arXivSub Start free trial

IJCAI 2025 Papers with Code — Page 3

International Joint Conference on Artificial Intelligence · 343 papers

Let’s Group: A Plug-and-Play SubGraph Learning Method for Memory-Efficient Spatio-Temporal Graph Modeling

Wenchao Weng (Zhejiang University of Technology), Xiangjie Kong (Zhejiang University of Technology)

CodeComputational EfficiencyRepresentation LearningGraph Neural NetworkTime Series

🎯 What it does: Perform subgraph learning on large-scale spatiotemporal graph models, providing pluggable subgraph partitioning and aggregation modules to significantly reduce GPU memory consumption.

Leveraging MLLM Embeddings and Attribute Smoothing for Compositional Zero-Shot Learning

Xudong Yan (Beijing Jiaotong University), Haojun Fei (Qifu Technology)

CodeClassificationTransformerLarge Language ModelVision Language ModelMultimodality

🎯 What it does: This paper proposes the TRIDENT framework, which enhances combination zero-shot learning (CZSL) performance using multimodal LLM embeddings, attribute smoothing, and visual feature decoupling.

Leveraging Personalized PageRank and Higher-Order Topological Structures for Heterophily Mitigation in Graph Neural Networks

Yumeng Wang (Tianjin University), Minglai Shao (Tianjin University)

CodeClassificationGraph Neural NetworkGraph

🎯 What it does: In this paper, the authors propose HPGNN, a graph neural network that integrates high-order personalized PageRank (HiPPR) with Simplicial Complex (SC) structure, for solving node classification problems in heterogeneous graphs;

LiBOG: Lifelong Learning for Black-Box Optimizer Generation

Jiyuan Pei (Victoria University of Wellington), Mengjie Zhang (Victoria University of Wellington)

CodeOptimizationMeta LearningRecurrent Neural NetworkReinforcement LearningBenchmark

🎯 What it does: Developed LiBOG, a framework applying lifelong learning in Meta-Black-Box Optimization (MetaBBO), which can continuously learn and generate high-performance black-box optimizers across sequentially emerging distributions of optimization problems.

Linear Trading Position with Sparse Spectrum

Zhao-Rong Lai (Jinan University), Haisheng Yang (Sun Yat-Sen University)

CodeOptimizationTabularFinance Related

🎯 What it does: Proposes the Linear Trading Position Sparse Spectrum (LTPSS) method, which constructs trading strategies using all principal components with adjustable spectral energy, and solves the problem via the Krasnosel'skiǐ-Mann fixed-point algorithm.

ListenNet: A Lightweight Spatio-Temporal Enhancement Nested Network for Auditory Attention Detection

Cunhang Fan (Anhui University), Zhao Lv (Anhui University)

CodeClassificationComputational EfficiencyConvolutional Neural NetworkTime SeriesBiomedical Data

🎯 What it does: Developed a lightweight spatiotemporal enhanced nested network called ListenNet for auditory attention detection using electroencephalogram (EEG) signals in multi-speaker environments.

LLM-enhanced Score Function Evolution for Causal Structure Learning

Zidong Wang (City University of Hong Kong), Xiaoguang Gao (Northwestern Polytechnical University)

CodeOptimizationTransformerLarge Language ModelPrompt EngineeringGraphTabular

🎯 What it does: This study proposes the L-SFE framework, which leverages large language models and evolutionary algorithms to automatically explore and generate improved score functions, thereby enhancing the performance of causal structure learning.

LLM4VKG: Leveraging Large Language Models for Virtual Knowledge Graph Construction

Guohui Xiao (Southeast University), Davide Lanti (Free University of Bozen-Bolzano)

CodeTransformerLarge Language ModelTextGraphRetrieval-Augmented Generation

🎯 What it does: This paper proposes the LLM4VKG framework, which utilizes large language models (LLMs) to automatically complete the construction process of virtual knowledge graphs (VKGs), including ontology completion and mapping generation.

LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data

Chuanxing Geng (Nanjing University of Aeronautics and Astronautics), Pong C. Yuen (Hong Kong Baptist University)

CodeAnomaly DetectionConvolutional Neural NetworkSupervised Fine-TuningImage

🎯 What it does: Leverages the uniform annotation of unlabeled wild data into K+1 classes, and observes loss differences in the K+1 classification task to achieve automatic filtering and detection of OOD samples.

Logic Distillation: Learning from Code Function by Function for Decision-making Tasks

Dong Chen (Zhengzhou University), Mingliang Xu (Zhengzhou University)

CodeKnowledge DistillationTransformerLarge Language ModelSupervised Fine-TuningTextRetrieval-Augmented Generation

🎯 What it does: This paper proposes a Logic Distillation (Logic Distillation, LD) framework that decomposes the decision-making logic of large language models (L-LLM) into callable functions. It fine-tunes small language models (S-LLM) using a function library, enabling them to invoke relevant functions in stages to complete sequential decision-making tasks.

LogiCase: Effective Test Case Generation from Logical Description in Competitive Programming

Sicheol Sung (Yonsei University), Sang-Ki Ko (University of Seoul)

CodeGenerationAI Code AssistantTransformerLarge Language ModelSupervised Fine-TuningText

🎯 What it does: Proposes Context-Free Grammars with Counters (CCFG) method for automatically generating high-quality test cases that comply with semantics and syntax from the natural language descriptions of competition problems.

Long-Term Individual Causal Effect Estimation via Identifiable Latent Representation Learning

Ruichu Cai (Guangdong University of Technology), Jiecheng Guo (DiDi China Ride Hailing Business Group)

CodeRepresentation LearningAuto EncoderTabular

🎯 What it does: Proposes a framework for estimating long-term individual causal effects by leveraging multi-source data to identify potential confounding variables, combining short-term potential outcome learning with an identifiable variational autoencoder to achieve long-term effect prediction.

