arXivSub Start free trial

IJCAI 2024 Papers with Code

International Joint Conference on Artificial Intelligence Β· 296 papers with a public code repository

3D Vision and Language Pretraining with Large-Scale Synthetic Data

Dejie Yang (Peking University), Yang Liu (Peking University)

CodeData SynthesisDomain AdaptationRepresentation LearningTransformerVision Language ModelTextPoint Cloud

🎯 What it does: Constructed a large-scale synthetic 3D scene and text-aligned dataset named SynVL3D, pre-trained the SynFormer3D model using this dataset, and introduced simulation-to-real domain adaptation in downstream 3D vision-language tasks;

3DBench: A Scalable 3D Benchmark and Instruction-Tuning Dataset

Junjie Zhang (Shanghai University), Dan Zeng (Shanghai University)

CodeLarge Language ModelPrompt EngineeringTextPoint CloudBenchmark

🎯 What it does: Proposes the 3DBench evaluation framework and an automatically constructed 0.23M instruction fine-tuning dataset to comprehensively evaluate the perception, reasoning, and expression capabilities of 3D-LLMs.

A Better Approximation for Bipartite Traveling Tournament in Inter-League Sports Scheduling

Jingyang Zhao (University of Electronic Science and Technology of China), Mingyu Xiao (University of Electronic Science and Technology of China)

CodeOptimizationGraphTabular

🎯 What it does: Proposed a randomized (3/2+Ρ) approximation algorithm for any scale BTTP (inter-league double round-robin tournament) problem

A Conservative Approach for Few-Shot Transfer in Off-Dynamics Reinforcement Learning

Paul Daoudi (Huawei Noah's Ark Lab), Ludovic Dos Santos (Criteo AI Lab)

CodeReinforcement Learning

🎯 What it does: Proposed the FOOD (Few-shOt Off Dynamics) algorithm, combining conservative RL regularization with simulation learning, leveraging the distribution gap between transition trajectories in source and target environments to achieve few-shot offline dynamic transfer.

A Context-Enhanced Framework for Sequential Graph Reasoning

Shuo Shi (East China Normal University), Zhengfeng Yang (East China Normal University)

CodeRepresentation LearningGraph Neural NetworkTransformerGraphSequentialBenchmark

🎯 What it does: Propose a context-enhanced framework (CEF), inserting a preprocessing module between the encoder and processor during serialized graph reasoning, utilizing historical hidden states to enhance features at each step and update context;

A Dataset and Model for Realistic License Plate Deblurring

Haoyan Gong (Xi'an Jiaotong-Liverpool University), Hongbin Liu (Xi'an Jiaotong-Liverpool University)

CodeRestorationTransformerGenerative Adversarial NetworkImage

🎯 What it does: Proposed a large-scale real-world license plate motion blur dataset, LPBlur, and designed a generative adversarial network (GAN) called LPDGAN specifically for license plate deblurring.

A De-singularity Subgradient Approach for the Extended Weber Location Problem

Zhao-Rong Lai (Jinan University), Ziliang Chen (Peng Cheng Laboratory)

CodeOptimizationTime SeriesFinance Related

🎯 What it does: Propose a subgradient method for removing singularities and the corresponding Weiszfeld algorithm (q-PWAWS) to address the singularity trap in the extended Weber location problem;

A Deep Reinforcement Learning Approach to Balance Viewport Prediction and Video Transmission in 360Β° Video Streaming

Guanghui Zhang (Shandong University), Jing Guo (Hong Kong Polytechnic University)

CodeOptimizationConvolutional Neural NetworkReinforcement LearningVideoTime Series

🎯 What it does: Proposed the QUTA system, which optimizes the QoE of 360° video streams by coordinating viewport prediction with video transmission parameters;

A Graph-based Representation Framework for Trajectory Recovery via Spatiotemporal Interval-Informed Seq2Seq

Yaya Zhao (Renmin University of China), Xiaoling Lu (Renmin University of China)

CodeRestorationRepresentation LearningGraph Neural NetworkTransformerGraphSequential

🎯 What it does: In low-sampling-rate urban trajectory data, a graph-based trajectory recovery framework named GRFTrajRec is constructed, leveraging trajectory-road network interaction and spatiotemporal interval information to achieve precise recovery of trajectory points.

A Grassmannian Manifold Self-Attention Network for Signal Classification

Rui Wang (Jiangnan University), Xiaoning Song (Jiangnan University)

CodeClassificationConvolutional Neural NetworkTransformerTime SeriesBiomedical Data

🎯 What it does: This paper proposes a lightweight deep network called GDLNet based on a Grassmannian manifold self-attention mechanism (GMSA) for efficient feature extraction and classification of sequential signals (e.g., radar, EEG).

A Neural Column Generation Approach to the Vehicle Routing Problem with Two-Dimensional Loading and Last-In-First-Out Constraints

Yifan Xia (State Key Laboratory for Novel Software Technology, Nanjing University), Xiangyi Zhang (1QB Information Technologies, Inc.)

CodeOptimizationRecurrent Neural NetworkTransformerTabular

🎯 What it does: Proposed a neural network-based column generation (NCG) algorithm that uses a machine learning model to predict the feasibility of two-dimensional loading under LIFO constraints, thereby improving traditional column generation for solving 2L-CVRP.

A SAT Solver + Computer Algebra Attack on the Minimum Kochen–Specker Problem

Zhengyu Li (Georgia Institute of Technology), Vijay Ganesh (Georgia Institute of Technology)

CodeOptimizationGraphPhysics Related

🎯 What it does: Proposed a verifiable proof generation method combining a SAT solver with a computer algebra system (CAS) to solve the three-dimensional Kochen-Specker (KS) problem and prove that the minimal KS system contains at least 24 vectors.

