arXivSub Start free trial

AAAI 2025 Papers with Code β€” Page 12

AAAI Conference on Artificial Intelligence Β· 1442 papers

Rethinking Transformer-Based Blind-Spot Network for Self-Supervised Image Denoising

Junyi Li (Harbin Institute of Technology), Wangmeng Zuo (Harbin Institute of Technology)

CodeRestorationKnowledge DistillationTransformerImage

🎯 What it does: A Transformer-based Blind Spot Network (TBSN) is proposed for self-supervised image denoising.

Rethinking U-Net: Task-Adaptive Mixture of Skip Connections for Enhanced Medical Image Segmentation

Zichen Luo (Tianjin University), Biao Sun (Tianjin University)

CodeSegmentationConvolutional Neural NetworkMixture of ExpertsImageBiomedical DataMagnetic Resonance Imaging

🎯 What it does: A TA-MoSC module is proposed based on U-Net, treating skip connections as a task allocation problem, and dynamically assigning appropriate multi-scale features for different decoding stages through a sparse Mixture-of-Experts router, thus achieving adaptive skip connections.

RETQA: A Large-Scale Open-Domain Tabular Question Answering Dataset for Real Estate Sector

Zhensheng Wang (Beijing Normal University), Weijia Jia (Beijing Normal University)

CodeTransformerLarge Language ModelSupervised Fine-TuningTabularFinance Related

🎯 What it does: The RETQA dataset and SLUTQA framework are proposed for open-domain long table question answering in the real estate industry.

RETRACTED: GEONet: Global Enhancement and Optimization Network for Lane Detection

Suyang Xi (Xiamen University), Xiaoxuan Liang (University of Massachusetts Amherst)

CodeObject DetectionAutonomous DrivingConvolutional Neural NetworkTransformerContrastive LearningImage

🎯 What it does: A global enhancement and optimization network named GEONet is proposed for lane detection in complex scenarios, combining a Global Feature Extraction Module (GFEM) and a Top-level Supplement Module (TTSM), and incorporating Whitened Batch Normalization (WBN), Whitened Contrastive Learning (WCL), as well as novel Angle Loss and GRIoU Loss to improve detection accuracy and robustness.

Retrieval-Augmented Dynamic Prompt Tuning for Incomplete Multimodal Learning

Jian Lang (University of Electronic Science and Technology of China), Fan Zhou (Kash Institute of Electronics and Information Industry)

CodeGenerationRetrievalTransformerPrompt EngineeringMultimodalityRetrieval-Augmented Generation

🎯 What it does: A retrieval-augmented dynamic prompt tuning framework RAGPT is designed to address the issue of missing modalities;

Retrieval-Augmented Visual Question Answering via Built-in Autoregressive Search Engines

Xinwei Long (Tsinghua University), Bowen Zhou (Tsinghua University)

CodeGenerationRetrievalTransformerLarge Language ModelReinforcement LearningPrompt EngineeringTextMultimodalityRetrieval-Augmented Generation

🎯 What it does: This paper proposes a unified retrieval-generation framework named ReAuSE for knowledge-driven visual question answering tasks, integrating generative retrieval and answer generation within the same large-scale multimodal language model.

Revelations: A Decidable Class of POMDPs with Omega-Regular Objectives

Marius Belly (CNRS, LaBRI, Universite de Bordeaux), Pierre Vandenhove (University of Antwerp)

CodeReinforcement Learning

🎯 What it does: Weak and strong reveal constraints are defined in partially observable Markov decision processes (POMDPs), and it is proven that under these two types of constraints, almost-sure strategies that satisfy Ο‰-regular objectives (including Parity, Buchi, CoBuchi) can be decided, and can be solved by reducing the POMDP to a belief-supported MDP, with an algorithmic complexity of EXPTIME;

Reverse Distribution Based Video Moment Retrieval for Effective Bias Elimination

Lingdu Kong (Northeastern University), Xiangmin Zhou (RMIT University)

CodeRetrievalGaussian SplattingVideoText

🎯 What it does: A video moment retrieval method based on reverse distribution, ReDis-VMR, and a dynamically scalable adjustment DEA is proposed to eliminate data and model bias and improve retrieval performance.

Reverse Region-to-Entity Annotation for Pixel-Level Visual Entity Linking

Zhengfei Xu (Beijing Institute of Technology), Xin Xin (Tencent)

CodeObject DetectionSegmentationTransformerLarge Language ModelSupervised Fine-TuningImage

🎯 What it does: This paper studies the pixel-level visual entity linking (PL-VEL) task and constructs the MaskOVEN-Wiki large-scale pixel-level annotated dataset.

Revisiting Graph Contrastive Learning on Anomaly Detection: A Structural Imbalance Perspective

Yiming Xu (Xi'an Jiaotong University), Chen Chen (University of Virginia)

CodeAnomaly DetectionGraph Neural NetworkContrastive LearningGraph

🎯 What it does: This paper proposes an anomaly detection framework based on graph contrastive learning (AD-GCL), specifically addressing the poor performance of tail anomaly detection caused by structural imbalance (between head nodes and tail nodes).

Revisiting Interpolation for Noisy Label Correction

Yuanzhuo Xu (Wuhan University), Steve Drew (University of Calgary)

CodeClassificationData-Centric LearningConvolutional Neural NetworkContrastive LearningImage

🎯 What it does: A label correction method based on gradient scaling theory, DULC, is designed to dynamically determine the interpolation weight of each sample using normalized Jensen-Shannon divergence, and to enhance the model's memory of true labels through weak/strong data augmentation and prediction sharpening.