M3ANet: Multi-scale and Multi-Modal Alignment Network for Brain-Assisted Target Speaker Extraction

Cunhang Fan (Anhui University), Zhao Lv (Anhui University)

CodeRecognitionConvolutional Neural NetworkRecurrent Neural NetworkContrastive LearningMultimodalityBiomedical DataAudio

🎯 What it does: This paper proposes a multi-scale multi-modal alignment network, M3ANet, for brain-assisted target speaker extraction, addressing the time deviation between EEG and speech and the insufficiency in speech feature extraction.

M4Bench: A Benchmark of Multi-domain Multi-granularity Multi-image Understanding for Multi-modal Large Language Models

Xiaojun Ye (Zhejiang University), Sheng Zhou (Zhejiang University)

CodeTransformerVision Language ModelImageVideoMultimodalityBenchmark

🎯 What it does: Proposed and implemented the M4 Bench benchmark to evaluate the performance of multimodal large language models in multi-domain, multi-granularity multi-image comparison tasks.

MAGE: Multimodal Alignment and Generation Enhancement via Bridging Visual and Semantic Spaces

Shaojun E (Global Tone Communication Technology Co Ltd), Ziyan Chen (Global Tone Communication Technology Co Ltd)

CodeGenerationTransformerVision Language ModelContrastive LearningImageTextMultimodality

🎯 What it does: Propose the MAGE model, which achieves dual alignment of visual and textual features in both dimensions and semantics through the Intelligent Alignment Network (IAN), and enhances cross-modal consistency via dual loss functions (image generation loss + image-text distance minimization loss); simultaneously construct the HMDSet multimodal tool calling dataset to expand the model's 'Any-to-Any' output capability.

Mamba-Based Graph Convolutional Networks: Tackling Over-smoothing with Selective State Space

Xin He (Jilin University), Xin Wang (Jilin University)

CodeGraph Neural NetworkGraphBenchmark

🎯 What it does: Introduce a selective state space mechanism based on Mamba into graph neural networks, and propose the MbaGCN framework.

MaskDGNN: Self-Supervised Dynamic Graph Neural Networks with Activeness-aware Temporal Masking

Yiming He (Ocean University of China), Yanwei Yu (Ocean University of China)

CodeComputational EfficiencyRepresentation LearningGraph Neural NetworkGraph

🎯 What it does: Proposed a self-supervised dynamic graph neural network called MaskDGNN, which performs edge masking along the timeline by evaluating node activity levels, and enhances the representation capability of dynamic graphs through a frequency domain enhancement module that adaptively models distribution drift.

MCF-Spouse: A Multi-Label Causal Feature Selection Method with Optimal Spouses Discovery

Lin Ma (Jilin University), Juncheng Hu (Jilin University)

CodeOptimizationData-Centric LearningTabularBiomedical Data

🎯 What it does: Propose a multi-label causal feature selection method called MCF-Spouse, which can identify optimal spouse variables on target labels to improve the quality of feature subsets.

Metapath and Hypergraph Structure-based Multi-Channel Graph Contrastive Learning for Student Performance Prediction

Lingyun Song (Northwestern Polytechnical University), Xuequn Shang (Northwestern Polytechnical University)

CodeRecommendation SystemGraph Neural NetworkContrastive LearningGraph

🎯 What it does: Proposed a student performance prediction framework named MCGCL based on multi-channel graph contrastive learning, enhancing student and question feature learning by constructing high-order hypergraphs and multiple meta-paths.

METOR: A Unified Framework for Mutual Enhancement of Objects and Relationships in Open-vocabulary Video Visual Relationship Detection

Yongqi Wang (Beijing Institute of Technology), Shuo Yang (Shenzhen MSU-BIT University)

CodeObject DetectionTransformerVision Language ModelContrastive LearningVideo

🎯 What it does: Proposed the METOR framework, which adopts a query-based unified model, combining CLIP-based context refinement encoding and iterative enhancement to achieve mutual improvement between objects and relationships in video visual relationship detection.

MHANet: Multi-scale Hybrid Attention Network for Auditory Attention Detection

Lu Li (Anhui University), Zhao Lv (Anhui University)

CodeClassificationConvolutional Neural NetworkTransformerTime SeriesBiomedical Data

🎯 What it does: Proposed a multi-scale hybrid attention network (MHANet) for detecting auditory attention from electroencephalogram (EEG) signals.

MiniMal: Hard-Label Adversarial Attack Against Static Malware Detection with Minimal Perturbation

Chengyi Li (National University of Defense Technology), Yuhang Mao

CodeAdversarial Attack

🎯 What it does: This paper proposes MiniMal, which implements black-box hard-label adversarial attacks on Windows PE files, significantly reducing the perturbation rate while maintaining malicious functionality.

Minimizing Polarization and Disagreement in the Friedkin–Johnsen Model with Unknown Innate Opinions

Federico Cinus (Sapienza University), Francesco Bonchi (CENTAI Institute)

CodeOptimizationGraph Neural NetworkGraph

🎯 What it does: The study addresses the opinion optimization problem under the Friedkin-Johnsen model, where intrinsic opinions are unknown and only limited nodes can be queried. It proposes a three-step framework encompassing node selection, opinion reconstruction, and objective function optimization.

Misclassification-driven Fingerprinting for DNNs Using Frequency-aware GANs

Weixing Liu (Shenzhen University), Shenghua Zhong (Shenzhen University)

CodeSafty and PrivacyGenerative Adversarial NetworkImage

🎯 What it does: Propose a fingerprint generation framework based on frequency-domain aware GAN, utilizing generated misclassified samples as fingerprints for model ownership verification.