A Self-explaining Neural Architecture for Generalizable Concept Learning

Sanchit Sinha (University of Virginia), Aidong Zhang (University of Virginia)

CodeDomain AdaptationExplainability and InterpretabilityRepresentation LearningAuto EncoderContrastive LearningImage

🎯 What it does: Propose a self-explaining neural network architecture for cross-domain generalizable concept learning.

A Semi-supervised Molecular Learning Framework for Activity Cliff Estimation

Fang Wu (Stanford University)

CodeDrug DiscoveryGraph Neural NetworkBiomedical Data

🎯 What it does: Propose the SemiMol semi-supervised framework, which uses a teacher model to evaluate pseudo-label confidence and dynamically introduces pseudo-labels through adaptive curriculum learning to address the active cliff estimation problem under low-data scenarios.

A Swap Relaxation-Based Local Search for the Latin Square Completion Problem

Zhenxuan Xie (Huazhong University of Science and Technology), Yuxuan Wang (Huazhong University of Science and Technology)

CodeOptimizationBenchmark

🎯 What it does: This paper proposes a local search algorithm called SRLS based on exchange relaxation for solving the partial Latin square completion problem.

A Top-Down Tree Model Counter for Quantified Boolean Formulas

Florent Capelli (University of Artois), Martina Seidl (Johannes Kepler University Linz)

CodeBenchmark

🎯 What it does: Proposed a top-down counter called d4-QBF for tree model counting on any quantified prefix QBF, and implemented the complete algorithm and tool.

Accelerating Diffusion Models for Inverse Problems through Shortcut Sampling

Gongye Liu (Tsinghua University), Yujiu Yang (Tsinghua University)

CodeRestorationSuper ResolutionDiffusion modelImage

🎯 What it does: In the unsupervised zero-shot scenario, solving inverse problems using diffusion models by proposing a shortcut sampling path from 'input-transition state-target' to avoid starting from noise.

Active Deep Multi-view Clustering

Helin Zhao (Anhui University), Peng Zhou (Anhui University)

CodeRepresentation LearningData-Centric LearningAuto EncoderContrastive LearningMultimodalityBenchmark

🎯 What it does: Propose an active deep multi-view clustering method called ADMC, which can guide the clustering process by actively selecting important samples for manual annotation.

ADELT: Transpilation between Deep Learning Frameworks

Linyuan Gong (University of California, Berkeley), Alvin Cheung (University of California, Berkeley)

CodeDomain AdaptationAI Code AssistantTransformerLarge Language ModelGenerative Adversarial NetworkText

🎯 What it does: This study proposes ADELT, a source-to-source deep learning framework translator that leverages LLMs to translate code skeletons, then employs domain adversarial learning to generate API keyword mapping tables for cross-framework translation;

AK4Prompts: Aesthetics-driven Automatically Keywords-Ranking for Prompts in Text-To-Image Models

Haiyang Zhang (Beijing University of Posts and Telecommunications), Anlong Ming (Beijing University of Posts and Telecommunications)

CodeGenerationTransformerPrompt EngineeringDiffusion modelImageText

🎯 What it does: Propose an automated keyword evaluation model, AK4Prompts, which can quantify the multidimensional impact of keywords on the image quality of text-to-image synthesis (TIS) models, and automatically select the optimal keywords for given prompts;

Alleviating Imbalanced Pseudo-label Distribution: Self-Supervised Multi-Source Domain Adaptation with Label-specific Confidence

Shuai LΓΌ, Ximing Li (Jilin University)

CodeClassificationDomain AdaptationConvolutional Neural NetworkAuto EncoderContrastive LearningImage

🎯 What it does: Proposed a self-supervised multi-source domain adaptation method called S3DA-LC, which alleviates the problem of pseudo-label distribution imbalance by dynamically generating pseudo-labels using label-specific confidence to improve target domain performance.

An Efficient Prototype-Based Clustering Approach for Edge Pruning in Graph Neural Networks to Battle Over-Smoothing

Yuyang Huang (Shanghai Jiao Tong University), Yang Yang (Shanghai Jiao Tong University)

CodeComputational EfficiencyRepresentation LearningGraph Neural NetworkGraph

🎯 What it does: Propose a clustering method called ClusterDrop based on learnable prototypes for targeted edge removal during GNN training to alleviate the over-smoothing problem.

An Image-enhanced Molecular Graph Representation Learning Framework

Hongxin Xiang (Hunan University), Xiangxiang Zeng (Hunan University)

CodeKnowledge DistillationRepresentation LearningDrug DiscoveryConvolutional Neural NetworkGraph Neural NetworkContrastive LearningImageGraphBiomedical DataBenchmark

🎯 What it does: Built a cross-modal knowledge distillation-based molecular graph representation learning framework called IEM, which enhances graph neural networks using multi-view 3D molecular images.

An NCDE-based Framework for Universal Representation Learning of Time Series

Zihan Liu (Beihang University), Leilei Sun (Beihang University)

CodeClassificationRepresentation LearningContrastive LearningTime SeriesStochastic Differential Equation

🎯 What it does: Propose CTRL, a self-supervised temporal representation learning framework based on neural controlled differential equations (NCDE), achieving general representations through dual tasks (reconstruction + contrastive) and masking augmentation.

Angluin-Style Learning of Deterministic BΓΌchi and Co-BΓΌchi Automata

Yong Li (University of Liverpool), Qiyi Tang (University of Liverpool)

Code

🎯 What it does: Proposed an Angluin-style active learning framework-based algorithm for deterministic Büchi automata (DBA) and deterministic co-Büchi automata (DCA), and reduced the complexity of equivalence queries by converting finite deterministic finite automata (FDFA) into DBA.