Revisiting Multimodal Emotion Recognition in Conversation from the Perspective of Graph Spectrum

Wei Ai (Central South University of Forestry and Technology), Keqin Li (State University of New York)

CodeRecognitionRecurrent Neural NetworkGraph Neural NetworkContrastive LearningMultimodality

🎯 What it does: Proposes the GS-MCC framework, which constructs a multimodal interaction graph through a sliding window, uses Fourier graph operators to extract high and low-frequency semantics, and employs contrastive learning to achieve semantic consistency and complementarity, ultimately performing sentiment prediction in a single MLP.

Revisiting Multimodal Fusion for 3D Anomaly Detection from an Architectural Perspective

Kaifang Long (Northeastern University), Zhichao Lu (City University of Hong Kong)

CodeAnomaly DetectionNeural Architecture SearchMultimodalityPoint Cloud

🎯 What it does: This paper systematically analyzes the impact of multimodal fusion architecture on 3D anomaly detection performance, proposing a two-layer fusion search space and implementing 3D-ADNAS.

Revisiting Tampered Scene Text Detection in the Era of Generative AI

Chenfan Qu (South China University of Technology), Lianwen Jin (South China University of Technology)

CodeObject DetectionSegmentationTransformerImageBenchmark

🎯 What it does: This paper proposes an open-set text detection task for forged scenes, constructs a high-quality benchmark dataset covering eight generative text editing models, and introduces a texture jitter pre-training and difference-aware forensics framework to enhance the model's detection capability for unknown forgeries.

Revolutionizing Encrypted Traffic Classification with MH-Net: A Multi-View Heterogeneous Graph Model

Haozhen Zhang (Tsinghua University), Ye Zhang (Nanjing University of Posts and Telecommunications)

CodeClassificationSafty and PrivacyGraph Neural NetworkContrastive LearningGraph

🎯 What it does: Proposes MH-Net, which utilizes multi-view heterogeneous flow graphs for packet-level and flow-level classification of encrypted traffic.

RFL: Simplifying Chemical Structure Recognition with Ring-Free Language

Qikai Chang (University of Science and Technology of China), Jinshui Hu (iFLYTEK Research)

CodeRecognitionRecurrent Neural NetworkImage

🎯 What it does: This paper proposes a Ring-Free Language (RFL) that decouples chemical structure diagrams into molecular skeletons, individual ring, and branch information, and based on this, designs a unified Molecular Skeleton Decoder (MSD) for end-to-end recognition.

RHanDS: Refining Malformed Hands for Generated Images with Decoupled Structure and Style Guidance

Chengrui Wang (Taobao and Tmall Group of Alibaba), Bo Zheng (Taobao and Tmall Group of Alibaba)

CodeGenerationData SynthesisPose EstimationDiffusion modelImageMesh

🎯 What it does: A RHanDS framework based on diffusion models is proposed to correct deformed hand structures in generated images while maintaining the original style.

RhythmMamba: Fast, Lightweight, and Accurate Remote Physiological Measurement

Bochao Zou (University of Science and Technology Beijing), Huimin Ma (China Academy of Electronics and Information Technology)

CodeComputational EfficiencyConvolutional Neural NetworkTransformerVideoTime Series

🎯 What it does: Designed and implemented RhythmMamba, an efficient remote photoplethysmography (rPPG) signal extraction framework based on state space models.

RI-MAE: Rotation-Invariant Masked AutoEncoders for Self-Supervised Point Cloud Representation Learning

Kunming Su (South China University of Technology), Kun Hu (University of Sydney)

CodeRepresentation LearningTransformerAuto EncoderPoint Cloud

🎯 What it does: Designed a rotation-invariant masked autoencoder (RI-MAE) for unsupervised point cloud representation learning.

Riemann-based Multi-scale Attention Reasoning Network for Text-3D Retrieval

Wenrui Li (Harbin Institute of Technology), Xiaopeng Fan (Peng Cheng Laboratory)

CodeRetrievalContrastive LearningTextPoint Cloud

🎯 What it does: The RMARN model is proposed, utilizing Riemannian geometry and multi-scale attention to achieve retrieval alignment between text and 3D point clouds.

RingFormer: A Ring-Enhanced Graph Transformer for Organic Solar Cell Property Prediction

Zhihao Ding (Hong Kong Polytechnic University), Chen Jason Zhang (Hong Kong Polytechnic University)

CodeGraph Neural NetworkTransformerGraph

🎯 What it does: Developed RingFormer, a graph Transformer framework that combines atomic layers, ring layers, and interlayers for predicting the properties of organic solar cell (OSC) molecules.

Risk-averse Total-reward MDPs with ERM and EVaR

Xihong Su (University of New Hampshire), Julien Grand-ClΓ©ment (HEC Paris)

CodeOptimizationReinforcement LearningTabularFinance Related

🎯 What it does: This paper studies the introduction of Entropy Risk Measure (ERM) and Entropy Value at Risk (EVaR) as risk measures within the framework of Total Return Criterion (TRC) in finite Markov Decision Processes (MDPs), and proves the existence of an optimal deterministic stationary policy in transient MDPs.

RMath: A Logic Reasoning-Focused Datasets Toward Mathematical Multistep Reasoning Tasks

Ziyi Hu (National University of Defense Technology), Yiping Song (National University of Defense Technology)

CodeTransformerLarge Language ModelPrompt EngineeringText

🎯 What it does: A mathematical reasoning dataset RMath for multi-step logical reasoning has been constructed, and a standardized reasoning framework and annotation scheme based on propositional logic have been proposed for training and evaluating the logical reasoning capabilities of LLMs.