MMET: A Multi-Input and Multi-Scale Transformer for Efficient PDEs Solving

Yichen Luo (KTH Royal Institute of Technology), Zhibo Pang (KTH Royal Institute of Technology)

CodeTransformerBenchmarkPhysics Related

🎯 What it does: Proposed a multi-input multi-scale efficient Transformer (MMET) for real-time solving of large-scale, complex multi-physics PDEs.

MMNet: Missing-Aware and Memory-Enhanced Network for Multivariate Time Series Imputation

Xiaoye Miao (Zhejiang University), Xiaohua Pan (Zhejiang University)

CodeRestorationConvolutional Neural NetworkTransformerTime SeriesBiomedical Data

🎯 What it does: This paper proposes a multi-scale missing-aware memory-enhanced network called MMNet for imputing missing values in multivariate time series;

Modality-Guided Dynamic Graph Fusion and Temporal Diffusion for Self-Supervised RGB-T Tracking

Shenglan Li (China University of Mining and Technology), Jiaqi Zhao (China University of Mining and Technology)

CodeObject TrackingGraph Neural NetworkTransformerDiffusion modelVideoMultimodality

🎯 What it does: Propose GDSTrack, a self-supervised RGB-T tracker that combines dynamic graph fusion and temporal graph diffusion to reduce pseudo-label noise and enhance tracking performance.

Most General Explanations of Tree Ensembles

Yacine Izza (National University of Singapore), Peter J. Stuckey (Monash University)

CodeExplainability and InterpretabilityTabularBenchmark

🎯 What it does: This paper studies how to compute the maximum widening inductive explanation (Max-iAXp) in tree ensemble models, which is the most general explanation that covers as much of the input space as possible while still maintaining the correctness of the model's predictions.

MS-DPPs: Multi-Source Determinantal Point Processes for Contextual Diversity Refinement of Composite Attributes in Text to Image Retrieval

Naoya Sogi (NEC Corporation), Takayuki Okatani (Tohoku University)

CodeRetrievalVision Language ModelImageText

🎯 What it does: Propose a post-processing method called MS-DPP in text-to-image retrieval, which utilizes multi-source Determinantal Point Process (DPP) to refine the diversity of multiple attributes in retrieval results, thereby controlling the diversity of attributes such as image appearance, capture time, and location while maintaining relevance.

MSCI: Addressing CLIP's Inherent Limitations for Compositional Zero-Shot Learning

Yue Wang (Nanjing University of Aeronautics and Astronautics), Yicong Li (Nanjing University of Aeronautics and Astronautics)

CodeTransformerSupervised Fine-TuningPrompt EngineeringVision Language ModelContrastive LearningImageTextMultimodality

🎯 What it does: Designed the MSCI model by adaptively aggregating low-level details and high-level global features, and gradually injecting these information into text prompts through multi-stage cross-modal interactions, thereby enhancing CLIP's performance in synthetic zero-shot recognition.

MSVIT: Improving Spiking Vision Transformer Using Multi-scale Attention Fusion

Wei Hua (China Nanhu Academy of Electronics and Information Technology), Yangyang Shu (University of New South Wales)

CodeClassificationRecognitionSpiking Neural NetworkTransformerImage

🎯 What it does: Propose a multi-scale spiking attention fusion Spike-Transformer (MSVIT), enhancing the representation capability of SNN in visual tasks through multi-scale feature fusion.

MTPNet: Multi-Grained Target Perception for Unified Activity Cliff Prediction

Zishan Shu (Peking University), Jie Chen (Peking University)

CodeDrug DiscoveryGraph Neural NetworkTransformerLarge Language ModelBiomedical Data

🎯 What it does: Proposed MTPNet, which utilizes macro and micro protein semantic-guided multi-granularity target-aware modules to achieve unified representation of molecular and receptor interaction information, thereby enabling regression and classification prediction of activity cliffs.

Multi-Modal Point Cloud Completion with Interleaved Attention Enhanced Transformer

Chenghao Fang (Shanxi University), Feilong Cao

CodeRestorationAutonomous DrivingTransformerMultimodalityPoint Cloud

🎯 What it does: Proposed a multimodal point cloud completion framework IAET, which jointly utilizes complete images and partial point clouds for 3D reconstruction.

Multi-Objective Neural Bandits with Random Scalarization

Ji Cheng (City University of Hong Kong), Qingfu Zhang (City University of Hong Kong)

CodeOptimizationReinforcement LearningImage

🎯 What it does: This paper proposes a neural network-based multi-objective multi-armed bandit (MONB) framework, utilizing stochastic normalization to address the multi-objective weight allocation problem;

Multi-Scale Temporal Neural Network for Stock Trend Prediction Enhanced by Temporal Hyepredge Learning

Lingyun Song (Northwestern Polytechnical University), Xuequn Shang (Northwestern Polytechnical University)

CodeConvolutional Neural NetworkTransformerGraphTime SeriesFinance Related

🎯 What it does: Propose the MSTNN framework based on multi-scale 3D convolution and temporal hypergraph attention to capture periodic fluctuations of individual stocks and higher-order associations at the industry level for predicting stock trends

Multi-Sourced Compositional Generalization in Visual Question Answering

Chuanhao Li (Beijing Institute Of Technology), Yunde Jia (Shenzhen Msu Bit University)

CodeRepresentation LearningTransformerSupervised Fine-TuningMultimodalityBenchmarkRetrieval-Augmented Generation

🎯 What it does: Investigate the performance of multi-source compositional generalization in visual question answering, and propose a retrieval-enhanced training framework to improve the model's unified representation capability for cross-modal primitives.

Multi-View Learning with Context-Guided Receptance for Image Denoising

Binghong Chen (Harbin Institute of Technology), Xiangqian Wu (Harbin Institute of Technology)

CodeRestorationRecurrent Neural NetworkImage

🎯 What it does: Proposed a context-guided receptive field weighted key-value network CRWKV for real-world image denoising.