Are Watermarks Bugs for Deepfake Detectors? Rethinking Proactive Forensics

Xiaoshuai Wu (Hunan University), Zheng Qin (Hunan University)

CodeAnomaly DetectionAdversarial AttackConvolutional Neural NetworkSupervised Fine-TuningGenerative Adversarial NetworkImage

🎯 What it does: Proposed a program called AdvMark that transforms robust watermarks into adversarial watermarks, achieving both image source tracking and improving the detection accuracy of deepfake detectors.

Attention Based Document-level Relation Extraction with None Class Ranking Loss

Xiaolong Xu (Nanjing University of Information Science and Technology), Wanchun Dou (Nanjing University)

CodeGraph Neural NetworkTransformerText

🎯 What it does: This paper proposes a document-level relation extraction model based on attention mechanisms, explicitly considering the no-relation scenario through None Class Ranking Loss to enhance multi-label prediction performance.

AutoAgents: A Framework for Automatic Agent Generation

Guangyao Chen (Peking University), Yemin Shi (Peking University)

CodeTransformerLarge Language ModelAgentic AIText

🎯 What it does: Propose the AutoAgents framework, which can automatically generate specialized agents based on tasks and enable collaborative execution.

Best Arm Identification with Retroactively Increased Sampling Budget for More Resource-Efficient HPO

Jasmin Brandt (Paderborn University), Eyke HΓΌllermeier

CodeOptimizationComputational EfficiencyHyperparameter SearchBenchmark

🎯 What it does: An incremental Successive Halving (iSHA) algorithm is proposed for non-random multi-armed bandit (Best Arm Identification) and hyperparameter optimization (HPO), which can increase the maximum budget after the original SHA runs as needed, while providing corresponding theoretical guarantees and experimental validation.

Beyond Alignment: Blind Video Face Restoration via Parsing-Guided Temporal-Coherent Transformer

Kepeng Xu (Xidian University), Yunsong Li (Xidian University)

CodeRestorationTransformerAuto EncoderVideo

🎯 What it does: Proposes an end-to-end alignment-free blind video face restoration framework named PGTFormer, which utilizes a semantically guided spatiotemporal vector quantized autoencoder and a spatiotemporally parsed codebook predictor to achieve high-quality and temporally coherent video face reconstruction.

BeyondVision: An EMG-driven Micro Hand Gesture Recognition Based on Dynamic Segmentation

Nana Wang (Beihang University), Hao Su (Zhengzhou University)

CodeRecognitionComputational EfficiencyConvolutional Neural NetworkBiomedical Data

🎯 What it does: This paper proposes a micro-gesture recognition system called BeyondVision, which includes a wearable wristband EMG acquisition device, a lightweight CNN network BV-Net, and a post-processing algorithm based on weight segmentation, achieving real-time mapping from micro-gestures to control commands.

BoostDream: Efficient Refining for High-Quality Text-to-3D Generation from Multi-View Diffusion

Yonghao Yu (Waseda University), Haorui Li (Southeast University)

CodeGenerationData SynthesisComputational EfficiencyVision Language ModelDiffusion modelScore-based ModelNeural Radiance FieldGaussian SplattingImageTextMesh

🎯 What it does: Propose BoostDream, a three-stage efficient refinement framework that converts rough 3D assets generated by feed-forward processes into high-quality, controllable 3D assets.

Boosting Efficiency in Task-Agnostic Exploration through Causal Knowledge

Yupei Yang (Shanghai Jiao Tong University), Lei Xu (Shanghai Jiao Tong University)

CodeAutonomous DrivingComputational EfficiencyReinforcement LearningWorld ModelPhysics Related

🎯 What it does: Proposes a task-agnostic reinforcement learning framework based on causal exploration, leveraging online causal discovery and structural constraints to enhance the sample efficiency and reliability of world model learning.

Boosting Single Positive Multi-label Classification with Generalized Robust Loss

Yanxi Chen (University of International Business and Economics), Bo Wang (University of International Business and Economics)

CodeClassificationImage

🎯 What it does: Proposed a general robust loss framework (GR Loss) for single positive multi-label learning (SPML), addressing missing labels and class imbalance through soft pseudo labels and weight adjustment.

Boundary-aware Decoupled Flow Networks for Realistic Extreme Rescaling

Jinmin Li (Tsinghua University), Rizen Guo (Tencent)

CodeRestorationConvolutional Neural NetworkFlow-based ModelImage

🎯 What it does: Designed a boundary-aware separated flow network (BDFlow), which achieves more realistic image resizing by splitting high-frequency information into semantic boundary distribution and non-semantic Gaussian distribution.

Bridging Stereo Geometry and BEV Representation with Reliable Mutual Interaction for Semantic Scene Completion

Bohan Li (Shanghai Jiao Tong University), Wenjun Zeng (Shanghai Jiao Tong University)

CodeSegmentationDepth EstimationAutonomous DrivingConvolutional Neural NetworkTransformerOptical FlowImage

🎯 What it does: Proposed a framework named BRGScene, which integrates stereo matching with bird's-eye view (BEV) 3D volumes to achieve monocular camera-based 3D semantic scene completion (SSC)

Bridging the Gap: Learning Pace Synchronization for Open-World Semi-Supervised Learning

Bo Ye (Southeast University), Min-Ling Zhang (Southeast University)

CodeClassificationContrastive LearningImage

🎯 What it does: Propose a Learning Rhythm Synchronization (LPS) framework that maintains consistent learning rates between known and unknown classes through adaptive margin loss and pseudo-label contrastive clustering, achieving better new class discovery and known class classification in open semi-supervised learning.

Bring Metric Functions into Diffusion Models

Jie An (University of Rochester), Jiebo Luo (University of Rochester)

CodeGenerationDiffusion modelScore-based ModelImage

🎯 What it does: Propose a cascaded diffusion model called Cas-DM, incorporating metric functions such as LPIPS during training to enhance the quality of generated images.

