arXivSub Start free trial

AAAI 2024 Papers with Code β€” Page 6

AAAI Conference on Artificial Intelligence Β· 1014 papers

KD-Club: An Efficient Exact Algorithm with New Coloring-Based Upper Bound for the Maximum k-Defective Clique Problem

Mingming Jin (Huazhong University of Science and Technology), Kun He (Huazhong University of Science and Technology)

CodeGraph Neural NetworkGraph

🎯 What it does: A graph coloring-based upper bound CLUB and the corresponding KD-Club algorithm are proposed for the exact solution of the maximum k-defective clique problem.

KeDuSR: Real-World Dual-Lens Super-Resolution via Kernel-Free Matching

Huanjing Yue (Tianjin University), Jingyu Yang (Tianjin University)

CodeRestorationSuper ResolutionGenerative Adversarial NetworkOptical FlowImage

🎯 What it does: In the real dual-camera super-resolution task, the KeDuSR network is proposed, which first aligns the central region of the reference image with the low-resolution image using a global + local alignment method. Then, it performs kernel-free matching between the corners and the central region of the low-resolution image to obtain reference information for the corner areas, and finally generates high-resolution results using adaptive fusion.

Keep the Faith: Faithful Explanations in Convolutional Neural Networks for Case-Based Reasoning

Tom Nuno Wolf (Technical University Munich), Christian Wachinger (Ludwig-Maximilians-University)

CodeClassificationExplainability and InterpretabilityConvolutional Neural NetworkImage

🎯 What it does: This paper studies the interpretability of ProtoPNet in case-based reasoning, proving that its commonly used pixel-level attribution maps do not satisfy interpretability axioms. Based on Shapley values, it proposes the ProtoPFaith method, providing realizable probability layer transformations and closed-form expectation/variance formulas, which can generate faithful pixel attribution maps for ProtoPNet.

Keypoint Fusion for RGB-D Based 3D Hand Pose Estimation

Xingyu Liu (Beijing University of Posts and Telecommunications), Jianxin Liao (Beijing University of Posts and Telecommunications)

CodePose EstimationTransformerMultimodalityPoint Cloud

🎯 What it does: Proposes the Keypoint-Fusion method, which utilizes RGB-Depth dual modalities for sparse keypoint aggregation and cross-modal fusion in 3D hand pose estimation.

KG-TREAT: Pre-training for Treatment Effect Estimation by Synergizing Patient Data with Knowledge Graphs

Ruoqi Liu (Ohio State University), Ping Zhang (Anytime.AI)

CodeGraph Neural NetworkTransformerSupervised Fine-TuningGraphBiomedical DataElectronic Health Records

🎯 What it does: KG-TREAT proposes a pre-training and fine-tuning framework that combines large-scale observational patient data with a medical knowledge graph for treatment effect estimation.

Knowledge Enhanced Representation Learning for Drug Discovery

Thanh Lam Hoang (IBM Research), Vanessa Lopez (IBM Research)

CodeRepresentation LearningDrug DiscoveryGraph Neural NetworkMultimodalityGraphBiomedical Data

🎯 What it does: A multimodal knowledge graph containing seven major public data sources (approximately 30 million triples) was constructed and released, and drug and protein embeddings were obtained by pre-training a graph neural network based on this graph.

Knowledge Graph Error Detection with Contrastive Confidence Adaption

Xiangyu Liu (Nanjing University), Wei Hu (Nanjing University)

CodeAnomaly DetectionTransformerContrastive LearningGraph

🎯 What it does: A knowledge graph error detection model named CCA is proposed, which reconstructs triples by jointly using text (BERT) and graph structure (Transformer), and combines interactive contrastive learning with adaptive confidence dynamic constraint training.

Knowledge Graph Prompting for Multi-Document Question Answering

Yu Wang (Vanderbilt University), Tyler Derr (Vanderbilt University)

CodeTransformerLarge Language ModelPrompt EngineeringTextMultimodalityRetrieval-Augmented Generation

🎯 What it does: This paper addresses the multi-document question answering (MD-QA) task by proposing the use of knowledge graphs (KG) to construct a graph traversal agent driven by LLMs for context retrieval and reasoning, thereby improving answer quality.

Knowledge-Aware Explainable Reciprocal Recommendation

Kai-Huang Lai (Sun Yat-sen University), Min Chen (South China University of Technology)

CodeRecommendation SystemExplainability and InterpretabilityRecurrent Neural NetworkGraph Neural NetworkTabular

🎯 What it does: A knowledge graph-driven, interpretable bidirectional recommendation system called KAERR is proposed to address the sparsity problem in bidirectional recommendations, encoding and integrating from the perspectives of candidates and positions using meta-paths.

Knowledge-Enhanced Historical Document Segmentation and Recognition

En-Hao Gao (Nanjing University), Wang-Zhou Dai (Nanjing University)

CodeRecognitionSegmentationConvolutional Neural NetworkImage

🎯 What it does: In this work, the authors propose the KESAR method, which utilizes an inductive learning framework to embed knowledge into segmentation and recognition models for character segmentation and recognition of historical document images.

KPA-Tracker: Towards Robust and Real-Time Category-Level Articulated Object 6D Pose Tracking

Liu Liu (Hefei University of Technology), Meng Wang (University of Science and Technology of China)

CodeObject TrackingPose EstimationVideoPoint Cloud

🎯 What it does: This paper proposes KPA-Tracker, a category-level joint object 6D position tracking framework based on 3D keypoints, capable of tracking the pose of each rigid part in online real-time scenes.