MVP-CBM: Multi-layer Visual Preference-enhanced Concept Bottleneck Model for Explainable Medical Image Classification

Chunjiang Wang (University Of Science And Technology Of China), S. Kevin Zhou (University Of Science And Technology Of China)

CodeClassificationExplainability and InterpretabilityTransformerLarge Language ModelVision Language ModelContrastive LearningBiomedical DataComputed TomographyUltrasound

🎯 What it does: This paper proposes a multi-layer visual preference enhanced concept bottleneck model (MVP-CBM), achieving explainable and high-precision medical image classification by capturing visual layer preferences for medical concepts and sparsely fusing multi-layer concept activations.

NeSyA: Neurosymbolic Automata

Nikolaos Manginas, Luc De Raedt (KU Leuven)

CodeClassificationRecognitionConvolutional Neural NetworkRecurrent Neural NetworkTransformerImageVideo

🎯 What it does: Developed a neural symbolic automaton called NESYA for sequence classification and annotation, integrating neural network perception with symbolic automata and providing probabilistic semantics.

Neuromorphic Sequential Arena: A Benchmark for Neuromorphic Temporal Processing

Xinyi Chen (Hong Kong Polytechnic University), Jibin Wu (Hong Kong Polytechnic University)

CodeSpiking Neural NetworkTransformerTime SeriesSequentialBenchmark

🎯 What it does: Proposed the Neuromorphic Sequential Arena (NSA) as a multi-task, application-oriented neuromorphic temporal processing benchmark, and developed the Segregated Temporal Probe (STP) tool to verify the temporal dependency of tasks, followed by systematic evaluations of various synapse neuron models and network architectures on NSA.

Noise-Resistant Label Reconstruction Feature Selection for Partial Multi-Label Learning

Wanfu Gao (Jilin University), Kunpeng Liu (Portland State University)

CodeClassificationImageBenchmark

🎯 What it does: To address the challenges of noisy labels and sparse positive samples in partial multi-label learning, the authors propose a three-stage feature selection framework: ① Reconstruct the label set using a label mutual information matrix to remove noise and enhance label reliability; ② Apply an improved low-rank assumption and graph Laplacian regularization on the reconstructed labels to learn a weight matrix while preserving the high-dimensional structure; ③ Further refine the weight matrix by leveraging label mutual information reconstruction to emphasize important labels, thereby enhancing the identification of positive labels.

NS4S: Neighborhood Search for Scheduling Problems Via Large Language Models

Junjie Zhang (Huazhong University of Science and Technology), Yan Jin (Huazhong University of Science and Technology)

CodeOptimizationTransformerLarge Language ModelTabular

🎯 What it does: Proposed a neighborhood search framework NS4S based on large language models for solving JSP, FJSP, and FJSP-SDST.

NuMDS: An Efficient Local Search Algorithm for Minimum Dominating Set Problem

Rui Sun (Northeast Normal University), Jiejiang Chen (Hangzhou Normal University)

CodeOptimizationGraphBenchmark

🎯 What it does: Propose an efficient local search algorithm called NuMDS for solving the minimum dominating set (MDS) problem.

On the Discrimination and Consistency for Exemplar-Free Class Incremental Learning

Tianqi Wang (Hong Kong Polytechnic University), Zhi Chen (University of Southern Queensland)

CodeClassificationRepresentation LearningContrastive LearningImage

🎯 What it does: In sample-free class-incremental learning (EF-CIL), this paper emphasizes the importance of discriminativeness and consistency in the feature space through theoretical analysis, and proposes the DCNet framework, which achieves stable and discriminative feature spaces via orthogonal embedding and dynamic aggregation compensation.

On the Learning with Augmented Class via Forests

Fan Xu (Nanjing University), Wei Gao (Nanjing University)

CodeClassificationImageTabular

🎯 What it does: This paper proposes two methods, LACForest and Deep Neural LACForest, which proactively mine unseen classes (augmented classes) in decision trees/forests using the 'enhanced Gini impurity' criterion, and further improve classification performance through pseudo labels.

Online Planning in MDPs with Stochastic Durative Actions

Tal Berman, Erez Karpas (Technion)

CodeReinforcement Learning

🎯 What it does: Proposed an online planning algorithm called TP-MCTS that can handle continuous actions with random effects while meeting constraints such as deadlines and time windows, and supports concurrent execution.

Optical Flow Estimation for Tiny Objects: New Problem, Specialized Benchmark, and Bioinspired Scheme

Xueyao Ji, Yizheng Wang (Beijing Institute of Basic Medical Sciences)

CodeConvolutional Neural NetworkOptical FlowVideoBenchmark

🎯 What it does: Proposed a lightweight bio-inspired optical flow estimation method named OTHR for accurately capturing the motion of extremely small objects (<100 pixels) and constructed a specialized optical flow dataset FlyingTO along with refined evaluation metrics tailored for small objects.

Optimal Transport on Categorical Data for Conterfactuals Using Compositional Data and Dirichlet Transport

Agathe Fernandes Machado (Université du Québec à Montréal), Arthur Charpentier (Université du Québec à Montréal)

CodeData SynthesisExplainability and InterpretabilityTabular

🎯 What it does: Convert discrete categorical features into compositional (probability) vectors and perform optimal transport on the probability simplex to generate interpretable counterfactual predictions.

Optimizing Personalized Federated Learning Through Adaptive Layer-Wise Learning

Weihang Chen (Shaanxi Normal University), Zheng Wang (University of Leeds)

CodeOptimizationFederated LearningConvolutional Neural NetworkImageText

🎯 What it does: Proposed FLAYER, a method in federated learning that achieves personalized model training through hierarchical aggregation, hierarchical adaptive learning rates, and hierarchical sparse masks.