Robust Image Hashing Based on Contrastive Masked Autoencoder with Weak-Strong Augmentation Alignment

Cundian Yang (Peking University), Xiyao Liu (Central South University)

CodeRecognitionRetrievalAnomaly DetectionTransformerAuto EncoderContrastive LearningImage

🎯 What it does: A robust image hashing framework called CMAA based on end-to-end contrastive masked autoencoders is proposed, which enhances robustness against large-scale and mixed attacks by combining weak-strong augmentation alignment, ViT masks, and non-parametric quantization.

Robust Self-Paced Hashing for Cross-Modal Retrieval with Noisy Labels

Ruitao Pu (Sichuan University), Dezhong Peng (Sichuan National Innovation New Vision UHD Video Technology Co., Ltd.)

CodeRetrievalContrastive LearningMultimodality

🎯 What it does: A robust self-paced hashing framework RSHNL is proposed to handle noisy labeled data in cross-modal retrieval.

Robust Tracking via Mamba-based Context-aware Token Learning

Jinxia Xie (Guangxi Normal University), Shuxiang Song (Wuzhou University)

CodeObject TrackingVideo

🎯 What it does: We propose TemTrack, a visual tracker that separates temporal information learning from appearance modeling, capturing target appearance changes and motion trends through trajectory tokens in a sliding window and a mamba-cross attention module.

RoDA: Robust Domain Alignment for Cross-Domain Retrieval Against Label Noise

Ziniu Yin (Sichuan University), Xu Wang (Sichuan University)

CodeRetrievalDomain AdaptationConvolutional Neural NetworkImage

🎯 What it does: This study proposes the RoDA framework to address the issue of label noise in cross-domain image retrieval.

RouterRetriever: Routing over a Mixture of Expert Embedding Models

Hyunji Lee (KAIST AI), Kyle Lo (Allen Institute for AI)

CodeRetrievalMixture of ExpertsTextBenchmark

🎯 What it does: Proposes the RouterRetriever model, which utilizes domain experts and embedding similarity routing for retrieval;

RoVRM: A Robust Visual Reward Model Optimized via Auxiliary Textual Preference Data

Chenglong Wang (Northeastern University), Jingbo Zhu (Northeastern University)

CodeRecommendation SystemReinforcement LearningVision Language ModelImageText

🎯 What it does: Through a three-stage progressive training and optimal transport preference data selection, the visual reward model is enhanced using text preference data, allowing large visual language models to better align with human preferences.

Rule-Guided Graph Neural Networks for Explainable Knowledge Graph Reasoning

Zhe Wang (Griffith University), Zhiqiang Zhuang (Tianjin University)

CodeExplainability and InterpretabilityGraph Neural NetworkGraphBenchmark

🎯 What it does: This paper proposes a rule-guided graph neural network for interpretable knowledge graph reasoning, which can utilize existing rules to guide learning during the training process, and directly extract high-confidence rules from the network parameters after the model training is completed.

S-INF: Towards Realistic Indoor Scene Synthesis via Scene Implicit Neural Field

Zixi Liang (University of Electronic Science and Technology of China), Lixin Duan (University of Electronic Science and Technology of China)

CodeGenerationData SynthesisTransformerNeural Radiance FieldPoint CloudMesh

🎯 What it does: A method for indoor scene synthesis called S-INF (Scene Implicit Neural Field) is proposed, which utilizes implicit neural fields to simultaneously learn the relationships of scene layout and detailed objects, generating more realistic and stylistically consistent 3D indoor scenes.

SΒ²DN: Learning to Denoise Unconvincing Knowledge for Inductive Knowledge Graph Completion

Tengfei Ma (Hunan University), Xiangxiang Zeng (Hunan University)

CodeRecommendation SystemKnowledge DistillationGraph Neural NetworkGraph

🎯 What it does: A Semantic Structure-aware Denoising Network (S²DN) is proposed for Inductive Knowledge Graph Completion (Inductive KGC), which enhances inference on new entities by smoothing semantic similarity relationships in subgraphs and adaptively filtering structures.

S2S2: Semantic Stacking for Robust Semantic Segmentation in Medical Imaging

Yimu Pan (Pennsylvania State University), James Z. Wang (Pennsylvania State University)

CodeSegmentationDomain AdaptationDiffusion modelMultimodalityBiomedical DataMagnetic Resonance ImagingComputed Tomography

🎯 What it does: A semantic stacking (S2S2) training strategy is proposed as an add-on to existing segmentation models to enhance the robustness of the models.

SAFIRE: Segment Any Forged Image Region

Myung-Joon Kwon (Korea Advanced Institute of Science and Technology), Changick Kim (NAVER WEBTOON AI)

CodeSegmentationContrastive LearningImage

🎯 What it does: We propose SAFIRE, a point-guided multi-source image segmentation method designed to achieve both counterfeit localization and multi-source differentiation simultaneously.

SAIL: Sample-Centric In-Context Learning for Document Information Extraction

Jinyu Zhang (Shanghai Jiao Tong University), Xinyi Le (Shanghai Jiao Tong University)

CodeData-Centric LearningTransformerLarge Language ModelPrompt EngineeringText

🎯 What it does: A sample-centered context learning framework (SAIL) is proposed for zero-shot document information extraction.

SalMΒ²: An Extremely Lightweight Saliency Mamba Model for Real-Time Cognitive Awareness of Driver Attention

Chunyu Zhao (Southwest Jiaotong University), Tao Deng (Southwest Jiaotong University)

CodeAutonomous DrivingContrastive LearningImage

🎯 What it does: A lightweight SalM2 driver attention prediction model has been developed, capable of capturing attention distribution in driving scenes in real-time.

