicted probabilities exceed a threshold. During training, the model enhances sentence representation through iterative refinement and the intermediate latent variables receive some weak supervision with soft labels, which are generated progressively by adjusting the temperature with a knowledge distillation algorithm. Specifically, the temperature is initialized with high value and drops along with the iteration until a temperature of 1. Experimental results on CNN/DM and NYT datasets have demonstrated the effectiveness of ThresSum, which significantly outperforms BERTSUMEXT with a substantial improvement of 0. 74 ROUGE-1 score on CNN/DM.

PDF Details