PALA: Class-imbalanced Graph Domain Adaptation via Prototype-anchored Learning and Alignment

Xin Ma (Sichuan University), Jiancheng Lv (Sichuan University)

CodeDomain AdaptationAdversarial AttackGraph Neural NetworkContrastive LearningGraph

🎯 What it does: Propose a prototype-anchored graph domain adaptation framework called PALA to address knowledge transfer bias caused by class imbalance in the source graph.

PAMol: Pocket-Aware Drug Design Method with Hypergraph Representation of Protein Pocket Structure and Feature Fusion

Xiaoli Lin (Wuhan University of Science and Technology), Xiaolong Zhang (Wuhan University of Science and Technology)

CodeDrug DiscoveryGraph Neural NetworkTransformerGenerative Adversarial NetworkGraphBiomedical Data

🎯 What it does: Propose a drug design framework called PAMol based on protein pocket hypergraph representation and multimodal feature fusion, which can generate molecules with high affinity and favorable pharmacological properties under target protein pocket conditions.

PanComplex: Leveraging Complex-Valued Neural Networks for Enhanced Pansharpening

Chunhui Luo (University of Science and Technology of China), Xueyang Fu (University of Science and Technology of China)

CodeRestorationSuper ResolutionConvolutional Neural NetworkImage

🎯 What it does: A dual-domain (spatial-frequency) framework called PanComplex based on complex convolution for fusing multispectral and panchromatic images, outputting high-resolution multispectral images.

Partial Label Clustering

Yutong Xie (Southeast University), Yuheng Jia (Southeast University)

CodeOptimizationRepresentation LearningImageTabular

🎯 What it does: Propose a PLC method that utilizes partial label information for clustering. First, construct a neighborhood weight matrix and perform label disambiguation, then generate must-link/cannot-link constraints and optimize them through dual propagation, ultimately obtaining clustering results in spectral clustering.

Partially Observable Reference Policy Programming

Edward Kim (Australian National University), Hanna Kurniawati (Australian National University)

CodeReinforcement LearningMesh

🎯 What it does: Proposed the PORPP algorithm, an online approximate POMDP solver capable of deeply sampling future history and incrementally updating policies.

Participatory Budgeting Project Strength via Candidate Control

Piotr Faliszewski (AGH University of Krakow), Krzysztof Sornat (AGH University of Krakow)

CodeOptimizationTabular

🎯 What it does: This paper studies the candidate control problem in participatory budget elections, where candidates can manipulate the outcome by deleting or adding projects, and provides theoretical analysis and experimental validation of its computational complexity.

PerfSeer: An Efficient and Accurate Deep Learning Models Performance Predictor

Xinlong Zhao (Shandong Normal University), Ke Liu (Shandong Normal University)

CodeComputational EfficiencyGraph Neural NetworkGraph

🎯 What it does: This paper proposes PerfSeer, a performance predictor capable of efficiently and accurately forecasting the execution time, memory usage, and SM utilization of deep learning models during both training and inference phases.

PeSANet: Physics-encoded Spectral Attention Network for Simulating PDE-Governed Complex Systems

Han Wan (Renmin University of China), Hao Sun (Renmin University of China)

CodeConvolutional Neural NetworkTime SeriesPhysics Related

🎯 What it does: Proposed a novel Physical Encoding Spectral Attention Network (PeSANet), achieving long-term prediction for two-dimensional complex systems governed by partial differential equations (PDEs) by combining hard-constrained local differential operator learning with frequency-domain spectral attention mechanisms.

Physics-Assisted and Topology-Informed Deep Learning for Weather Prediction

Jiaqi Zheng (Sun Yat-Sen University), Yerong Feng (Shenzhen Institute of Meteorological Innovation)

CodeGraph Neural NetworkTime SeriesPhysics Related

🎯 What it does: Developed a weather prediction model called PASSAT, which integrates physical equations with Earth's surface topology, enabling numerical solutions of transport and Navier-Stokes equations on a sphere, and employs spherical graph neural networks to estimate initial velocity fields and interactions between the atmosphere and the surface.

Picturized and Recited with Dialects: A Multimodal Chinese Representation Framework for Sentiment Analysis of Classical Chinese Poetry

Xiaocong Du (ShanghaiTech University), Haipeng Zhang (ShanghaiTech University)

CodeClassificationRepresentation LearningConvolutional Neural NetworkTransformerLarge Language ModelVision Language ModelContrastive LearningImageTextMultimodalityAudio

🎯 What it does: This paper proposes a tri-modal Chinese representation framework that uses audio, visual, and textual modalities together to perform emotion analysis on classical Chinese poetry;

PNAct: Crafting Backdoor Attacks in Safe Reinforcement Learning

Weiran Guo (Tongji University), Ling Wang (Tongji University)

CodeAdversarial AttackReinforcement LearningBenchmark

🎯 What it does: Proposed the PNAct framework, which achieves precise control over safety constraints in Safe Reinforcement Learning (Safe RL) through the design of positive and negative action samples and a loss function, enabling agents to execute dangerous actions under triggering conditions without affecting rewards.

POLO: An LLM-Powered Project-Level Code Performance Optimization Framework

Jiameng Bai (Zhejiang University), Gang Chen (Zhejiang University)

CodeOptimizationAI Code AssistantTransformerLarge Language ModelText

🎯 What it does: Propose the POLO framework, which identifies hotspots through dynamic analysis, constructs a program structure graph via static structural analysis, and achieves project-level performance optimization by iteratively rewriting code using dual-agent LLMs.