SAM-Aware Graph Prompt Reasoning Network for Cross-Domain Few-Shot Segmentation

Shi-Feng Peng (Nanjing University of Science and Technology), Guo-Sen Xie (Southeast University)

CodeSegmentationGraph Neural NetworkLarge Language ModelImageBenchmark

🎯 What it does: Proposes the SAM-aware Graph Prompt Reasoning Network (GPRN), which generates visual prompts through SAM, utilizes a graph attention network to achieve global semantic consistency among prompts, and employs adaptive point selection for refined segmentation during testing.

Sample-aware Adaptive Structured Pruning for Large Language Models

Jun Kong (Yunnan University), Xuejie Zhang (Yunnan University)

CodeTransformerLarge Language ModelSupervised Fine-TuningText

🎯 What it does: This paper proposes a sample-aware adaptive structural pruning framework for large language models called AdaPruner, which achieves more efficient structural pruning by adaptively searching for the best calibration data and importance estimation metrics.

SAP: Corrective Machine Unlearning with Scaled Activation Projection for Label Noise Robustness

Sangamesh Kodge (Purdue University), Kaushik Roy (Purdue University)

CodeClassificationData-Centric LearningConvolutional Neural NetworkTransformerImage

🎯 What it does: This paper proposes a single-step correction machine learning algorithm based on Singular Value Decomposition (SVD) called SAP, which uses a small number of low cross-entropy loss samples to estimate reliable samples and projects the model weights into a reliable activation space, thereby eliminating the impact of label noise.

SatCLIP: Global, General-Purpose Location Embeddings with Satellite Imagery

Konstantin Klemmer (Microsoft Research), Marc Rußwurm (Wageningen University and Research)

CodeRepresentation LearningTransformerContrastive LearningImage

🎯 What it does: This paper proposes SatCLIP, a globally universal location encoder trained through contrastive learning by aligning satellite images with latitude and longitude coordinates, and fine-tuned for various geographic prediction tasks.

Scalable Acceleration for Classification-Based Derivative-Free Optimization

Tianyi Han (Beijing Supreium Technology), Yuan Jin (Beijing Supreium Technology)

CodeOptimizationHyperparameter SearchTabular

🎯 What it does: This paper studies a classification-based gradient-free optimization algorithm framework and proposes a new RACE-CARS algorithm, which accelerates the search through random coordinate shrinking and region reduction.

Scalable Decentralized Algorithms for Online Personalized Mean Estimation

Franco Galante (Politecnico di Torino), Emilio Leonardi (Politecnico di Torino)

CodeFederated LearningComputational EfficiencyImage

🎯 What it does: Two scalable decentralized online mean estimation algorithms (B‑ColME and C‑ColME) are proposed, which estimate the mean with communication limited to a finite number of neighbors under multi-dimensional distributions.

Scalable Knowledge Refactoring Using Constrained Optimisation

Minghao Liu (University of Oxford), Andrew Cropper (University of Oxford)

CodeCompressionOptimizationTabularAlzheimer's Disease

🎯 What it does: This paper proposes a knowledge reconstruction method based on constraint optimization, aimed at compressing the size of logic programs.

Scalable Trajectory-User Linking with Dual-Stream Representation Networks

Hao Zhang (Ocean University of China), Yanwei Yu (Ocean University of China)

CodeRecurrent Neural NetworkContrastive LearningTime SeriesSequential

🎯 What it does: This paper proposes ScaleTUL, a scalable trajectory-user linking framework that utilizes a dual-stream encoder and spatiotemporal enhancement to address the large-scale trajectory matching problem.

ScaleMatch: Multi-scale Consistency Enhancement for Semi-supervised Semantic Segmentation

Liang Lv (Wuhan University), Lefei Zhang (Wuhan University)

CodeSegmentationConvolutional Neural NetworkSupervised Fine-TuningImage

🎯 What it does: The ScaleMatch framework is proposed to enhance the scale invariance and pseudo-label quality of semi-supervised semantic segmentation models under limited labeled data through Cross-Scale Interaction Fusion (CIF) and Intra-Scale Consistency Learning (ISVC, FSVC).

Scaling Combinatorial Optimization Neural Improvement Heuristics with Online Search and Adaptation

Federico Julian Camerota VerdΓΉ (University of Trieste), Luca Bortolussi (University of Trieste)

CodeOptimizationTransformerReinforcement LearningTabular

🎯 What it does: An improved heuristic based on Limited Rollback Beam Search (LRBS) is proposed to enhance the reasoning performance of deep reinforcement learning models in combinatorial optimization.

SCALM: Detecting Bad Practices in Smart Contracts Through LLMs

Zongwei Li (Hainan University), Xin Wang (Hainan University)

CodeTransformerLarge Language ModelPrompt EngineeringTextRetrieval-Augmented Generation

🎯 What it does: Proposed and implemented the SCALM framework, which utilizes large language models to detect bad practices in smart contracts.

SCANS: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering

Zouying Cao (Shanghai Jiao Tong University), Hai Zhao (Shanghai Jiao Tong University)

CodeSafty and PrivacyLarge Language ModelPrompt EngineeringText

🎯 What it does: A security awareness control method based on activation layer driving (SCANS) is proposed, which mitigates the misrejection of legitimate queries by extracting rejection behavior vectors and performing activation shifts in security-critical layers.

Scene Graph-Grounded Image Generation

Fuyun Wang (Nanjing University of Science and Technology), Zhen Cui (Nanjing University of Science and Technology)

CodeGenerationData SynthesisGraph Neural NetworkDiffusion modelAuto EncoderContrastive LearningImage

🎯 What it does: A scene graph-based image generation framework SGG-IG is designed and implemented, directly aligning scene graphs with generated images without an intermediate layout, integrating modules such as mask self-supervision, spatial contrastive loss, and image-scene alignment.

