{"total":99,"rows":[{"id":"2308.08241","title":"TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Series","created":"2023-08-16","cited_by_count":169,"area":null},{"id":"2307.03759","title":"A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection","created":"2023-07-07","cited_by_count":145,"area":null},{"id":"2303.09030","title":"Large Selective Kernel Network for Remote Sensing Object Detection","created":"2023-03-16","cited_by_count":98,"area":null},{"id":"2401.03495","title":"Segment Anything Model for Medical Image Segmentation: Current Applications and Future Directions","created":"2024-01-07","cited_by_count":97,"area":null},{"id":"2307.00855","title":"Review of Large Vision Models and Visual Prompt Engineering","created":"2023-07-03","cited_by_count":77,"area":null},{"id":"2404.03264","title":"Foundation Model for Advancing Healthcare: Challenges, Opportunities, and Future Directions","created":"2024-04-04","cited_by_count":77,"area":null},{"id":"2308.12488","title":"GPTEval: A Survey on Assessments of ChatGPT and GPT-4","created":"2023-08-24","cited_by_count":73,"area":null},{"id":"2310.08370","title":"UniPAD: A Universal Pre-training Paradigm for Autonomous Driving","created":"2023-10-12","cited_by_count":73,"area":null},{"id":"2405.17730","title":"MMPareto: Boosting Multimodal Learning with Innocent Unimodal Assistance","created":"2024-05-28","cited_by_count":73,"area":null},{"id":"2305.08196","title":"A Comprehensive Survey on Segment Anything Model for Vision and Beyond","created":"2023-05-14","cited_by_count":64,"area":null},{"id":"2304.06632","title":"AI-Generated Content (AIGC): A Survey","created":"2023-03-26","cited_by_count":59,"area":null},{"id":"2404.09516","title":"State Space Model for New-Generation Network Alternative to Transformers: A Survey","created":"2024-04-15","cited_by_count":59,"area":null},{"id":"2412.20206","title":"Toward Visual Grounding: A Survey","created":"2024-12-28","cited_by_count":52,"area":null},{"id":"2310.02227","title":"SNIP: Bridging Mathematical Symbolic and Numeric Realms with Unified Pre-training","created":"2023-10-03","cited_by_count":47,"area":null},{"id":"2405.18653","title":"Recent Advances of Foundation Language Models-based Continual Learning: A Survey","created":"2024-05-28","cited_by_count":46,"area":null},{"id":"2403.11735","title":"LSKNet: A Foundation Lightweight Backbone for Remote Sensing","created":"2024-03-18","cited_by_count":44,"area":null},{"id":"2401.12224","title":"LLM4EDA: Emerging Progress in Large Language Models for Electronic Design Automation","created":"2023-12-28","cited_by_count":40,"area":null},{"id":"2505.05108","title":"Multi-agent Embodied AI: Advances and Future Directions","created":"2025-05-08","cited_by_count":36,"area":null},{"id":"2410.00379","title":"CXPMRG-Bench: Pre-training and Benchmarking for X-ray Medical Report Generation on CheXpert Plus Dataset","created":"2024-10-01","cited_by_count":35,"area":null},{"id":"2503.01210","title":"Every SAM Drop Counts: Embracing Semantic Priors for Multi-Modality Image Fusion and Beyond","created":"2025-03-03","cited_by_count":35,"area":null},{"id":"2403.11530","title":"Continual Forgetting for Pre-trained Vision Models","created":"2024-03-18","cited_by_count":29,"area":null},{"id":"2404.00225","title":"Heterogeneous Contrastive Learning for Foundation Models and Beyond","created":"2024-03-30","cited_by_count":27,"area":null},{"id":"2312.10692","title":"Pedestrian Attribute Recognition via CLIP based Prompt Vision-Language Fusion","created":"2023-12-17","cited_by_count":24,"area":null},{"id":"2403.18383","title":"Generative Multi-modal Models are Good Class-Incremental Learners","created":"2024-03-27","cited_by_count":22,"area":null},{"id":"2305.03678","title":"Towards Segment Anything Model (SAM) for Medical Image Segmentation: A Survey","created":"2023-05-05","cited_by_count":21,"area":null},{"id":"2405.17927","title":"The Evolution of Multimodal Model Architectures","created":"2024-05-28","cited_by_count":21,"area":null},{"id":"2504.05408","title":"Frontier AI's Impact on the Cybersecurity Landscape","created":"2025-04-07","cited_by_count":21,"area":null},{"id":"2308.04369","title":"SSTFormer: Bridging Spiking Neural Network and Memory Support