Causality-enhanced Discreted Physics-informed Neural Networks for Predicting Evolutionary Equations

Ye Li (Nanjing University of Aeronautics and Astronautics), Sheng-Jun Huang (Nanjing University of Aeronautics and Astronautics)

CodeComputational EfficiencyBenchmarkPhysics Related

🎯 What it does: Propose a physics-informed neural network (TL-DPINN) based on implicit time discretization, which accelerates solving evolutionary partial differential equations through step-by-step training and transfer learning.

CausalNET: Unveiling Causal Structures on Event Sequences by Topology-Informed Causal Attention

Hua Zhu (Huazhong University of Science and Technology), Bang Liu (Universite de Montreal)

CodeExplainability and InterpretabilityTransformerTime SeriesSequential

🎯 What it does: Constructed the CausalNET model, using Transformer and a trainable causal graph to perform causal structure learning on event sequences.

CF-Deformable DETR: An End-to-End Alignment-Free Model for Weakly Aligned Visible-Infrared Object Detection

Haolong Fu (Hunan University), Zhiyong Li (Hunan University)

CodeObject DetectionTransformerContrastive LearningImageMultimodality

🎯 What it does: Designed an end-to-end alignment-agnostic visible-infrared object detection model called CF-Deformable DETR, achieving cross-modal point-level feature extraction and fusion directly on weakly aligned data.

ChatSpot: Bootstrapping Multimodal LLMs via Precise Referring Instruction Tuning

Liang Zhao (MEGVII Technology), Xiangyu Zhang (MEGVII Technology)

CodeClassificationRecognitionTransformerLarge Language ModelSupervised Fine-TuningPrompt EngineeringVision Language ModelImageTextMultimodality

🎯 What it does: Propose ChatSpot, a unified end-to-end multimodal large language model that supports multiple precise pointing interactions (clicking, box selection, polygon drawing) and achieves fine-grained vision-language question answering and instruction following.

Class-Specific Semantic Generation and Reconstruction Learning for Open Set Recognition

Liu Haoyang (Hefei University Of Technology), Xuegang Hu (Hefei University Of Technology)

CodeClassificationRecognitionAuto EncoderGenerative Adversarial NetworkImage

🎯 What it does: Propose an open-set recognition framework based on class-specific semantic generation and reconstruction learning (CSGRL), which generates boundary samples of known classes through a generator and uses an additional autoencoder to fit the joint boundary of the unknown space, thus considering both known and unknown classes in the reconstruction error to achieve more robust unknown sample rejection and known class classification.

CMACE: CMAES-based Counterfactual Explanations for Black-box Models

Xudong Yin (Ant Group), Yao Yang (Zhejiang Lab)

CodeOptimizationExplainability and InterpretabilityTabular

🎯 What it does: This paper proposes a model-agnostic adversarial explanation method called CMACE based on CMA-ES for generating optimal counterfactual explanations for black-box models.

CMMU: A Benchmark for Chinese Multi-modal Multi-type Question Understanding and Reasoning

Zheqi He (Beijing Academy Of Artificial Intelligence), Hua Huang (Beijing Normal University)

CodeLarge Language ModelVision Language ModelMultimodalityBenchmark

🎯 What it does: Designed and released the CMMU Chinese multimodal and multi-type question-answering benchmark, which includes multiple disciplines and various difficulty levels of multiple-choice, multiple-select, and fill-in-the-blank questions.

CoCoG: Controllable Visual Stimuli Generation Based on Human Concept Representations

Chen Wei (Southern University of Science and Technology), Quanying Liu (Southern University of Science and Technology)

CodeGenerationData SynthesisExplainability and InterpretabilityVision Language ModelDiffusion modelImageBenchmark

🎯 What it does: Built a concept encoder to extract interpretable low-dimensional concept embeddings from visual stimuli, and trained a two-stage diffusion decoder using these embeddings to generate constrained images in the concept space, achieving controllable visual stimulus generation based on human concept representations.

CoFInAl: Enhancing Action Quality Assessment with Coarse-to-Fine Instruction Alignment

Kanglei Zhou (Beihang University), Xiaohui Liang (Beihang University)

CodeClassificationTransformerSupervised Fine-TuningVision-Language-Action ModelVideo

🎯 What it does: Treat action quality assessment (AQA) as a coarse-to-fine hierarchical classification task, proposing the CoFInAl framework that leverages coarse-level prototype learning and fixed ETF sub-grade prototypes to achieve coarse-to-fine instruction alignment, thereby improving evaluation performance.

Combinatorial Routing for Neural Trees

Jiahao Li (Guangdong University of Technology), Yuguang Yan (Guangdong University of Technology)

CodeNeural Architecture SearchImage

🎯 What it does: Proposes a neural tree method called CombRo based on multicast routing, which automatically searches and generates high-performance neural network architectures from a mother tree network.

CompetEvo: Towards Morphological Evolution from Competition

Kangyao Huang (Tsinghua University), Huaping Liu (Tsinghua University)

CodeRobotic IntelligenceReinforcement Learning

🎯 What it does: Propose a competitive evolution framework called CompetEvo, enabling robots to co-evolve their body morphology and combat strategies through self-play.

Concept-Level Causal Explanation Method for Brain Function Network Classification

Jinduo Liu (Beijing University of Technology), Junzhong Ji (Beijing University of Technology)

CodeClassificationConvolutional Neural NetworkGraphBiomedical Data

🎯 What it does: Propose a causal concept-based explanation method named CLCEM, which automatically extracts interpretable ROI concepts from brain functional networks and drives classification decisions through concept contributions;

Constrained Intrinsic Motivation for Reinforcement Learning

Xiang Zheng (City University of Hong Kong), Cong Wang (City University of Hong Kong)

CodeReinforcement LearningBenchmark

🎯 What it does: This paper proposes Constrained Intrinsic Motivation (CIM), designing new intrinsic goals and adaptive coefficients for Reward-Free Pre-Training (RFPT) and Exploration with Intrinsic Motivation (EIM) tasks, achieving more efficient skill discovery and exploration.