ScholarGEC: Enhancing Controllability of Large Language Model for Chinese Academic Grammatical Error Correction

Zixiao Kong (University of Science and Technology of China), Yu Su (Hefei Normal University)

CodeTransformerLarge Language ModelSupervised Fine-TuningPrompt EngineeringText

🎯 What it does: This study proposes the ScholarGEC framework, which enhances the controllability and accuracy of LLM in grammatical error correction of Chinese academic papers by utilizing knowledge prefixes, a detect-correct structure, and self-reflection techniques.

SCKD: Semi-Supervised Cross-Modality Knowledge Distillation for 4D Radar Object Detection

Ruoyu Xu (Zhejiang University), Eryun Liu (Zhejiang University)

CodeObject DetectionKnowledge DistillationMultimodalityPoint Cloud

🎯 What it does: This paper proposes a 4D radar 3D object detection method based on semi-supervised cross-modal knowledge distillation, called SCKD.

SCOPE: Sign Language Contextual Processing with Embedding from LLMs

Yuqi Liu (ShanghaiTech University), Lan Xu (ShanghaiTech University)

CodeRecognitionImage TranslationTransformerLarge Language ModelSupervised Fine-TuningVideoText

🎯 What it does: This paper proposes a context-aware sign language recognition and translation framework called SCOPE based on LLM embeddings, and contributes the first large-scale Chinese sign language dialogue dataset.

ScoreNet: Consistency-driven Framework with Multi-side Information Fusion for Session-based Recommendation

Piao Tong (University of Electronic Science and Technology of China), Tian Lan (Byte Dance)

CodeRecommendation SystemTransformerSequential

🎯 What it does: Proposes the ScoreNet framework, which combines the MPRE and PECS modules for multi-side information fusion, improving interest modeling and score consistency in session-based recommendations.

SdalsNet: Self-Distilled Attention Localization and Shift Network for Unsupervised Camouflaged Object Detection

Peiyao Shou (Hangzhou Dianzi University), Chenggang Yan (Hangzhou Dianzi University)

CodeObject DetectionSegmentationKnowledge DistillationTransformerImage

🎯 What it does: This paper proposes a fully unsupervised camouflage object detection method called SdalsNet, which utilizes self-distillation attention localization and transfer to learn target features and directly obtain segmentation results from the attention map.

SECodec: Structural Entropy-based Compressive Speech Representation Codec for Speech Language Models

Linqin Wang (Kunming University of Science and Technology), Ling Dong (Kunming University of Science and Technology)

CodeGenerationCompressionTransformerGenerative Adversarial NetworkAudio

🎯 What it does: This paper proposes a speech discretization encoder SECodec based on Structural Entropy (SE) and a speech language model SESLM driven by Structural Entropy, which can automatically determine the codebook size and reduce Euclidean distance distortion through a 2D structural entropy quantization method, thereby enhancing speech reconstruction and zero-shot TTS performance.

Security Attacks on LLM-based Code Completion Tools

Wen Cheng (Nanjing University), Wei Wang (Nanjing University)

CodeSafty and PrivacyAdversarial AttackAI Code AssistantTransformerLarge Language ModelPrompt EngineeringText

🎯 What it does: This paper studies the security vulnerabilities of large language model-driven code completion tools (LCCT) and proposes and validates two types of attacks against LCCT: jailbreak attacks based on context information aggregation and hierarchical code exploitation, as well as code-based training data extraction attacks.

See Through Their Minds: Learning Transferable Brain Decoding Models from Cross-Subject fMRI

Yulong Liu (Xi'an Jiaotong University), Nanning Zheng (Xi'an Jiaotong University)

CodeClassificationRecognitionGenerationRetrievalDiffusion modelContrastive LearningImageTextMagnetic Resonance Imaging

🎯 What it does: This study investigates cross-subject fMRI brain decoding models, using shallow adapters to map fMRI data from different subjects into a unified representational space, and then performing high-level semantic recognition and low-level pixel-level reconstruction through a shared deep decoding module.

SeeDiff: Off-the-Shelf Seeded Mask Generation from Diffusion Models

Joon Hyun Park (Hanyang University), Sungyong Baik (Hanyang University)

CodeSegmentationData SynthesisDiffusion modelImage

🎯 What it does: This paper proposes a training-free and prompt-free offline framework called SeeDiff, which utilizes the attention maps from Stable Diffusion to generate high-quality pixel-level segmentation masks and can directly synthesize semantic segmentation datasets.

SeFAR: Semi-supervised Fine-grained Action Recognition with Temporal Perturbation and Learning Stabilization

Yongle Huang (Northwestern Polytechnical University), Dian Shao (Northwestern Polytechnical University)

CodeRecognitionTransformerLarge Language ModelVideoMultimodality

🎯 What it does: The SeFAR framework is proposed, which enhances performance in semi-supervised fine-grained action recognition through dual-layer temporal element modeling, moderate temporal perturbation enhancement, and adaptive regulation.

SegFace: Face Segmentation of Long-Tail Classes

Kartik Narayan (Johns Hopkins University), Vishal M. Patel (Johns Hopkins University)

CodeSegmentationTransformerImage

🎯 What it does: This paper proposes SegFace, a face segmentation method that utilizes a lightweight transformer decoder and learnable class-specific tokens, specifically aimed at improving long-tail categories.

Segment Any 3D Gaussians

Jiazhong Cen (Shanghai Jiao Tong University), Qi Tian (Huawei Technologies Co Ltd)

CodeSegmentationKnowledge DistillationContrastive LearningGaussian SplattingPoint Cloud

🎯 What it does: Developed the SAGA method to achieve promptable multi-scale 3D segmentation within a 3D Gaussian expansion framework.