Label-Efficient Few-Shot Semantic Segmentation with Unsupervised Meta-Training

Jianwu Li (Beijing Institute of Technology), Tianfei Zhou (Nanjing University of Science and Technology)

CodeSegmentationMeta LearningTransformerImage

🎯 What it does: Utilize self-supervised pixel embeddings for pixel clustering under unsupervised conditions, automatically construct pseudo meta-tasks, and train few-shot semantic segmentation models;

LAMM: Label Alignment for Multi-Modal Prompt Learning

Jingsheng Gao (Shanghai Jiao Tong University), Yuzhuo Fu (Southeast University)

CodeClassificationDomain AdaptationKnowledge DistillationPrompt EngineeringVision Language ModelContrastive LearningImageMultimodality

🎯 What it does: This paper proposes a label alignment method called LAMM, which dynamically learns the embeddings of categories in downstream tasks, significantly improving the performance of multimodal prompt learning in few-shot, cross-domain, and incremental learning scenarios.

LaneGraph2Seq: Lane Topology Extraction with Language Model via Vertex-Edge Encoding and Connectivity Enhancement

Renyuan Peng (Fudan University), Li Zhang (Fudan University)

CodeAutonomous DrivingTransformerLarge Language ModelGraph

🎯 What it does: Proposes LaneGraph2Seq, a method for sequential prediction of lane graphs using a Transformer language model.

Language-Guided Transformer for Federated Multi-Label Classification

I-Jieh Liu (National Taiwan University), Yu-Chiang Frank Wang (NVIDIA)

CodeClassificationFederated LearningTransformerImage

🎯 What it does: A federated multi-label classification framework FedLGT based on language-guided Transformer is proposed, which can utilize the label association information of clients for local training in multi-label tasks and guide local learning through global model knowledge.

Large Language Models Are Neurosymbolic Reasoners

Meng Fang (University of Liverpool), Jun Wang (University College London)

CodeTransformerLarge Language ModelPrompt EngineeringText

🎯 What it does: Exploring the application of LLM as a neural symbolic reasoner in text games, designing LLM agents to interact with external symbolic modules to complete symbolic tasks.

Large Occluded Human Image Completion via Image-Prior Cooperating

Hengrun Zhao (Dalian University of Technology), Lijun Wang (Dalian University of Technology)

CodeRestorationSegmentationTransformerGenerative Adversarial NetworkImage

🎯 What it does: This paper proposes a two-stage 'Image-Prior Collaborative Completion' framework to simultaneously recover images and human segmentation priors in human images with large occlusions, significantly improving the reconstruction quality of occluded human areas.

Large-Scale Multi-Robot Coverage Path Planning via Local Search

Jingtao Tang (Simon Fraser University), Hang Ma (Simon Fraser University)

CodeOptimizationRobotic IntelligenceSimultaneous Localization and MappingGraph

🎯 What it does: A new local search-based multi-robot coverage path planning framework LS-MCPP is proposed, and an Extended-STC (ESTC) algorithm that can directly search on the decomposed graph is designed.

LatestEval: Addressing Data Contamination in Language Model Evaluation through Dynamic and Time-Sensitive Test Construction

Yucheng Li (University of Surrey), Chenghua Lin (University of Manchester)

CodeTransformerLarge Language ModelPrompt EngineeringTextBenchmark

🎯 What it does: This paper presents LatestEval, an automatic benchmark for reading comprehension evaluation that constructs the latest text while avoiding data contamination.

LaViP: Language-Grounded Visual Prompting

Nilakshan Kunananthaseelan (Monash University), Mehrtash Harandi (Monash University)

CodeClassificationRecognitionDomain AdaptationTransformerPrompt EngineeringVision Language ModelImageMultimodality

🎯 What it does: This paper proposes a language-guided visual prompting method called LaViP, which generates language-based input perception visual prompts at the input end of the visual encoder, enabling downstream task transfer of VLM without modifying model parameters.

Layer-Wise Representation Fusion for Compositional Generalization

Yafang Zheng (Xiamen University), Xiaodong Shi (Xiamen University)

CodeRepresentation LearningTransformerText

🎯 What it does: This paper proposes a Layer-wise Representation Fusion (LRF) framework, which introduces a fuse-attention module in each layer of the encoder and decoder of the Transformer, gradually fusing the syntactic and semantic information from the previous layers to address the representation entanglement (RE) problem that arises in the top layer of the model, thereby enhancing the combinatorial generalization ability of sequence-to-sequence models.

LDMVFI: Video Frame Interpolation with Latent Diffusion Models

Duolikun Danier (University of Bristol), David Bull (University of Bristol)

CodeRestorationGenerationData SynthesisDiffusion modelAuto EncoderVideo

🎯 What it does: A method for video frame interpolation using latent diffusion models is proposed, treating VFI as a conditional generation task.

LDS2AE: Local Diffusion Shared-Specific Autoencoder for Multimodal Remote Sensing Image Classification with Arbitrary Missing Modalities

Jiahui Qu (Xidian University), Yufei Yang (Xidian University)

CodeClassificationTransformerDiffusion modelAuto EncoderImageMultimodality

🎯 What it does: A Local Diffusion Shared-Specific Autoencoder (LDS AE) has been designed and implemented, capable of completing multi-modal remote sensing image classification tasks with any missing modality using only one model.

Learn How to See: Collaborative Embodied Learning for Object Detection and Camera Adjusting

Lingdong Shen (University of Chinese Academy of Sciences), Zichen Wang (University of Chinese Academy of Sciences)

CodeObject DetectionTransformerReinforcement LearningImage

🎯 What it does: Proposes the Student-Teacher Framework (STF), which utilizes replay buffer, teacher rewards, and GPT student networks to achieve collaborative learning of camera actions, thereby enhancing active object detection performance.