ConstrainedZero: Chance-Constrained POMDP Planning Using Learned Probabilistic Failure Surrogates and Adaptive Safety Constraints

Robert J. Moss (Stanford University), Mykel J. Kochenderfer (Stanford University)

CodeOptimization

🎯 What it does: This paper proposes ConstrainedZero, an extension of the BetaZero POMDP planning algorithm, designed to address chance-constrained POMDP (CC-POMDP) problems. It can simultaneously learn value functions, action policies, and failure probabilities in the Bayesian space, and employs an adaptive safety threshold in online Monte Carlo Tree Search (MCTS) for safe decision-making.

Contextualized Speech Recognition: Rethinking Second-Pass Rescoring with Generative Large Language Models

Yixuan Tang (National University of Singapore), Anthony K. H. Tung

CodeRecognitionTransformerLarge Language ModelPrompt EngineeringTextAudio

🎯 What it does: Propose a secondary generation framework based on large language models (LLMs) for contextual semantic ASR tasks, replacing traditional secondary re-ranking methods;

Contrastive Representation Learning for Self-Supervised Taxonomy Completion

Yuhang Niu (Nankai University), Xiaojie Yuan (Nankai University)

CodeClassificationRepresentation LearningTransformerPrompt EngineeringContrastive LearningText

🎯 What it does: Proposes the CoSTC framework, which employs contrastive learning for two-stage pre-training: first performing instance contrast between query-query and position-position within the same view, then conducting query-position contrast matching across views through diversity and difficulty sampling to enhance the quality of representations for self-supervised lexical classification.

Correct and Optimal: The Regular Expression Inference Challenge

Mojtaba Valizadeh (University of Sussex), Martin Berger (University of Sussex)

CodeOptimizationTransformerLarge Language ModelTextBenchmarkRetrieval-Augmented Generation

🎯 What it does: Proposed the Regular Expression Inference (REI) challenge, defining the task of learning minimal regular expressions as a machine learning benchmark, releasing four large-scale datasets and providing baseline models.

CPa-WAC: Constellation Partitioning-based Scalable Weighted Aggregation Composition for Knowledge Graph Embedding

Sudipta Modak (University of Windsor), Esam Abdel-Raheem (University of Windsor)

CodeRepresentation LearningGraph Neural NetworkGraph

🎯 What it does: This study proposes a knowledge graph embedding framework CPa-WAC based on Louvain/Leiden constellation partitioning and lightweight GCN, and merges the embeddings of subgraphs through a global decoder to achieve efficient training and high-quality link prediction.

Cross-Domain Few-Shot Semantic Segmentation via Doubly Matching Transformation

Jiayi Chen (Nanjing University of Aeronautics and Astronautics), Jie Qin (Nanjing University of Aeronautics and Astronautics)

CodeSegmentationDomain AdaptationConvolutional Neural NetworkContrastive LearningImage

🎯 What it does: This paper proposes a Dual Matching Transformation Network (DMTNet) to address the cross-domain few-shot semantic segmentation problem.

Cross-Scale Domain Adaptation with Comprehensive Information for Pansharpening

Meiqi Gong (Wuhan University), Jiayi Ma (Wuhan University)

CodeDomain AdaptationConvolutional Neural NetworkRecurrent Neural NetworkImage

🎯 What it does: This paper proposes a cross-scale domain adaptive fusion (pansharpening) method to synthesize high-resolution multispectral images by combining multispectral imagery with full-resolution panchromatic imagery.

Cutting the Black Box: Conceptual Interpretation of a Deep Neural Net with Multi-Modal Embeddings and Multi-Criteria Decision Aid

Nicolas Atienza (Thales Research and Technology), Michele Sebag (Universite Paris Saclay)

CodeExplainability and InterpretabilityKnowledge DistillationConvolutional Neural NetworkTransformerVision Language ModelAuto EncoderImage

🎯 What it does: Through the CB2 framework, pixel-level depth visual models are mapped to a concept space, and an interpretable 2-additive hierarchical Choquet integral (MCDA) student model is trained to explain the teacher model's decisions.

DarkFed: A Data-Free Backdoor Attack in Federated Learning

Minghui Li (Huazhong University of Science and Technology), Yichen Wang (National Engineering Research Center for Big Data Technology and System)

CodeFederated LearningAdversarial AttackImage

🎯 What it does: Propose DarkFed, an attack scheme that achieves backdoor injection in federated learning without real data, utilizing shadow datasets and attribute simulation techniques to successfully implant backdoors in simulated clients even without task-related data.

DCDet: Dynamic Cross-based 3D Object Detector

Shuai Liu (Sun Yat-sen University), Kai Huang (Sun Yat-sen University)

CodeObject DetectionAutonomous DrivingPoint Cloud

🎯 What it does: Proposed a dynamic label assignment (DCLA) based on cross-shaped regions and a rotation-weighted IoU (RWIoU) loss, constructing a single-stage 3D object detection framework named DCDet;

Decoupled Invariant Attention Network for Multivariate Time-series Forecasting

Haihua Xu (University of Macau), Pengyang Wang (University of Macau)

CodeGraph Neural NetworkTransformerTime Series

🎯 What it does: Proposed the Decoupled Invariant Attention Network (DIAN), which decouples invariant and variant patterns in multivariate time series through a variable-invariant attention mechanism in spatial and temporal dimensions, and enhances prediction robustness by generating intervention samples via a time intervention mechanism.