Selective Forgetting: Advancing Machine Unlearning Techniques and Evaluation in Language Models

Lingzhi Wang (Harbin Institute of Technology), Georg Gottlob (University of Calabria)

CodeData-Centric LearningTransformerLarge Language ModelText

🎯 What it does: The SEUL method is proposed to achieve selective and fine-grained forgetting in language models, and sensitive information forgetting evaluation metrics S-EL, S-MA, as well as an online/offline sensitive span automatic labeling process are designed.

Selective Visual Prompting in Vision Mamba

Yifeng Yao (Peking University), Jiahuan Zhou (Peking University)

CodeClassificationRecognitionTransformerPrompt EngineeringImage

🎯 What it does: A Selective Visual Prompting (SVP) method specifically designed for Vision Mamba is proposed and implemented for efficient fine-tuning.

Self-attention-based Diffusion Model for Time-series Imputation in Partial Blackout Scenarios

Mohammad Rafid Ul Islam (Oregon State University), Alan Fern (Oregon State University)

CodeDiffusion modelScore-based ModelTime Series

🎯 What it does: This paper proposes a self-attention-based diffusion model SADI for high-quality imputation of missing values in multivariate time series under the 'partial blackout' missing pattern.

Self-Attentive Spatio-Temporal Calibration for Precise Intermediate Layer Matching in ANN-to-SNN Distillation

Di Hong (Zhejiang University), Yueming Wang (Zhejiang University)

CodeKnowledge DistillationSpiking Neural NetworkImage

🎯 What it does: This paper studies a Self-Attention Spatio-Temporal Calibration (SASTC) method to improve ANN-to-SNN knowledge distillation.

Self-Corrected Flow Distillation for Consistent One-Step and Few-Step Image Generation

Quan Dao (Rutgers University), Anh Tran (VinAI Research)

CodeGenerationData SynthesisKnowledge DistillationFlow-based ModelRectified FlowGenerative Adversarial NetworkImage

🎯 What it does: Distill the pre-trained flow matching teacher model into a model capable of achieving single-step and few-step consistent image generation.

Self-Explainable Graph Transformer for Link Sign Prediction

Lu Li (Huazhong Agricultural University), Zeyu Zhang (Huazhong Agricultural University)

CodeRecommendation SystemExplainability and InterpretabilityGraph Neural NetworkTransformerGraph

🎯 What it does: Developed a self-explanatory signature graph Transformer (SE-SGformer) that can predict link symbols and provide interpretable positive/negative neighbor information.

Semantic Ambiguity Modeling and Propagation for Fine-Grained Visual Cross View Geo-Localization

Mingtao Feng (Xidian University), Ajmal Saeed Mian

CodeRecognitionRetrievalConvolutional Neural NetworkContrastive LearningImage

🎯 What it does: This paper studies the semantic ambiguity of semi-positive sample generation in visual cross-view geographic localization, proposing an automatic balance between retrieval and offset regression joint training by modeling the uncertainty of offset regression and propagating it to the retrieval task.

Semi-IIN: Semi-Supervised Intra-Inter Modal Interaction Learning Network for Multimodal Sentiment Analysis

Jinhao Lin (South China University of Technology), Qi Liu (South China University of Technology)

CodeClassificationConvolutional Neural NetworkMultimodality

🎯 What it does: Proposes the Semi-IIN network, which combines self-training with unsupervised data to dynamically separate and select multimodal interaction information for sentiment analysis.

Semi-Implicit Neural Ordinary Differential Equations

Hong Zhang (Argonne National Laboratory), Romit Maulik (Pennsylvania State University)

CodeGraphTime SeriesOrdinary Differential Equation

🎯 What it does: A semi-implicit neural ODE (SINODE) framework is proposed, utilizing linear-nonlinear partitioning and IMEX Runge-Kutta integration, and achieving reversible exact gradients through discrete adjoint differentiation.

Semi-Supervised Multimodal Classification Through Learning from Modal and Strategic Complementarities

Junchi Chen (Beihang University), Junfan Chen (Beihang University)

CodeClassificationTransformerContrastive LearningImageTextMultimodality

🎯 What it does: This paper studies image-text semi-supervised multimodal classification in scenarios with scarce labels and proposes the MSC framework.

SemiDFL: A Semi-Supervised Paradigm for Decentralized Federated Learning

Xinyang Liu (Shenzhen Institute of Artificial Intelligence and Robotics for Society), Bo Liu

CodeFederated LearningDiffusion modelImage

🎯 What it does: This paper proposes SemiDFL, a new framework for semi-supervised federated learning that operates without a central server, enabling collaborative training among clients with label scarcity and highly non-homogeneous distributions through model and data space consensus.

Sequential Conditional Transport on Probabilistic Graphs for Interpretable Counterfactual Fairness

Agathe Fernandes Machado (Universite du Quebec a Montreal), Ewen Gallic (Aix Marseille University)

CodeExplainability and InterpretabilityComputational EfficiencyGraph Neural NetworkTabular

🎯 What it does: A sequential transport method based on conditional univariate optimal transport is proposed to generate counterfactual samples that conform to causal graphs, thereby assessing individual-level fairness.

Sequential Joint Dependency Aware Human Pose Estimation with State Space Model

Hanxi Yin (University of Amsterdam), Zhixiang Chen (University of Sheffield)

CodePose EstimationGraph Neural NetworkTransformerImage

🎯 What it does: This paper proposes a single-camera 2D-to-3D human pose estimation model that incorporates sequential joint dependency perception, utilizing a state space model (SSM) to integrate the sequential relationships of joints into feature learning.