Transformer for Frame-Event based Recognition","created":"2023-08-08","cited_by_count":20,"area":null},{"id":"2309.08836","title":"Bias and Fairness in Chatbots: An Overview","created":"2023-09-16","cited_by_count":20,"area":null},{"id":"2402.08323","title":"Mapping the Ethics of Generative AI: A Comprehensive Scoping Review","created":"2024-02-13","cited_by_count":19,"area":null},{"id":"2403.00691","title":"Tri-Modal Motion Retrieval by Learning a Joint Embedding Space","created":"2024-03-01","cited_by_count":16,"area":null},{"id":"2401.02317","title":"BA-SAM: Scalable Bias-Mode Attention Mask for Segment Anything Model","created":"2024-01-04","cited_by_count":15,"area":null},{"id":"2402.01874","title":"The RL/LLM Taxonomy Tree: Reviewing Synergies Between Reinforcement Learning and Large Language Models","created":"2024-02-02","cited_by_count":15,"area":null},{"id":"2408.12889","title":"Unleashing the Potential of SAM2 for Biomedical Images and Videos: A Survey","created":"2024-08-23","cited_by_count":14,"area":null},{"id":"2312.01640","title":"SequencePAR: Understanding Pedestrian Attributes via A Sequence Generation Paradigm","created":"2023-12-04","cited_by_count":13,"area":null},{"id":"2405.14117","title":"Knowledge Localization: Mission Not Accomplished? Enter Query Localization!","created":"2024-05-23","cited_by_count":13,"area":null},{"id":"2503.12781","title":"SAM2 for Image and Video Segmentation: A Comprehensive Survey","created":"2025-03-17","cited_by_count":13,"area":null},{"id":"2306.02240","title":"ProTeCt: Prompt Tuning for Taxonomic Open Set Classification","created":"2023-06-04","cited_by_count":12,"area":null},{"id":"2411.16746","title":"LoBAM: LoRA-Based Backdoor Attack on Model Merging","created":"2024-11-23","cited_by_count":12,"area":null},{"id":"2310.11417","title":"VcT: Visual change Transformer for Remote Sensing Image Change Detection","created":"2023-10-17","cited_by_count":11,"area":null},{"id":"2401.02643","title":"Training and Serving System of Foundation Models: A Comprehensive Survey","created":"2024-01-05","cited_by_count":11,"area":null},{"id":"2602.13191","title":"CoPE-VideoLM: Leveraging Codec Primitives For Efficient Video Language Modeling","created":"2026-02-13","cited_by_count":11,"area":null},{"id":"2304.10091","title":"Learning CLIP Guided Visual-Text Fusion Transformer for Video-based Pedestrian Attribute Recognition","created":"2023-04-20","cited_by_count":10,"area":null},{"id":"2412.00767","title":"Prompt as Free Lunch: Enhancing Diversity in Source-Free Cross-domain Few-shot Learning through Semantic-Guided Prompting","created":"2024-12-01","cited_by_count":10,"area":null},{"id":"2507.11405","title":"DCR: Quantifying Data Contamination in LLMs Evaluation","created":"2025-07-15","cited_by_count":10,"area":null},{"id":"2404.00983","title":"Continual Learning for Smart City: A Survey","created":"2024-04-01","cited_by_count":9,"area":null},{"id":"2406.17145","title":"GraphPipe: Improving Performance and Scalability of DNN Training with Graph Pipeline Parallelism","created":"2024-06-24","cited_by_count":9,"area":null},{"id":"2503.09091","title":"Multi-Modal Foundation Models for Computational Pathology: A Survey","created":"2025-03-12","cited_by_count":9,"area":null},{"id":"2305.06472","title":"ChatGPT-Like Large-Scale Foundation Models for Prognostics and Health Management: A Survey and Roadmaps","created":"2023-05-10","cited_by_count":8,"area":null},{"id":"2506.09385","title":"ReID5o: Achieving Omni Multi-modal Person Re-identification in a Single Model","created":"2025-06-11","cited_by_count":8,"area":null},{"id":"2312.09812","title":"Structural Information Guided Multimodal Pre-training for Vehicle-centric Perception","created":"2023-12-15","cited_by_count":7,"area":null},{"id":"2404.17926","title":"Pre-training on High Definition X-ray Images: An Experimental Study","created":"2024-04-27","cited_by_count":7,"area":null},{"id":"2406.09988","title":"Details Make a Difference: Object State-Sensitive Neurorobotic Task Planning","created":"2024-06-14","cited_by_count":7,"area":null},{"id":"2404.17929","title":"Spatio-Temporal Side Tuning Pre-trained Foundation Models for Video-based Pedestrian Attribute