Decoupling Breaks Data Barriers: A Decoupled Pre-training Framework for Multi-intent Spoken Language Understanding

Libo Qin (Central South University), Wanxiang Che

CodeTransformerLarge Language ModelSupervised Fine-TuningTextAudio

🎯 What it does: Proposes a decoupled pre-training framework DPF for multi-intent speech understanding, conducting two-stage pre-training using a large amount of unlabeled multi-intent data.

Deep Embedding Clustering Driven by Sample Stability

Zhanwen Cheng (Shanxi University), Yuhua Qian (Shanxi University)

CodeRepresentation LearningConvolutional Neural NetworkAuto EncoderImage

🎯 What it does: Propose a sample stability-driven deep embedded clustering method called DECS, eliminating the dependence on pseudo-labels in traditional clustering;

Deep Hierarchical Graph Alignment Kernels

Shuhao Tang (Tongji University), Wei Ye (Tongji University)

CodeClassificationRepresentation LearningLarge Language ModelGraph

🎯 What it does: Proposed Deep Hierarchical Graph Alignment Kernels (DHGAK), achieving more accurate graph similarity computation by clustering and aligning hierarchical substructures in a deep embedding space.

Denoising-Aware Contrastive Learning for Noisy Time Series

Shuang Zhou (Hong Kong Polytechnic University), Korris Chung (Hong Kong Polytechnic University)

CodeClassificationRepresentation LearningTransformerAuto EncoderContrastive LearningTime SeriesBiomedical DataElectrocardiogram

🎯 What it does: Propose an end-to-end denoising-aware contrastive learning framework DECL, which automatically selects an appropriate denoising method for each noisy time series and suppresses noise through contrastive learning in representation learning.

DenseKoopman: A Plug-and-Play Framework for Dense Pedestrian Trajectory Prediction

Xianbang Li (Beihang University), Liang Xu (Beihang University)

CodeAutonomous DrivingConvolutional Neural NetworkRecurrent Neural NetworkVideo

🎯 What it does: Propose the DenseKoopman framework, which utilizes the Koopman operator to map nonlinear pedestrian trajectories in dense scenes to a high-dimensional linear space, enabling linearized trajectory prediction;

Design a Win-Win Strategy That Is Fair to Both Service Providers and Tasks When Rejection Is Not an Option

Yohai Trabelsi (Bar-Ilan University), Sarit Kraus (Bar-Ilan University)

CodeAutonomous DrivingOptimizationTabularTime Series

🎯 What it does: Proposed two online matching models based on minimax fairness, and designed algorithms using linear programming and heuristics to achieve fair allocation between service providers and tasks without allowing task rejections.

Detecting and Understanding Vulnerabilities in Language Models via Mechanistic Interpretability

Jorge GarcΓ­a-Carrasco (University of Alicante), Juan Trujillo (University of Alicante)

CodeExplainability and InterpretabilityAdversarial AttackTransformerLarge Language ModelText

🎯 What it does: Propose a framework based on mechanism interpretability, combined with adversarial sample generation, to systematically locate and understand adversarial vulnerability components in language models for specific tasks.

DGCD: An Adaptive Denoising GNN for Group-level Cognitive Diagnosis

Haiping Ma (Anhui University), Hengshu Zhu (Anhui University)

CodeRepresentation LearningGraph Neural NetworkAuto EncoderGraph

🎯 What it does: Construct a group-student-exercise (GSE) heterogeneous graph, leverage graph neural networks to learn high-order representations of groups, and integrate an adaptive denoising module and entropy-weighted balancing module to achieve group-level cognitive diagnosis.

DGR: A General Graph Desmoothing Framework for Recommendation via Global and Local Perspectives

Leilei Ding (University of Science and Technology of China), Yanyong Zhang (University of Science and Technology of China)

CodeRecommendation SystemGraph Neural NetworkSupervised Fine-TuningContrastive LearningGraph

🎯 What it does: Proposes a general graph smoothing elimination framework called DGR to address the over-smoothing problem in GCN-based recommendation systems.

Dialogue Cross-Enhanced Central Engagement Attention Model for Real-Time Engagement Estimation

Jun Yu (University of Science and Technology of China), Peng Chang (PAII Inc)

CodeRecognitionTransformerMultimodality

🎯 What it does: Propose a Dialogue Cross-Enhanced CEAM (Dialogue Cross-Enhanced Center Attention Model) and a central sliding window method to achieve accurate estimation of participation in real-time two-person interactions.

DiffStega: Towards Universal Training-Free Coverless Image Steganography with Diffusion Models

Yiwei Yang (Shanghai Jiao Tong University), Guangtao Zhai (Shanghai Jiao Tong University)

CodeGenerationSafty and PrivacyDiffusion modelImage

🎯 What it does: This paper proposes DiffStega, an unencapsulated image steganography method based on diffusion models, which generates a reference image using a preset password and achieves encryption and decryption through noise flipping.

Domain Adaptive and Fine-grained Anomaly Detection for Single-cell Sequencing Data and Beyond

Kaichen Xu (Zhongnan University of Economics and Law), Xiaobo Sun (Zhongnan University of Economics and Law)

CodeDomain AdaptationAnomaly DetectionGenerative Adversarial NetworkBiomedical Data

🎯 What it does: Propose a generative framework named ACSleuth that unifies anomaly cell detection, domain adaptation, and fine-grained anomaly cell classification in single-cell sequence data;

DTS-TPT: Dual Temporal-Sync Test-time Prompt Tuning for Zero-shot Activity Recognition

Rui Yan (Nanjing University), Tieniu Tan (Nanjing University)

CodeRecognitionLarge Language ModelPrompt EngineeringVision Language ModelVideo

🎯 What it does: This paper proposes the Dual-Temporal Synchronization Test-Time Prompt Tuning framework (DTS-TPT) for zero-shot video action recognition.