SGTC: Semantic-Guided Triplet Co-training for Sparsely Annotated Semi-Supervised Medical Image Segmentation

Ke Yan (Ocean University of China), Zhi Liu (Shandong University)

CodeSegmentationConvolutional Neural NetworkContrastive LearningBiomedical DataMagnetic Resonance Imaging

🎯 What it does: This paper proposes a semantic-guided triple co-training framework SGTC, which achieves semi-supervised learning for medical image segmentation by labeling three orthogonal slices with a small number of volume samples.

Sharpening Neural Implicit Functions with Frequency Consolidation Priors

Chao Chen (Tsinghua University), Zhizhong Han (Wayne State University)

CodeGenerationData SynthesisOptimizationPoint Cloud

🎯 What it does: Utilizing frequency-integrated priors to transform low-frequency SDF observations into high-frequency complete SDF, thereby enhancing the detail and integrity of neural implicit models.

Sharper Error Bounds in Late Fusion Multi-view Clustering with Eigenvalue Proportion Optimization

Liang Du (Shanxi University), Yuhua Qian (Shanxi University)

CodeOptimizationImageBiomedical Data

🎯 What it does: This paper proposes a stricter analysis of the generalization error of multiple kernel K-means using the eigenvalue ratio and local Rademacher complexity, and based on this, designs a low-pass graph filter to enhance the eigenvalue ratio, thereby improving the performance of multi-view late fusion clustering.

ShotVL: Human-Centric Highlight Frame Retrieval via Language Queries

Wangyu Xue (Tsinghua University), Yaoxue Zhang (Tsinghua University)

CodeClassificationRetrievalTransformerSupervised Fine-TuningVision Language ModelVideoTextBenchmark

🎯 What it does: The BestShot task is proposed, which aims to accurately locate highlight frames in human videos through language queries, and a corresponding benchmark has been constructed.

SIGMA: Selective Gated Mamba for Sequential Recommendation

Ziwei Liu (City University of Hong Kong), Xiangyu Zhao (City University of Hong Kong)

CodeRecommendation SystemRecurrent Neural NetworkSequential

🎯 What it does: This paper proposes the SIGMA framework, which utilizes Partial Flip Mamba (PF-Mamba), Dense Selective Gate (DS Gate), and Feature Extraction GRU (FE-GRU) to improve sequence recommendation systems.

Sign-IDD: Iconicity Disentangled Diffusion for Sign Language Production

Shengeng Tang (Hefei University of Technology), Richang Hong (Hefei University of Technology)

CodeGenerationPose EstimationDiffusion modelVideoText

🎯 What it does: This study proposes a sign language gesture generation framework called Sign-IDD based on diffusion models, which achieves high-quality generation of sign language gestures from text gloss by transforming 3D joint representations into 4D skeletal representations and incorporating an attribute-controllable diffusion module.

Similar Modality Enhancement and Action Consistency Learning for Weakly Supervised Temporal Action Localization

Maodong Li (Wuhan University), Bing Li (Hubei Luojia Laboratory)

CodeRecognitionObject DetectionOptical FlowVideo

🎯 What it does: Proposes the SEAL method, which combines the SME module and the ACL module to achieve temporal action localization using weakly supervised video-level labels.

Simplifying Control Mechanism in Text-to-Image Diffusion Models

Zhida Feng (Wuhan University of Science and Technology), Shikun Feng (Baidu Inc.)

CodeGenerationData SynthesisConvolutional Neural NetworkDiffusion modelImageText

🎯 What it does: Proposes SimpleControlNet, a simplified control mechanism for text-to-image diffusion models;

SimRP: Syntactic and Semantic Similarity Retrieval Prompting Enhances Aspect Sentiment Quad Prediction

Zhongquan Jian (Xiamen University), Qingqiang Wu (Xiamen University)

CodeGenerationRetrievalTransformerLarge Language ModelSupervised Fine-TuningPrompt EngineeringText

🎯 What it does: By constructing prompts that include syntactic and semantic similar examples, the generation performance of Aspect Sentiment Quad Prediction (ASQP) is improved.

Simulate and Eliminate: Revoke Backdoors for Generative Large Language Models

Haoran Li (Hong Kong University of Science and Technology), Yangqiu Song (Hong Kong University of Science and Technology)

CodeGenerationAdversarial AttackTransformerLarge Language ModelSupervised Fine-TuningPrompt EngineeringText

🎯 What it does: A backdoor removal method named SANDE is proposed for generative large language models, which can directly repair LLMs that have been implanted with backdoors without relying on clean models.

Single Image Rolling Shutter Removal with Diffusion Models

Zhanglei Yang (University of Electronic Science and Technology of China), Shuaicheng Liu (Megvii Technology)

CodeRestorationDiffusion modelOptical FlowImage

🎯 What it does: This paper proposes RS-Diffusion, which utilizes a diffusion model to achieve single-frame rolling shutter correction and constructs a real annotated RS-Real dataset.

Single-View Graph Contrastive Learning with Soft Neighborhood Awareness

Qingqiang Sun (Great Bay University), Kai Wang (Central South University)

CodeRepresentation LearningGraph Neural NetworkContrastive LearningGraph

🎯 What it does: This paper proposes a single-view graph contrastive learning framework called SIGNA, which learns node representations using 'soft neighborhood awareness' without relying on cross-view augmentation.

SKI Models: Skeleton Induced Vision-Language Embeddings for Understanding Activities of Daily Living

Arkaprava Sinha (University of North Carolina at Charlotte), Srijan Das (University of North Carolina at Charlotte)

CodeRecognitionKnowledge DistillationRepresentation LearningVision Language ModelVideoText

🎯 What it does: The SKI model is proposed, which achieves zero-shot recognition and video description of daily life actions by injecting 3D skeletal information into the visual-language embedding space.