POMP: Pathology-omics Multimodal Pre-training Framework for Cancer Survival Prediction

Suixue Wang (Hainan University), Qingchen Zhang (Hainan University)

CodeRepresentation LearningTransformerContrastive LearningImageMultimodalityTabular

🎯 What it does: Proposed the POMP framework, which pre-trains and fuses pathological images with multi-omics data for cancer survival prediction.

Preference Elicitation for Multi-objective Combinatorial Optimization with Active Learning and Maximum Likelihood Estimation

Marianne Defresne (KU Leuven), Tias Guns (KU Leuven)

CodeOptimization

🎯 What it does: This paper proposes a constructive preference inference method based on active learning and maximum likelihood estimation for multi-objective combinatorial optimization problems.

Preference-based Deep Reinforcement Learning for Historical Route Estimation

Boshen Pan (Dalian University of Technology), Qiang Zhang (Dalian University of Technology)

CodeAutonomous DrivingOptimizationData-Centric LearningReinforcement Learning from Human FeedbackReinforcement LearningSequentialBenchmark

🎯 What it does: Studied vehicle route planning based on preference-based deep reinforcement learning, leveraging historical routes to learn driver preferences and generate routes more aligned with human preferences.

Preventing Latent Diffusion Model-Based Image Mimicry via Angle Shifting and Ensemble Learning

Minghao Li (Chinese Academy of Sciences), Lihua Jing (University of Chinese Academy of Sciences)

CodeAdversarial AttackDiffusion modelAuto EncoderImage

🎯 What it does: Perform untargeted adversarial attacks on LDMs by proposing an alternating iterative framework, angle offset (cosine similarity) attack, gradient integration, and fixed noise strategy to reduce VRAM usage while enhancing attack effectiveness.

Privacy Preserving Solution of DCOPs by Local Search

Shmuel Goldklang (Open University of Israel), Tamir Tassa (Open University of Israel)

CodeOptimizationSafty and PrivacyGraph

🎯 What it does: Proposed P-DSA, a privacy-preserving implementation for distributed constraint optimization problems based on local search.

Projection, Interaction and Fusion: A Progressive Difference Fusion Network for Salient Object Detection

Xiao Ke (Engineering Research Center Of Big Data Intelligence Ministry Of Education), Yuzhen Niu (Engineering Research Center Of Big Data Intelligence Ministry Of Education)

CodeObject DetectionComputational EfficiencyTransformerImage

🎯 What it does: Propose a novel salient object detection network PDFNet based on Transformer, aiming to address the bottleneck of scale, shape, and confusion between global-detail information.

Prototype-guided Knowledge Propagation with Adaptive Learning for Lifelong Person Re-identification

Zhijie Lu (Wuhan University), Mang Ye (Wuhan University)

CodeRetrievalMeta LearningConvolutional Neural NetworkContrastive LearningImage

🎯 What it does: Developed an example-free lifelong person re-identification method called PKA, combining prototype-guided knowledge propagation and adaptive parameter evolution to prevent catastrophic forgetting.

Q-Detection: A Quantum-Classical Hybrid Poisoning Attack Detection Method

Haoqi He (Sun Yat-sen University), Yan Xiao (Sun Yat-sen University)

CodeAnomaly DetectionAdversarial AttackConvolutional Neural NetworkImagePhysics Related

🎯 What it does: Propose a quantum-classical hybrid data poisoning detection method called Q-Detection, which utilizes Q-WAN to train a weight allocation network and filter a clean subset from training data.

Quantifying the Self-Interest Level of Markov Social Dilemmas

Richard Willis (King's College London), Michael Luck (University of Sussex)

CodeReinforcement Learning

🎯 What it does: This paper proposes an empirical method to quantify the self-interest level in Markov social dilemmas and evaluates agent cooperation through reward exchange.

Query-Based and Unnoticeable Graph Injection Attack from Neighborhood Perspective

Chang Liu (Beijing University of Posts and Telecommunications), Xingquan Zuo (Beijing University of Posts and Telecommunications)

CodeAdversarial AttackGraph

🎯 What it does: Designed a model-agnostic, black-box graph injection attack method called QUGIA, which generates injected node features using a Bayesian framework and constructs attack edges from the perspective of victim node neighbors, maintaining graph homophily to achieve stealthy attacks.

R2DQG: A Quality Meets Diversity Framework for Question Generation over Knowledge Bases

Yimeng Ren (Beijing University of Posts and Telecommunications), Mingliang Yan (Beijing University of Posts and Telecommunications)

CodeGenerationLarge Language ModelPrompt EngineeringTextGraph

🎯 What it does: Proposed a two-phase template-guided and error-correction framework named R DQG for generating diverse and semantically accurate knowledge graph question answering problems.

Reinforced In-Context Black-Box Optimization

Lei Song (Nanjing University), Chao Qian (Nanjing University)

CodeOptimizationRobotic IntelligenceTransformerSupervised Fine-TuningSequential

🎯 What it does: Learned an end-to-end black-box optimization algorithm called RIBBO, which uses offline optimization history to train a causal Transformer model to generate query points.

Relation-Augmented Dueling Bayesian Optimization via Preference Propagation

Xiang Xia (East China Normal University), Hong Qian (East China Normal University)

CodeOptimizationContrastive Learning

🎯 What it does: Proposes Relation-Enhanced Dueling Bayesian Optimization (RADBO), which more fully utilizes existing pairwise preference information in dueling black-box optimization through preference propagation techniques.

Reliable and Diverse Hierarchical Adapter for Zero-shot Video Classification

Wenxuan Ge (Nanjing University of Science and Technology), Xiangbo Shu (Nanjing University of Science and Technology)

CodeClassificationVision Language ModelVideo

🎯 What it does: Propose a training-free hierarchical adapter for zero-shot video classification

ReplayCAD: Generative Diffusion Replay for Continual Anomaly Detection

Lei Hu (South China University of Technology), Tianshui Chen (Guangdong University of Technology)

CodeAnomaly DetectionDiffusion modelImage

🎯 What it does: Proposed a ReplayCAD framework based on pre-trained diffusion models to compress and replay historical data in continual learning anomaly detection tasks, thereby mitigating catastrophic forgetting and improving pixel-level defect segmentation performance.