Learn to Follow: Decentralized Lifelong Multi-Agent Pathfinding via Planning and Learning

Alexey Skrynnik (AIRI), Aleksandr Panov (AIRI)

CodeOptimizationRobotic IntelligenceRecurrent Neural NetworkReinforcement LearningGraph

🎯 What it does: This paper studies decentralized lifelong multi-agent path planning (LMAPF) and proposes the FOLLOWER method, which combines heuristic planning with reinforcement learning.

Learning Coalition Structures with Games

Yixuan Even Xu (Tsinghua University), Fei Fang (Carnegie Mellon University)

CodeReinforcement Learning

🎯 What it does: An important but previously overlooked problemβ€”Coalition Structure Learning (CSL)β€”is proposed and studied by designing a series of games to infer the coalition structure among agents.

Learning Deformable Hypothesis Sampling for Accurate PatchMatch Multi-View Stereo

Hongjie Li (Wuhan University), Hanjiang Xiong (Wuhan University)

CodeDepth EstimationImage

🎯 What it does: Proposes a learnable Deformable Hypothesis Sampler embedded in the PatchMatch MVS framework to enhance depth estimation accuracy.

Learning Diffusions under Uncertainty

Hao Huang (Wuhan University), Chuanhui Yang (Ant Group)

CodeOptimizationGraph Neural NetworkGraph

🎯 What it does: The study infers the structure of diffusion networks given only the infection probabilities of nodes and proposes an iterative maximization algorithm based on nonlinear regression called PIND.

Learning Discrete-Time Major-Minor Mean Field Games

Kai Cui (Technische Universitat Darmstadt), Heinz Koeppl (Technische Universitat Darmstadt)

CodeReinforcement LearningSequential

🎯 What it does: A discrete-time multi-leader-follower equilibrium game (M3FG) framework is proposed for scalable analysis of multi-player non-cooperative games that include dominant players and public noise.

Learning Diverse Risk Preferences in Population-Based Self-Play

Yuhua Jiang (Tsinghua University), Qianchuan Zhao (Tsinghua University)

CodeReinforcement Learning

🎯 What it does: A self-play method based on risk preference learning is proposedβ€”Risk-Sensitive PPO (RPPO), which is embedded into a Population-Based Self-Play framework to obtain RPBT, aimed at generating diverse and robust playing strategies.

Learning Encodings for Constructive Neural Combinatorial Optimization Needs to Regret

Rui Sun (Southern University of Science and Technology), Zhenkun Wang (Southern University of Science and Technology)

CodeOptimizationReinforcement LearningTabular

🎯 What it does: A general plugin called LCH-Regret is proposed, which introduces a regret mechanism into Learning Constructive Heuristics (LCH);

Learning from Ambiguous Demonstrations with Self-Explanation Guided Reinforcement Learning

Yantian Zha (Arizona State University), Subbarao Kambhampati (Arizona State University)

CodeRobotic IntelligenceReinforcement LearningGenerative Adversarial NetworkSequential

🎯 What it does: A self-explanatory guided RL learning framework SERLfD is proposed, which alleviates the negative impact of ambiguous demonstrations on RL learning by identifying task-related relationships through a self-explanatory network.

Learning from History: Task-agnostic Model Contrastive Learning for Image Restoration

Gang Wu (Harbin Institute of Technology), Xianming Liu (Harbin Institute of Technology)

CodeRestorationSuper ResolutionContrastive LearningImage

🎯 What it does: Utilize the target model itself to generate negative samples for retraining existing image restoration models through model contrastive learning;

Learning Generalized Segmentation for Foggy-Scenes by Bi-directional Wavelet Guidance

Qi Bi (University of Amsterdam), Theo Gevers (University of Amsterdam)

CodeSegmentationDomain AdaptationAutonomous DrivingTransformerImage

🎯 What it does: A foggy scene semantic segmentation method is proposed under the domain generalization setting, utilizing a bidirectional wavelet-guided self-attention mechanism (BWG) to separate low-frequency content from high-frequency urban style and fog style, and training only on clear images to achieve good generalization capability for any unknown foggy scenes.

Learning Invariant Inter-pixel Correlations for Superpixel Generation

Sen Xu (Beijing Jiaotong University), Lixin Liao (DaoAI Robotics Inc.)

CodeSegmentationGenerationConvolutional Neural NetworkImage

🎯 What it does: The Content Disentangle Superpixel (CDS) algorithm is proposed, which utilizes auxiliary modalities to separate the style noise of training data, thereby learning pixel correlations that are independent of image content and have better generalization capabilities, used for generating high-quality superpixels.

Learning Multi-Modal Cross-Scale Deformable Transformer Network for Unregistered Hyperspectral Image Super-resolution

Wenqian Dong (Xidian University), Shaoxiong Hou (Xidian University)

CodeRestorationSuper ResolutionTransformerImage

🎯 What it does: A multi-modal cross-scale deformable transformation network (M2DTN) is proposed to achieve super-resolution of unaligned hyperspectral images.

Learning Multimodal Volumetric Features for Large-Scale Neuron Tracing

Qihua Chen (University of Science and Technology of China), Feng Wu (University of Science and Technology of China)

CodeSegmentationRepresentation LearningConvolutional Neural NetworkContrastive LearningImagePoint Cloud

🎯 What it does: A large-scale FlyTracing dataset is constructed, utilizing connection-aware contrastive learning to learn dense embeddings of EM images, and integrating these embeddings with 3D morphological representations (point clouds/voxels) to predict connections between over-segmented neuronal fragments, thereby reducing manual correction work.