SkillTree: Explainable Skill-Based Deep Reinforcement Learning for Long-Horizon Control Tasks

Yongyan Wen (Harbin Institute of Technology), Peng Liu (Kuaishou Technology)

CodeExplainability and InterpretabilityKnowledge DistillationRobotic IntelligenceReinforcement LearningTabular

🎯 What it does: A hierarchical interpretable deep reinforcement learning framework called SkillTree is constructed, which maps continuous action spaces to discrete skill spaces and implements high-level policies using differentiable decision trees, making the decision-making process at the skill level interpretable.

Skip Mamba Diffusion for Monocular 3D Semantic Scene Completion

Li Liang (University of Western Australia), Ajmal Saeed Mian (University of Western Australia)

CodeSegmentationGenerationDiffusion modelAuto EncoderPoint Cloud

🎯 What it does: This paper proposes a monocular 3D semantic scene completion method based on a variational autoencoder conditional latent space and Skimba diffusion network.

SkipPool: Improved Sparse Hierarchical Graph Pooling with Differentiable Exploration

Sarith Imaduwage (Independent Researcher)

CodeGraph Neural NetworkPoint CloudGraph

🎯 What it does: An improved sparse hierarchical graph pooling method called SKIPPOOL is proposed, which skips over-represented areas through differentiable exploration to better preserve graph-level information.

SLACE: A Monotone and Balance-Sensitive Loss Function for Ordinal Regression

Inbar Nachmani (Technion Israel Institute of Technology), Avigdor Gal (Technion Israel Institute of Technology)

CodeClassificationOptimizationTabular

🎯 What it does: The SLACE loss function is proposed, which combines monotonicity, balanced sensitivity, and convexity for ordinal regression.

SLIP: Spoof-Aware One-Class Face Anti-Spoofing with Language Image Pretraining

Pei-Kai Huang (National Tsing Hua University), Chiou-Ting Hsu (National Tsing Hua University)

CodeClassificationRecognitionTransformerPrompt EngineeringVision Language ModelImageMultimodality

🎯 What it does: This paper proposes the SLIP framework through a CLIP-based visual-language pre-training model and prompt learning, utilizing language-guided pseudo-spoof prompts to generate spoof cue maps, achieve feature decoupling, and integrate pseudo-spoof image features, addressing the performance decline caused by the lack of spoof data in single-class FAS.

SLRL: Semi-Supervised Local Community Detection Based on Reinforcement Learning

Li Ni (Anhui University), Victor S. Sheng (Texas Tech University)

CodeGraph Neural NetworkReinforcement LearningGraph

🎯 What it does: This paper proposes a semi-supervised local community detection method based on reinforcement learning, called SLRL, which utilizes known communities to guide local structure extraction and community expansion.

Small Language Model Makes an Effective Long Text Extractor

Yelin Chen (Xinjiang University), Jie Tang (Tsinghua University)

CodeRecognitionTransformerLarge Language ModelText

🎯 What it does: A lightweight span-based method SeNER is proposed for entity recognition in long texts, capable of identifying long entity blocks under GPU memory-friendly conditions.

SMMF: Square-Matricized Momentum Factorization for Memory-Efficient Optimization

Kwangryeol Park (Ulsan National Institute of Science and Technology), Seulki Lee (Ulsan National Institute of Science and Technology)

CodeOptimizationConvolutional Neural NetworkTransformerImageText

🎯 What it does: The paper presents SMMF, an adaptive learning rate optimizer that compresses arbitrary-order momentum tensors through square matricization and one-time matrix decomposition, significantly reducing memory usage.

Smoothness Really Matters: A Simple Yet Effective Approach for Unsupervised Graph Domain Adaptation

Wei Chen (Beihang University), Fuzhen Zhuang (Independent Researcher)

CodeDomain AdaptationGraph Neural NetworkGraph

🎯 What it does: This paper proposes a UGDA method for direct structural smoothing on the target graphβ€”TDSS, which combines neighborhood sampling and Laplacian smoothing to enhance the robustness of node representations.

SoLA: Leveraging Soft Activation Sparsity and Low-Rank Decomposition for Large Language Model Compression

Xinhao Huang (Hong Kong University of Science and Technology), Zeyi Wen (Hong Kong University of Science and Technology)

CodeCompressionTransformerLarge Language ModelText

🎯 What it does: A training-free LLM compression method called SoLA is proposed, which utilizes soft activation sparsity and low-rank decomposition for fine-grained model compression, retaining a small number of highly activated neurons and performing SVD decomposition on the remaining parts, achieving significant compression rates without the need for post-training.

Solving Epistemic Logic Programs Using Generate-and-Test with Propagation

Jorge Fandinno (University of Nebraska Omaha), Lute Lillo (University of Vermont)

CodeBenchmark

🎯 What it does: A general generation-testing framework is proposed, and a new epistemic logic program solver is implemented within this framework.

Solving Higher-Order Quantified Boolean Satisfiability via Higher-Order Model Checking

Hiroshi Unno (Tohoku University), Jie-Hong Roland Jiang (National Taiwan University)

CodeBenchmark

🎯 What it does: The first higher-order quantified Boolean satisfiability (HOQBF) solver HOMCSAT is proposed and implemented by transforming HOQBF into a higher-order model checking problem and utilizing the HORSAT2 solver to complete the solution.

SongEditor: Adapting Zero-Shot Song Generation Language Model as a Multi-Task Editor

Chenyu Yang (Chinese University of Hong Kong), Haizhou Li

CodeGenerationTransformerLarge Language ModelDiffusion modelAuto EncoderTextAudio

🎯 What it does: This paper presents SongEditor, a multi-task editor that extends a zero-shot song generation language model, supporting segment-wise and track-wise editing as well as generating songs from scratch.