Dual Contrastive Graph-Level Clustering with Multiple Cluster Perspectives Alignment

Jinyu Cai (National University of Singapore), Wenzhong Guo (Fuzhou University)

CodeRepresentation LearningGraph Neural NetworkContrastive LearningGraph

🎯 What it does: Proposed a dual-contrast graph hierarchical clustering method DCGLC, achieving unsupervised graph layer clustering through graph contrastive learning and multi-view clustering alignment.

DVPE: Divided View Position Embedding for Multi-View 3D Object Detection

Jiasen Wang (Shanghai University), Yang Zhou (Shanghai University)

CodeObject DetectionAutonomous DrivingTransformerImageTime Series

🎯 What it does: Proposes a divided-view position embedding (DVPE) framework for multi-view 3D object detection, integrating separable view visibility attention, temporal modeling of 2D RoI priors, and a one-to-many assignment training strategy.

Dynamic against Dynamic: An Open-Set Self-Learning Framework

Haifeng Yang (Nanjing University of Aeronautics and Astronautics), Songcan Chen (Nanjing University of Aeronautics and Astronautics)

CodeClassificationRecognitionImageBenchmark

🎯 What it does: Propose an open-set self-learning (OSSL) framework based on the dynamic-to-dynamic idea, designed to dynamically adapt to unknown class samples and enhance recognition performance in open and dynamic scenarios.

Dynamic Many-Objective Molecular Optimization: Unfolding Complexity with Objective Decomposition and Progressive Optimization

Dong-Hee Shin (Korea University), Tae-Eui Kam (Korea University)

CodeOptimizationDrug DiscoveryTransformerReinforcement LearningBiomedical DataBenchmark

🎯 What it does: Propose a DyMol method that addresses dynamic multi-objective molecular optimization problems using the ideas of decomposition and progressive optimization.

Dynamically Anchored Prompting for Task-Imbalanced Continual Learning

Chenxing Hong (Xiamen University), Hanzi Wang (Xiamen University)

CodeClassificationTransformerPrompt EngineeringImage

🎯 What it does: Proposed a dynamic anchoring prompt (DAP) method to address the task imbalance problem in continual learning;

Dynamicity-aware Social Bot Detection with Dynamic Graph Transformers

Buyun He (University of Science and Technology of China), Pengyuan Zhou (Aarhus university)

CodeClassificationAnomaly DetectionGraph Neural NetworkTransformerGraph

🎯 What it does: This paper proposes a new social bot detection framework called BotDGT, focusing on the dynamics of social networks, combining a structural module and a temporal module to capture the context of historical interaction graphs and evolutionary behaviors;

EAB-FL: Exacerbating Algorithmic Bias through Model Poisoning Attacks in Federated Learning

Syed Irfan Ali Meerza (University of Tennessee, Knoxville), Jian Liu (University of Tennessee, Knoxville)

CodeFederated LearningAdversarial AttackImageTabular

🎯 What it does: A technique leveraging model redundancy space for model poisoning attacks is proposed within the federated learning framework to significantly exacerbate group unfairness while maintaining overall model accuracy.

EAT: Self-Supervised Pre-Training with Efficient Audio Transformer

Wenxi Chen (Shanghai Jiao Tong University), Xie Chen (Shanghai Jiao Tong University)

CodeClassificationComputational EfficiencyRepresentation LearningConvolutional Neural NetworkTransformerAudio

🎯 What it does: Propose the EAT model, which employs a self-supervised trained audio Transformer, combined with inverse block multiple masking and Utterance-Frame Objective to enhance pre-training efficiency and performance.

EC-SNN: Splitting Deep Spiking Neural Networks for Edge Devices

Di Yu (Zhejiang University), Shuiguang Deng (Zhejiang University)

CodeComputational EfficiencyKnowledge DistillationSpiking Neural NetworkImageAudio

🎯 What it does: Split large deep SNNs into multiple sub-models and parallelize their execution on multiple edge devices, further compressing the sub-models using channel pruning.

EFEVD: Enhanced Feature Extraction for Smart Contract Vulnerability Detection

Chi Jiang (University of Electronic Science and Technology of China), Yin Zhang (University of Electronic Science and Technology of China)

CodeClassificationAnomaly DetectionConvolutional Neural NetworkGraph Neural NetworkTransformerTextGraphFinance Related

🎯 What it does: This paper proposes an enhanced feature extraction method (EFEVD) that improves smart contract vulnerability detection through community features and cross-task shared features.

Effective Approach to LTLf Best-Effort Synthesis in Multi-Tier Environments

Benjamin Aminof (Universit' a degli Studi di Roma 'La Sapienza'), Sasha Rubin (University of Sydney)

CodeOptimizationComputational EfficiencyBenchmark

🎯 What it does: This paper studies best-effort synthesis using LTLf in multi-tier environments and proposes an algorithm that completes in linear time.

Efficient and Stable Offline-to-online Reinforcement Learning via Continual Policy Revitalization

Rui Kong (Nanjing University), Ming Li (Nanjing University)

CodeReinforcement LearningBenchmark

🎯 What it does: Propose a Continuous Policy Revival (CPR) method in offline-to-online reinforcement learning, achieving stable and efficient online fine-tuning through periodic policy reset, retaining historical policy sets, and using adaptive policy constraints.

Efficient Event Stream Super-Resolution with Recursive Multi-Branch Fusion

Quanmin Liang (Sun Yat-Sen University), Yonghong Tian (Peng Cheng Laboratory)

CodeSuper ResolutionRecurrent Neural Network

🎯 What it does: Propose a recursive multi-branch information fusion network RMFNET, which extracts and fuses information using positive/negative event branches and an event frame branch to achieve efficient event stream super-resolution.