Learning Not to Regret

David SychrovskΓ½ (Charles University), Martin Schmid (EquiLibre Technologies)

CodeOptimizationMeta LearningReinforcement Learning from Human FeedbackRecurrent Neural NetworkReinforcement LearningTabularSequential

🎯 What it does: This paper proposes a 'learning to avoid regret' framework for games sampled from a distribution, utilizing meta-learning methods to automatically generate regret-avoiding algorithms for that distribution, achieving rapid convergence in matrix games and river card poker distributions.

Learning Persistent Community Structures in Dynamic Networks via Topological Data Analysis

Dexu Kong, Yang Li (Shenzhen International Graduate School Tsinghua University)

CodeRepresentation LearningGraph Neural NetworkAuto EncoderGraph

🎯 What it does: An end-to-end dynamic community detection framework is proposed, combining a Matrix Factorization Clustering module (MFC) and a Topological Regularization module (TopoReg), to enhance temporal consistency and clustering accuracy by maintaining the persistent topology of community networks.

Learning Representations on the Unit Sphere: Investigating Angular Gaussian and Von Mises-Fisher Distributions for Online Continual Learning

Nicolas Michel (Gustave Eiffel University), Jean-FranΓ§ois Bercher (Gustave Eiffel University)

CodeRepresentation LearningConvolutional Neural NetworkImage

🎯 What it does: A representation learning method based on maximum a posteriori estimation is proposed, using angular Gaussian distribution and von Mises-Fisher distribution on the unit sphere to learn fixed-direction representations and achieve online continual learning with memory replay.

Learning Robust Rationales for Model Explainability: A Guidance-Based Approach

Shuaibo Hu (Hefei University of Technology), Kui Yu (Hefei University of Technology)

CodeExplainability and InterpretabilityText

🎯 What it does: A selection-prediction framework G-RAT based on a guiding module is proposed to improve the text selective rationalization model, addressing its degradation and failure issues.

Learning Safe Action Models with Partial Observability

Hai S. Le (Washington University in St. Louis), Roni Stern (Ben Gurion University of the Negev)

CodeOptimizationSafty and PrivacyRobotic IntelligenceSequentialBenchmark

🎯 What it does: This paper proposes two algorithms, PI-SAM and EPI-SAM, for safely learning PDDL action models from partially observable trajectories, ensuring that the generated plans are executable and can achieve the goals.

Learning the Causal Structure of Networked Dynamical Systems under Latent Nodes and Structured Noise

Augusto Santos (Instituto de Telecomunicacoes), JosΓ© M. F. Moura (Carnegie Mellon University)

CodeGraphTime Series

🎯 What it does: Learning the hidden causal network structure in linear network dynamical systems with only partial node observations and the presence of colored noise.

Learning Time Slot Preferences via Mobility Tree for Next POI Recommendation

Tianhao Huang (Nankai University), Xiaojie Yuan (Nankai University)

CodeRecommendation SystemTransformerSequential

🎯 What it does: This paper proposes a Mobility Tree based on a hierarchical tree structure and designs the MTNet model, which utilizes multi-granularity time slot nodes to learn users' next location preferences at different time periods.

Learning to Learn in Interactive Constraint Acquisition

Dimosthenis Tsouros (KU Leuven), Tias Guns (KU Leuven)

CodeOptimizationMeta LearningTabularBenchmark

🎯 What it does: This study investigates the introduction of statistical machine learning methods into Constraint Acquisition (CA) to reduce the number of required queries.

Learning to Manipulate Artistic Images

Wei Guo (Zhejiang University), Qian Zheng (Zhejiang University)

CodeImage TranslationGenerationImage

🎯 What it does: A mask-based zero-shot artistic image manipulation network SIM-Net is proposed, capable of modifying artistic images in any style without using semantic labels or training data.

Learning to Rank in Generative Retrieval

Yongqi Li (Hong Kong Polytechnic University), Wenjie Li (Microsoft)

CodeRetrievalTransformerLarge Language ModelSupervised Fine-TuningText

🎯 What it does: This paper proposes the LTRGR framework, which adds a learning-to-rank phase on top of the generative retrieval model, allowing the model to directly optimize the ranking of retrieval results.

Learning Visual Abstract Reasoning through Dual-Stream Networks

Kai Zhao (Beijing Normal University), Bailu Si (Beijing Normal University)

CodeClassificationExplainability and InterpretabilityConvolutional Neural NetworkTransformerImage

🎯 What it does: This paper proposes a Dual-stream Reasoning Network (DRNet) that extracts image features by simultaneously using two branches: CNN (for processing local/object information) and ViT (for processing global/spatial information), and learns abstract rules in a rule extractor to solve visual abstract reasoning tasks of Raven’s Progressive Matrices (RPM).

Learning with Noisy Labels Using Hyperspherical Margin Weighting

Shuo Zhang (Southeast University), Chengyu Liu (Southeast University)

CodeClassificationData-Centric LearningImage

🎯 What it does: The IAM metric and HMW weighting method are proposed to improve the robustness of learning on datasets with noisy labels.

Learning-Augmented Online Algorithm for Two-Level Ski-Rental Problem

Keyuan Zhang (Virginia Tech), Bo Ji (Virginia Tech)

CodeOptimizationTabularTime Series

🎯 What it does: A robust online algorithm RDTSR and a learning-enhanced algorithm LADTSR based on machine learning predictions are proposed and implemented for the two-tier ski rental problem, addressing optimal cost decisions under various payment options (rental, single purchase, combination purchase).

LERE: Learning-Based Low-Rank Matrix Recovery with Rank Estimation

Zhengqin Xu (Shanghai Jiao Tong University), Xiaokang Yang (Shanghai Jiao Tong University)

CodeRestorationOptimizationVideo

🎯 What it does: A learning-driven low-rank matrix recovery method called LERE is proposed, which first estimates the matrix rank using a new R_GDE rule, and then iteratively solves on randomly sampled submatrices using a 17-step FRMNN deep network, recovering the complete low-rank matrix through the correlation of row/column submatrices; this process does not require prior rank information and can handle sparse noise matrices with large condition numbers.