Representation Learning with Mutual Influence of Modalities for Node Classification in Multi-Modal Heterogeneous Networks

Jiafan Li (Institute of Software, Chinese Academy of Sciences), Hongan Wang (Institute of Software, Chinese Academy of Sciences)

CodeClassificationRepresentation LearningGraph Neural NetworkTransformerMultimodalityGraph

🎯 What it does: This paper proposes a model named HGNN-IMA for node classification in multi-modal heterogeneous networks, achieving mutual influence and fusion of node representations by embedding cross-modal attention within the heterogeneous graph transformer framework.

RePST: Language Model Empowered Spatio-Temporal Forecasting via Semantic-Oriented Reprogramming

Hao Wang (Hong Kong University of Science and Technology), Hao Liu (Hong Kong University of Science and Technology)

CodeTransformerLarge Language ModelTime Series

🎯 What it does: Propose the REPST framework, which utilizes pre-trained language models (PLM) for spatiotemporal prediction. It maps spatiotemporal sequences into the text vocabulary space through semantic-oriented decomposition and selective reprogramming, with predictions generated by a frozen GPT-2.

Rethinking Removal Attack and Fingerprinting Defense for Model Intellectual Property Protection: A Frequency Perspective

Cheng Zhang (Hunan University), Zixing Zhang (Hunan University)

CodeAdversarial AttackConvolutional Neural NetworkImage

🎯 What it does: Propose a frequency domain-based model ownership removal attack and the corresponding frequency domain fingerprint defense.

Rewarding Explainability in Drug Repurposing with Knowledge Graphs

Susana Nunes (University of Lisbon), Catia Pesquita (University of Lisbon)

CodeExplainability and InterpretabilityDrug DiscoveryRecurrent Neural NetworkReinforcement LearningGraphBiomedical Data

🎯 What it does: Propose a reinforcement learning-based knowledge graph path search method called REx, designed to generate scientifically interpretable paths for drug repurposing prediction;

Riding the Wave: Multi-Scale Spatial-Temporal Graph Learning for Highway Traffic Flow Prediction Under Overload Scenarios

Xigang Sun (Southeast University), Jun Zhu (Zhejiang Mobile Digital Intelligence Technology Co., Ltd.)

CodeAutonomous DrivingGraph Neural NetworkTransformerContrastive LearningGraphTime Series

🎯 What it does: Propose a traffic flow prediction framework HST-WAVE for highway overloading scenarios, combining multi-scale woven Transformer, coupled heterogeneous graph attention network, and adaptive temporal contrastive learning;

Risk-Aware Task Migration for Multiplex Unmanned Swarm Networks in Adversarial Environments

Kai Di (Zhejiang Normal University), Yichuan Jiang (Southeast University)

CodeOptimizationRobotic IntelligenceGraph

🎯 What it does: Designed and implemented a dual-scale risk-aware task migration algorithm to balance task loads in multi-layer drone swarms under adversarial environments.

Robust Graph Contrastive Learning for Incomplete Multi-view Clustering

Deyin Zhuang, Zhenwen Ren (Southwest University of Science and Technology)

CodeRepresentation LearningGraph Neural NetworkAuto EncoderContrastive LearningGraph

🎯 What it does: Proposed a robust graph contrastive learning framework RGCL to address the graph noise correspondence problem in incomplete multi-view clustering, completing missing data, constructing relational graphs, performing contrastive learning, and achieving graph-level alignment.

Robust Misinformation Detection by Visiting Potential Commonsense Conflict

Bing Wang (Jilin University), Shengsheng Wang (Jilin University)

CodeClassificationTransformerLarge Language ModelPrompt EngineeringTextRetrieval-Augmented Generation

🎯 What it does: Designed a plug-in augmentation method for misinformation detection called MD-PCC, which expresses potential common-sense conflicts as text increments to enhance detection effectiveness.

RRG-Mamba: Efficient Radiology Report Generation with State Space Model

Xiaodi Hou (Dalian Maritime University), Yijia Zhang (Dalian Maritime University)

CodeGenerationComputational EfficiencyTransformerLarge Language ModelVision Language ModelMultimodalityBiomedical Data

🎯 What it does: Propose the RRG-Mamba framework, combining Mamba and RoPE to generate radiology reports, addressing the trade-off between global dependency modeling and computational efficiency.

RTdetector: Deep Transformer Networks for Time Series Anomaly Detection Based on Reconstruction Trend

Xinhong Liu (Central South University), Ming Zhao (Central South University)

CodeAnomaly DetectionTransformerTime Series

🎯 What it does: Proposed an RTdetector, a time series anomaly detection model based on Transformer, which enhances anomaly discrimination by leveraging reconstruction trends.

Rule-Guided Reinforcement Learning Policy Evaluation and Improvement

Martin Tappler (TU Wien), Ezio Bartocci (University of Vienna)

CodeExplainability and InterpretabilityReinforcement Learning

🎯 What it does: This paper proposes the LEGIBLE framework, which evaluates and improves policies by extracting rules from deep reinforcement learning strategies, generalizing these rules using domain knowledge, and enforcing them at runtime.

Run Like a Neural Network, Explain Like k-Nearest Neighbor

Xiaomeng Ye (Berry College), David Crandall (Indiana University Bloomington)

CodeClassificationRecognitionExplainability and InterpretabilityConvolutional Neural NetworkRecurrent Neural NetworkImageText

🎯 What it does: Studied and improved the neural network k-nearest neighbors (NN-kNN) model, proposing a scalable, high-dimensional processable, and parameter-efficient version, and verified its interpretability and performance on image and text tasks.