Efficient Tuning and Inference for Large Language Models on Textual Graphs

Yun Zhu (Zhejiang University), Siliang Tang (Zhejiang University)

CodeClassificationComputational EfficiencyGraph Neural NetworkTransformerLarge Language ModelGraph

🎯 What it does: Proposes ENGINE, a parameter and memory-efficient fine-tuning method for large language models (LLMs) on text graphs, which employs a frozen LLM with a lightweight G-Ladder side structure, and further enhances training and inference speed through caching and dynamic early stopping.

Eliminating the Cross-Domain Misalignment in Text-guided Image Inpainting

Muqi Huang (Wuhan University), Lefei Zhang (Wuhan University)

CodeRestorationGenerationVision Language ModelDiffusion modelImageText

🎯 What it does: Propose a structure-aware training scheme (SAIL) and an asymmetric cross-domain attention mechanism (ACDA) to improve text-guided image inpainting, making the generated results more structurally and texturally consistent with the original image and text description.

EMOTE: An Explainable Architecture for Modelling the Other through Empathy

Manisha Senadeera (Deakin University), Santu Rana (Deakin University)

CodeExplainability and InterpretabilityReinforcement Learning

🎯 What it does: This paper proposes EMOTE (Explainable Architecture for Modelling the Other through Empathy), which models the action value and reward function of independent agents by learning the Q-function of the agent itself, and achieves online inverse reinforcement learning through a two-stage network that generates explainable empathy states;

Empirical Analysis of Dialogue Relation Extraction with Large Language Models

Guozheng Li (Southeast University), Yikai Guo (Beijing Institute of Computer Technology and Application)

CodeTransformerLarge Language ModelSupervised Fine-TuningPrompt EngineeringTextMultimodality

🎯 What it does: Explored the application of large language models in dialogue relation extraction, including prompt-based extraction for ChatGPT and LoRA fine-tuning for open-source LLMs.

Enabling Mixed Effects Neural Networks for Diverse, Clustered Data Using Monte Carlo Methods

Andrej Tschalzev (University of Mannheim), Heiner Stuckenschmidt (University of Mannheim)

CodeClassificationExplainability and InterpretabilityData-Centric LearningTabularBenchmark

🎯 What it does: Proposed and implemented a mixed-effect neural network training framework named MC-GMENN, capable of simultaneously handling multi-class and multi-cluster features, and achieving precise Bayesian estimation of random effects through Monte Carlo EM and NUTS sampling.

Enhancing Boundary Segmentation for Topological Accuracy with Skeleton-based Methods

Chuni Liu (University of Science and Technology Beijing), Ke Xu (University of Science and Technology Beijing)

CodeSegmentationConvolutional Neural NetworkImage

🎯 What it does: This paper proposes a Skea-Topo Aware loss function for boundary segmentation tasks, significantly improving the topological consistency of segmentation results.

Enhancing Cooperation through Selective Interaction and Long-term Experiences in Multi-Agent Reinforcement Learning

Tianyu Ren (University of Manchester), Xiao-Jun Zeng (University of Manchester)

CodeReinforcement LearningGraph

🎯 What it does: In an iterated prisoner's dilemma game on a 2D grid, researchers designed a multi-agent reinforcement learning framework enabling agents to simultaneously learn cooperation/betrayal strategies and neighbor selection strategies under the guidance of long-term experience.

Enhancing Fine-Grained Urban Flow Inference via Incremental Neural Operator

Qiang Gao (Southwestern University of Finance and Economics), Xueqin Chen (Delft University of Technology)

CodeOptimizationSafty and PrivacyConvolutional Neural NetworkTime SeriesSequential

🎯 What it does: Proposes a fine-grained traffic inference framework UNOI (Urban Neural Operator with Incremental Learning) based on neural operators and incremental learning, which can predict fine-grained traffic with only coarse-grained inputs, and addresses catastrophic forgetting and privacy leakage issues through two incremental strategies.

Error-aware Sampling in Adaptive Shells for Neural Surface Reconstruction

Qi Wang (Zhejiang University), Hujun Bao (Zhejiang University)

CodeNeural Radiance FieldPoint CloudMesh

🎯 What it does: The paper proposes an error-aware sampling method based on learnable spatially varying kernel sizes, and achieves significant reduction in the number of sampling points while maintaining reconstruction accuracy through a dual cropping strategy to obtain an adaptive shell.

Estimating before Debiasing: A Bayesian Approach to Detaching Prior Bias in Federated Semi-Supervised Learning

Guogang Zhu (Beihang University), Hao Su (Beihang University)

CodeFederated LearningImage

🎯 What it does: Propose FedDB, a Bayesian debiasing method for federated semi-supervised learning, which improves the model's generalization performance on imbalanced data by estimating and correcting label prior bias.

EvaNet: Elevation-Guided Flood Extent Mapping on Earth Imagery

Mirza Tanzim Sami (University of Alabama at Birmingham), Yang Zhou (Auburn University)

CodeSegmentationConvolutional Neural NetworkImage

🎯 What it does: Proposed EvaNet, a flood extent segmentation network guided by digital elevation models (DEM).

EVE: Efficient Zero-Shot Text-Based Video Editing With Depth Map Guidance and Temporal Consistency Constraints

Yutao Chen (Shandong University), Qingpei Guo (Ant Group)

CodeGenerationDepth EstimationVision Language ModelDiffusion modelVideoTextBenchmark

🎯 What it does: Proposed EVE, a zero-copy text-driven video editing method based on pre-trained LDM, enhancing temporal consistency through depth map guidance and frame-aligned attention.