Let All Be Whitened: Multi-Teacher Distillation for Efficient Visual Retrieval

Zhe Ma (Zhejiang University), Lei Yang (Ant Group)

CodeRetrievalComputational EfficiencyKnowledge DistillationConvolutional Neural NetworkContrastive LearningImageVideo

🎯 What it does: Utilizing a multi-teacher distillation framework (Whiten-MTD) to transfer knowledge from various large pre-trained retrieval models to a lightweight student model, achieving efficient visual retrieval.

Let There Be Sound: Reconstructing High Quality Speech from Silent Videos

Ji-Hoon Kim (Korea Advanced Institute of Science and Technology), Joon Son Chung (Korea Advanced Institute of Science and Technology)

CodeRecognitionGenerationData SynthesisConvolutional Neural NetworkTransformerFlow-based ModelGenerative Adversarial NetworkVideoAudio

🎯 What it does: This paper proposes a system for reconstructing high-quality speech from silent videos (Lip-to-Speech) by mapping lip movements to speech.

LF-ViT: Reducing Spatial Redundancy in Vision Transformer for Efficient Image Recognition

Youbing Hu (Harbin Institute of Technology), Zhijun Li (Harbin Institute of Technology)

CodeClassificationRecognitionComputational EfficiencyTransformerImage

🎯 What it does: A two-stage Vision Transformer framework called LF-ViT is proposed, which first performs localization on downsampled images. If the confidence is insufficient, it uses Neighborhood Global Class Attention (NGCA) to locate class-discriminative regions in the full-resolution image, and then continues inference only in that region, achieving efficient image classification.

LGMRec: Local and Global Graph Learning for Multimodal Recommendation

Zhiqiang Guo (Huazhong University of Science and Technology), Bin Ruan (Wuhan Digital Engineering Institute)

CodeRecommendation SystemGraph Neural NetworkContrastive LearningMultimodality

🎯 What it does: This paper proposes a new multimodal recommendation framework LGMRec, which can simultaneously capture users' local interests and global interests.

LimeAttack: Local Explainable Method for Textual Hard-Label Adversarial Attack

Hai Zhu (University of Science and Technology of China), Kai Liu (Lazada)

CodeExplainability and InterpretabilityAdversarial AttackConvolutional Neural NetworkRecurrent Neural NetworkTransformerText

🎯 What it does: A text adversarial attack method based on hard labels, LimeAttack, is proposed. This method estimates the importance of words using the local interpretable model-agnostic explanations (LIME), and combines beam search and semantic similarity sampling rules to generate high-quality adversarial samples under a very limited query budget.

Limitations of Face Image Generation

Harrison Rosenberg (University of Wisconsin Madison), Ramya Korlakai Vinayak (University of Wisconsin Madison)

CodeRecognitionGenerationData SynthesisDiffusion modelImage

🎯 What it does: This study proposes an end-to-end framework that utilizes text-to-image diffusion models (Stable Diffusion v2.1 and Realistic Vision) combined with SEGA to generate a diverse facial dataset with fine-grained social attributes (race, gender, age, beard, glasses, smile), and conducts quantitative evaluation, facial recognition validation, and user experience research on the generated results.

Limited Query Graph Connectivity Test

Mingyu Guo (University of Adelaide), Hung Nguyen (University of Adelaide)

CodeOptimizationGraph Neural NetworkReinforcement LearningGraph

🎯 What it does: A Limited Query Graph Connectivity Test model is proposed, along with a scalable exact algorithm and a heuristic method based on query limits that can be solved on large-scale graphs.

Linear-Time Algorithms for Front-Door Adjustment in Causal Graphs

Marcel WienΓΆbst, Maciej LiΕ›kiewicz (University of Luebeck)

CodeGraph

🎯 What it does: Developed a linear time algorithm for finding front-door adjustment sets and their minimized versions, and implemented multi-language code;

Locality Preserving Refinement for Shape Matching with Functional Maps

Yifan Xia (Wuhan University), Jiayi Ma (Wuhan University)

CodeMesh

🎯 What it does: A two-stage local consistency point-to-point mapping refinement method called LOPR is proposed to eliminate outliers and improve correspondence accuracy in non-rigid shape matching.

LogFormer: A Pre-train and Tuning Pipeline for Log Anomaly Detection

Hongcheng Guo (Cloudwise Research), Qi Tian (Huawei)

CodeAnomaly DetectionTransformerTextChain-of-Thought

🎯 What it does: Proposes the LogFormer framework, which includes the Log-Attention module and a two-stage process of pre-training + adapter fine-tuning for cross-domain log anomaly detection.

LogoStyleFool: Vitiating Video Recognition Systems via Logo Style Transfer

Yuxin Cao (Tsinghua University), Jin Lu (CSIRO Data61)

CodeRecognitionAdversarial AttackRecurrent Neural NetworkReinforcement LearningVideo

🎯 What it does: This study proposes a black-box video attack framework called LogoStyleFool, which deceives video recognition models by perturbing stylized logos overlaid in the corners of videos.

Long-Tailed Learning as Multi-Objective Optimization

Weiqi Li (Tianjin University), Wei Feng

CodeOptimizationImageBenchmark

🎯 What it does: This paper proposes a method to transform long-tail classification tasks into multi-objective optimization problems, and achieves collaborative updates of gradients for head and tail categories through Gradient Balancing Grouping (GBG).