SALE-MLP: Structure Aware Latent Embeddings for GNN to Graph-free MLP Distillation

Harsh Pal (Mastercard), Aakarsh Malhotra (Mastercard)

CodeComputational EfficiencyKnowledge DistillationRepresentation LearningGraph Neural NetworkContrastive LearningGraph

🎯 What it does: Designed a graph structure-aware graph-agnostic MLP distillation method called SALE-MLP, which maps node features into a latent space consistent with graph topology during training using unsupervised structural loss, followed by training a lightweight MLP for node classification and link prediction through soft label distillation.

SCVBench: A Benchmark with Multi-turn Dialogues for Story-Centric Video Understanding

Sisi You (Nanjing University of Posts and Telecommunications), Bing-Kun Bao (Nanjing University of Posts and Telecommunications)

CodeTransformerLarge Language ModelAgentic AIVision Language ModelVideoTextMultimodalityBenchmarkChain-of-Thought

🎯 What it does: Propose SCVBench, which evaluates video story-level understanding through multi-turn dialogue and event ordering tasks.

SDDiff: Boosting Radar Perception via Spatial-Doppler Diffusion

Shengpeng Wang (Huazhong University of Science and Technology), Wei Wang (Wuhan University)

CodeAutonomous DrivingConvolutional Neural NetworkDiffusion modelPoint Cloud

🎯 What it does: Proposed the SDDiff model, which achieves radar point cloud extraction (PCE) and ego-vehicle velocity estimation (EVE) simultaneously through spatial-Doppler diffusion, significantly improving radar perception quality.

Secure and Efficient Watermarking for Latent Diffusion Models in Model Distribution Scenarios

Liangqi Lei (Beijing Institute of Technology), Qi Wu (University of Adelaide)

CodeSafty and PrivacyAdversarial AttackSupervised Fine-TuningDiffusion modelAuto EncoderImageText

🎯 What it does: In large-scale model distribution scenarios, a secure and efficient watermarking scheme called DistriMark is proposed, achieving strong binding and non-bypassability of watermarks through secure controllers with random seed injection and VAE fine-tuning;

Seeking Proxy Point via Stable Feature Space for Noisy Correspondence Learning

Yucheng Xie (University of Electronic Science and Technology of China), Xiaofeng Zhu (University of Electronic Science and Technology of China)

CodeRetrievalRepresentation LearningData-Centric LearningContrastive LearningMultimodality

🎯 What it does: Propose a robust learning framework called Seeking Proxy Point via Stable Feature Space (SPS) to address the problem of noisy correspondence in cross-modal retrieval.

Semantic-Guided Diffusion Model for Single-Step Image Super-Resolution

Zihang Liu (Beijing Institute of Technology), Hao Tang (Peking University)

CodeSuper ResolutionKnowledge DistillationDiffusion modelImage

🎯 What it does: Propose a semantic-guided single-step diffusion model called SAMSR for image super-resolution.

SEP: A General Lossless Compression Framework with Semantics Enhancement and Multi-Stream Pipelines

Meng Wan (Chinese Academy of Sciences), Chong Li (Chinese Academy of Sciences)

CodeCompressionTransformerImageTextAudio

🎯 What it does: Proposed a general-purpose lossless compression framework called SEP based on semantic enhancement and a multi-stream pipeline

SepALM: Audio Language Models Are Error Correctors for Robust Speech Separation

Zhaoxi Mu (Xi'an Jiaotong University), Gang Wang (Xi'an Jiaotong University)

CodeRestorationKnowledge DistillationTransformerLarge Language ModelMultimodalityChain-of-ThoughtAudio

🎯 What it does: Proposed the SepALM framework, integrating four modules: speech separation, text-domain error correction, resynthesis, and alignment, achieving more robust speech separation in complex noise environments.

Sharpness-aware Zeroth-order Optimization for Graph Transformers

Yang Liu (Academy of Mathematics and Systems Science Chinese Academy of Science), Shirui Pan (Griffith University)

CodeOptimizationDrug DiscoveryGraph Neural NetworkTransformerGraph

🎯 What it does: Proposed and implemented a sharpness-aware zeroth-order optimizer (SZO) for graph Transformers, addressing the challenge of gradient estimation caused by non-differentiable operations.

ShortcutProbe: Probing Prediction Shortcuts for Learning Robust Models

Guangtao Zheng (University of Virginia), Aidong Zhang (University of Virginia)

CodeDomain AdaptationExplainability and InterpretabilityData-Centric LearningConvolutional Neural NetworkTransformerSupervised Fine-TuningImageText

🎯 What it does: Proposes a post-hoc group-free bias mitigation framework called ShortcutProbe, which can automatically detect and eliminate prediction shortcuts after model training to enhance robustness.

Simulate, Refine and Integrate: Strategy Synthesis for Efficient SMT Solving

Bingzhe Zhou (Nanjing University), Xiaoxing Ma (Nanjing University)

CodeOptimizationComputational EfficiencyGraph Neural NetworkReinforcement LearningGraphBenchmark

🎯 What it does: SIRISMT automatically synthesizes SMT solving strategies using reinforcement learning and graph neural networks, significantly improving the efficiency of Z3.

Simulating Misinformation Diffusion on Social Media Through CoNVaI: A Textual- and Agent-Based Diffusion Model

Raquel Rodríguez-García (UNED), Álvaro Rodrigo (UNED)

CodeAgentic AIText

🎯 What it does: This paper proposes a misinformation diffusion simulation model called CoNVaI, based on text content and agents, to more realistically reproduce the information spreading process on social media.