Long-Tailed Partial Label Learning by Head Classifier and Tail Classifier Cooperation

Yuheng Jia (Southeast University), Min-Ling Zhang (Southeast University)

CodeClassificationConvolutional Neural NetworkImage

🎯 What it does: A long-tail biased label learning method is proposed, which constructs a head classifier and a tail classifier to work collaboratively, utilizing soft pseudo-labels and class distribution estimation to achieve high-quality label disambiguation.

Low Category Uncertainty and High Training Potential Instance Learning for Unsupervised Domain Adaptation

Xinyu Zhang (Jilin University), Shuai LΓΌ

CodeDomain AdaptationContrastive LearningImage

🎯 What it does: An unsupervised domain adaptation method based on low category uncertainty and high training potential instance learning (LUHP) is proposed.

Low-Light Face Super-resolution via Illumination, Structure, and Texture Associated Representation

Chenyang Wang (Harbin Institute of Technology), Xianming Liu (Harbin Institute of Technology)

CodeRestorationSuper ResolutionConvolutional Neural NetworkTransformerDiffusion modelImage

🎯 What it does: For the super-resolution task of low-resolution facial images under low light conditions, a joint low-light compensation and facial structure recovery framework (IC-FSRNet) is proposed, and based on this, a detail enhancement network (DENet) using a diffusion model is further employed to improve image quality.

LRS: Enhancing Adversarial Transferability through Lipschitz Regularized Surrogate

Tao Wu (Missouri University of Science and Technology), Donald C. Wunsch II (Missouri University of Science and Technology)

CodeAdversarial AttackConvolutional Neural NetworkSupervised Fine-TuningImage

🎯 What it does: This paper proposes the Lipschitz Regularized Surrogate (LRS) method, which fine-tunes a pre-trained surrogate model by applying first or second-order Lipschitz regularization to enhance the transferability of adversarial examples, thereby significantly improving the attack success rate without altering existing transfer-based black-box attacks.

M2Doc: A Multi-Modal Fusion Approach for Document Layout Analysis

Ning Zhang (South China University of Technology), Lianwen Jin (Platform of AI)

CodeObject DetectionSegmentationConvolutional Neural NetworkLarge Language ModelImageTextMultimodalityPhysics Related

🎯 What it does: This paper proposes a pluggable multimodal fusion method M2Doc, which transforms existing unimodal document layout analysis detectors into multimodal detectors, significantly improving layout detection accuracy.

M3D: Dataset Condensation by Minimizing Maximum Mean Discrepancy

Hansong Zhang (Institute of Information Engineering, Chinese Academy of Sciences), Shiming Ge (Shanghai University)

CodeClassificationData SynthesisOptimizationGenerative Adversarial NetworkImage

🎯 What it does: This paper studies the task of dataset condensation and proposes a new method called M3D based on Maximum Mean Discrepancy (MMD), which achieves higher-order moment alignment in Reproducing Kernel Hilbert Space (RKHS) to generate more informative synthetic samples.

M3SOT: Multi-Frame, Multi-Field, Multi-Space 3D Single Object Tracking

Jiaming Liu (Xidian University), Can Qin (Northeastern University)

CodeObject TrackingAutonomous DrivingTransformerPoint Cloud

🎯 What it does: A 3D single-object tracking framework named M3SOT is proposed, which utilizes multi-frame, different receptive fields, and multi-task space to fully exploit the spatiotemporal information of point clouds, enhancing tracking accuracy and robustness in sparse point clouds.

Machine Learning-Powered Combinatorial Clock Auction

Ermis Nikiforos Soumalias (University of Zurich), Sven Seuken (University of Zurich)

CodeOptimizationTabularBenchmark

🎯 What it does: In iterative combinatorial auctions, machine learning models are used to approximate bidders' value functions, and information is obtained through demand queries rather than value queries.

Machine-Created Universal Language for Cross-Lingual Transfer

Yaobo Liang (Microsoft Research Asia), Nan Duan (Microsoft Research Asia)

CodeTransformerContrastive LearningText

🎯 What it does: A general-purpose language MUL was designed and implemented, which is automatically generated by machines and used as a cross-language intermediate language for cross-language transfer;

Make Lossy Compression Meaningful for Low-Light Images

Shilv Cai (Huazhong University of Science and Technology), Xu Zou (Peking University)

CodeRestorationCompressionTransformerAuto EncoderImage

🎯 What it does: An end-to-end joint low-light image compression and enhancement model is proposed, which completes low-light enhancement directly during the compression process, rather than the traditional methods of compressing first and then enhancing or enhancing first and then compressing.

Make Prompts Adaptable: Bayesian Modeling for Vision-Language Prompt Learning with Data-Dependent Prior

Youngjae Cho (Korea Advanced Institute of Science and Technology), Il-Chul Moon (Korea Advanced Institute of Science and Technology)

CodeClassificationDomain AdaptationPrompt EngineeringVision Language ModelImageMultimodality

🎯 What it does: This paper proposes an Adaptive Particle Prompt Learning (APP) based on a Bayesian framework for prompt learning in visual-language pre-training models, addressing overfitting and distribution shift issues in few-shot learning.

Make RepVGG Greater Again: A Quantization-Aware Approach

Xiangxiang Chu (Meituan), Bo Zhang (Meituan)

CodeClassificationObject DetectionSegmentationConvolutional Neural NetworkImage

🎯 What it does: A quantization-friendly improved structure for RepVGG, named QARepVGG, is proposed and implemented, maintaining accuracy close to FP32 under INT8 inference.

Manifold-Based Verbalizer Space Re-embedding for Tuning-Free Prompt-Based Classification

Haochun Wang (Harbin Institute of Technology), Ting Liu (Harbin Institute of Technology)

CodeClassificationTransformerPrompt EngineeringContrastive LearningText

🎯 What it does: A completely parameter-free prompt-based classification method is proposed, which utilizes Local Linear Embedding with Intra-class Neighborhood Constraints (LLE-INC) to re-embed the [MASK] word vector space, and on this basis, optional contrastive learning can be used to enhance performance.

MAPTree: Beating β€œOptimal” Decision Trees with Bayesian Decision Trees

Colin Sullivan (Stanford University), Sebastian Thrun (Stanford University)

CodeClassificationOptimizationTabular

🎯 What it does: The MAPTree algorithm is proposed, which uses the AND/OR graph search method to find the maximum a posteriori decision tree on the BCART posterior distribution.

Mask-Homo: Pseudo Plane Mask-Guided Unsupervised Multi-Homography Estimation

Yasi Wang (Samsung Research China), Qiang Wang (Samsung Research China)

CodeTransformerOptical FlowImage

🎯 What it does: Proposes the Mask-Homo framework, achieving pseudo-plane mask-guided multi-Homography estimation to address alignment issues caused by depth differences among multiple planes.

MaskDiff: Modeling Mask Distribution with Diffusion Probabilistic Model for Few-Shot Instance Segmentation

Minh-Quan Le (University of Science), Minh-Triet Tran (University of Science)

CodeSegmentationDomain AdaptationDiffusion modelImage

🎯 What it does: Proposes the MaskDiff method, which utilizes a conditional diffusion probability model to model the distribution of binary masks in few-shot instance segmentation, achieving more robust mask generation.

MathAttack: Attacking Large Language Models towards Math Solving Ability

Zihao Zhou (Xi'an Jiaotong-Liverpool University), Kaizhu Huang (ShanghaiTech University)

CodeAdversarial AttackTransformerLarge Language ModelText

🎯 What it does: The MathAttack model is proposed, which utilizes logical entity recognition and word-level attack methods to assess the robustness of large language models' mathematical problem-solving abilities.

Maximizing the Success Probability of Policy Allocations in Online Systems

Artem Betlei (Criteo AI Lab), Benjamin Heymann (Criteo AI Lab)

CodeOptimizationTabular

🎯 What it does: A framework for bid strategy allocation at the user timeline level is proposed, with an optimization objective focused on 'success probability' rather than expected revenue, introducing the SuccessProbaMax algorithm.

MCA: Moment Channel Attention Networks

Yangbo Jiang (Zhejiang University), Nenggan Zheng (Zhejiang University)

CodeClassificationObject DetectionSegmentationConvolutional Neural NetworkImage

🎯 What it does: A channel attention mechanism based on higher-order moment aggregation, called MCA (Moment Channel Attention), is proposed, which enhances the network's expressive capability by utilizing statistical moment information.

Measuring Task Similarity and Its Implication in Fine-Tuning Graph Neural Networks

Renhong Huang (Zhejiang University), Yang Yang (FinVolution Group)

CodeGraph Neural NetworkContrastive LearningGraph

🎯 What it does: This study investigates the similarity between graph pre-training models and downstream tasks, proposing a task consistency metric and a Bridge-Tune fine-tuning strategy based on this metric.

MedBench: A Large-Scale Chinese Benchmark for Evaluating Medical Large Language Models

Yan Cai (East China Normal University), Liang He (East China Normal University)

CodeTransformerLarge Language ModelPrompt EngineeringTextBiomedical DataElectronic Health RecordsBenchmarkChain-of-Thought

🎯 What it does: MedBench is proposed β€” a large Chinese medical benchmark containing 40,041 questions, covering three stages of medical examinations (National Physician Qualification, Resident Physician Standardized Training, Physician Practice Qualification) as well as over 2,000 real electronic health record question-answer pairs, aimed at uniformly assessing the knowledge mastery and reasoning ability of large medical language models.

MedSegDiff-V2: Diffusion-Based Medical Image Segmentation with Transformer

Junde Wu (University of Oxford), Yanwu Xu (National University of Singapore)

CodeSegmentationTransformerDiffusion modelImageMultimodalityMagnetic Resonance ImagingComputed TomographyPositron Emission TomographyUltrasound

🎯 What it does: A diffusion model MedSegDiff-V2 that integrates Transformer has been developed for multimodal medical image segmentation.

MELO: Enhancing Model Editing with Neuron-Indexed Dynamic LoRA

Lang Yu (East China Normal University), Liang He (East China Normal University)

CodeTransformerLarge Language ModelSupervised Fine-TuningText

🎯 What it does: A model editing framework MELO based on neuron-indexed dynamic LoRA is proposed, which can achieve multi-attribute editing on LLMs and is easy to integrate.

MemoryBank: Enhancing Large Language Models with Long-Term Memory

Wanjun Zhong (Sun Yat-Sen University), Yanlin Wang (Sun Yat-Sen University)

CodeRetrievalTransformerLarge Language ModelSupervised Fine-TuningTextMultimodalityRetrieval-Augmented Generation

🎯 What it does: A long-term memory mechanism called MemoryBank was designed and implemented for large language models (LLM) and integrated into the AI companion chatbot SiliconFriend to enable retrieval, updating of historical conversations, and user profile construction.

MERGE: Fast Private Text Generation

Zi Liang (Xi'an Jiaotong University), Ziyang Zhou (Xi'an Jiaotong University)

CodeGenerationSafty and PrivacyComputational EfficiencyTransformerLarge Language ModelText

🎯 What it does: The MERGE framework is proposed to accelerate Transformer text generation in the MPC environment, addressing the slow issues of embedding queries and autoregressive generation.

MESED: A Multi-Modal Entity Set Expansion Dataset with Fine-Grained Semantic Classes and Hard Negative Entities

Yangning Li (Shenzhen International Graduate School Tsinghua University), Rui Zhang (Shenzhen International Graduate School Tsinghua University)

CodeRetrievalRepresentation LearningTransformerContrastive LearningImageTextMultimodality

🎯 What it does: This paper proposes the Multi-modal Entity Set Expansion (MESE) task, which utilizes text and image representations of entities and achieves entity expansion through self-supervised pre-training and deep modal fusion.

Meta-Learning-Based Adaptive Stability Certificates for Dynamical Systems

Amit Jena (Texas A&M University), Le Xie (Texas A&M University)

CodeMeta LearningTime Series

🎯 What it does: This paper proposes a meta-learning based neural Lyapunov function (meta-NLF) that can quickly adapt to new dynamic models and provide stability region (ROA) estimates when system parameters change over time.

MetaRLEC: Meta-Reinforcement Learning for Discovery of Brain Effective Connectivity

Zuozhen Zhang (Beijing University of Technology), Jinduo Liu (Beijing University of Technology)

CodeMeta LearningRecurrent Neural NetworkTransformerReinforcement LearningTime SeriesBiomedical DataMagnetic Resonance Imaging

🎯 What it does: A method for discovering effective brain connectivity (EC) based on meta reinforcement learning, called MetaRLEC, is proposed, which utilizes the actor-critic framework and a meta-critic to enhance learning efficiency on small sample high noise fMRI data.

MFABA: A More Faithful and Accelerated Boundary-Based Attribution Method for Deep Neural Networks

Zhiyu Zhu (University of Sydney), Kim-Kwang Raymond Choo (University of Texas at San Antonio)

CodeClassificationExplainability and InterpretabilityComputational EfficiencyAdversarial AttackConvolutional Neural NetworkImage

🎯 What it does: A more faithful and faster boundary-based attribution method, MFABA, is proposed, utilizing second-order Taylor expansion and adversarial attack gradients for efficient feature attribution.

MGNet: Learning Correspondences via Multiple Graphs

Dai Luanyuan, Jinhui Tang (Nanyang Technological University)

CodePose EstimationGraph Neural NetworkImage

🎯 What it does: This study focuses on outlier removal in sparse correspondences and proposes MGNet, which simultaneously constructs implicit and explicit local graphs and introduces Graph Soft Degree Attention to achieve high-quality correspondence filtering.

MICA: Towards Explainable Skin Lesion Diagnosis via Multi-Level Image-Concept Alignment

Yequan Bie (Hong Kong University of Science and Technology), Hao Chen (Hong Kong University of Science and Technology)

CodeClassificationExplainability and InterpretabilityConvolutional Neural NetworkLarge Language ModelContrastive LearningImageMultimodality

🎯 What it does: A multi-modal interpretable skin disease diagnosis framework MICA is proposed, which achieves interpretable diagnosis through multi-layer image-concept alignment.

MIND: Multi-Task Incremental Network Distillation

Jacopo Bonato (Leonardo Labs), Alessandro Nicolosi (Leonardo Labs)

CodeKnowledge DistillationImage

🎯 What it does: Designed and implemented MIND (Multi-Task Incremental Network Distillation), a replay-free, parameter-isolation-based incremental learning framework that achieves continuous learning by training a brand new model for each new task or using self-distillation, and then distilling its knowledge into the current sub-network.

Minibatch Stochastic Three Points Method for Unconstrained Smooth Minimization

Soumia Boucherouite (Mohammed VI Polytechnic University), El Houcine Bergou (Mohammed VI Polytechnic University)

CodeOptimizationAdversarial AttackImageTabular

🎯 What it does: This paper proposes the Minibatch Stochastic Three Points (MiSTP) zero-order optimization method, which updates parameters using random search directions and sub-batch objective function approximations, and provides theoretical complexity and experimental validation in both non-convex and convex scenarios.

Minimal Macro-Based Rewritings of Formal Languages: Theory and Applications in Ontology Engineering (and Beyond)

Christian Kindermann (Stanford University), Uli Sattler (University of Manchester)

CodeOptimizationComputational EfficiencyBiomedical Data

🎯 What it does: A finite form language rewriting framework based on nested grammar macros is proposed, providing polynomial time algorithms for various problems and applying it to the minimization rewriting of large biomedical OWL ontologies.

Mining Fine-Grained Image-Text Alignment for Zero-Shot Captioning via Text-Only Training

Longtian Qiu (ShanghaiTech University), Xuming He (ShanghaiTech University)

CodeGenerationRetrievalTransformerLarge Language ModelContrastive LearningImageTextMultimodality

🎯 What it does: A zero-shot image captioning framework based on CLIP, called MacCap, is proposed. It utilizes text data to train an adapter that only uses text, enabling the model to generate natural language descriptions directly from CLIP image embeddings, and extends this framework to zero-shot VQA.

Mining Gaze for Contrastive Learning toward Computer-Assisted Diagnosis

Zihao Zhao (ShanghaiTech University), Dinggang Shen (Shanghai United Imaging Intelligence Co., Ltd.)

CodeClassificationRepresentation LearningContrastive LearningImageBiomedical DataMagnetic Resonance Imaging

🎯 What it does: A comparative learning pre-training method based on radiologists' eye movement data, McGIP, is proposed, which constructs positive sample pairs using eye movement similarity.

Mitigating Idiom Inconsistency: A Multi-Semantic Contrastive Learning Method for Chinese Idiom Reading Comprehension

Mingmin Wu (Huazhong Agricultural University), Ying Sha (Huazhong Agricultural University)

CodeContrastive LearningText

🎯 What it does: This paper proposes a Multi-Semantic Contrastive Learning Model (MSCLM) to address the issues of metaphor inconsistency and contextual inconsistency in the reading comprehension of Chinese idioms.