Recognition","created":"2024-04-27","cited_by_count":6,"area":null},{"id":"2407.17689","title":"SAM-MIL: A Spatial Contextual Aware Multiple Instance Learning Approach for Whole Slide Image Classification","created":"2024-07-25","cited_by_count":6,"area":null},{"id":"2506.05191","title":"MokA: Multimodal Low-Rank Adaptation for MLLMs","created":"2025-06-05","cited_by_count":6,"area":null},{"id":"2601.03115","title":"Discovering and Causally Validating Emotion-Sensitive Neurons in Large Audio-Language Models","created":"2026-01-06","cited_by_count":6,"area":null},{"id":"2303.14778","title":"RGBT Tracking via Progressive Fusion Transformer with Dynamically Guided Learning","created":"2023-03-26","cited_by_count":5,"area":null},{"id":"2312.11128","title":"Unleashing the Power of CNN and Transformer for Balanced RGB-Event Video Recognition","created":"2023-12-18","cited_by_count":5,"area":null},{"id":"2407.17533","title":"SFPrompt: Communication-Efficient Split Federated Fine-Tuning for Large Pre-Trained Models over Resource-Limited Devices","created":"2024-07-24","cited_by_count":5,"area":null},{"id":"2407.17616","title":"Pretraining a Neural Operator in Lower Dimensions","created":"2024-07-24","cited_by_count":5,"area":null},{"id":"2408.08315","title":"Segment Anything for Videos: A Systematic Survey","created":"2024-07-31","cited_by_count":5,"area":null},{"id":"2411.10070","title":"Step-wise Distribution Alignment Guided Style Prompt Tuning for Source-free Cross-domain Few-shot Learning","created":"2024-11-15","cited_by_count":5,"area":null},{"id":"2502.03749","title":"PINS: Proximal Iterations with Sparse Newton and Sinkhorn for Optimal Transport","created":"2025-02-06","cited_by_count":5,"area":null},{"id":"2309.15857","title":"A Survey on Image-text Multimodal Models","created":"2023-09-23","cited_by_count":4,"area":null},{"id":"2404.13239","title":"Beyond Pixel-Wise Supervision for Medical Image Segmentation: From Traditional Models to Foundation Models","created":"2024-04-20","cited_by_count":4,"area":null},{"id":"2407.19886","title":"A Unified Graph Transformer for Overcoming Isolations in Multi-modal Recommendation","created":"2024-07-29","cited_by_count":4,"area":null},{"id":"2412.12468","title":"Transferable and Forecastable User Targeting Foundation Model","created":"2024-12-17","cited_by_count":4,"area":null},{"id":"2501.09705","title":"Practical Continual Forgetting for Pre-trained Vision Models","created":"2025-01-16","cited_by_count":4,"area":null},{"id":"2507.13659","title":"When Person Re-Identification Meets Event Camera: A Benchmark Dataset and An Attribute-guided Re-Identification Framework","created":"2025-07-18","cited_by_count":4,"area":null},{"id":"2508.03426","title":"R2GenKG: Hierarchical Multi-modal Knowledge Graph for LLM-based Radiology Report Generation","created":"2025-08-05","cited_by_count":4,"area":null},{"id":"2602.04920","title":"CyIN: Cyclic Informative Latent Space for Bridging Complete and Incomplete Multimodal Learning","created":"2026-02-04","cited_by_count":4,"area":null},{"id":"2305.19205","title":"AMatFormer: Efficient Feature Matching via Anchor Matching Transformer","created":"2023-05-30","cited_by_count":3,"area":null},{"id":"2311.17945","title":"Contrastive Vision-Language Alignment Makes Efficient Instruction Learner","created":"2023-11-29","cited_by_count":3,"area":null},{"id":"2401.17803","title":"SU-SAM: A Simple Unified Framework for Adapting Segment Anything Model in Underperformed Scenes","created":"2024-01-31","cited_by_count":3,"area":null},{"id":"2406.18845","title":"Retain, Blend, and Exchange: A Quality-aware Spatial-Stereo Fusion Approach for Event Stream Recognition","created":"2024-06-27","cited_by_count":3,"area":null},{"id":"2410.16239","title":"MoRE: Multi-Modal Contrastive Pre-training with Transformers on X-Rays, ECGs, and Diagnostic Report","created":"2024-10-21","cited_by_count":3,"area":null},{"id":"2505.12903","title":"Towards Low-Latency Event Stream-based Visual Object Tracking: A Slow-Fast Approach","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2308.11994","title":"Progressive Feature Mining and External Knowledge-Assisted Text-Pedestrian Image Retrieval","created":"2023-08-23","cited_by_count":2,"area":null},{"id":"2401.00031","title":"Self-supervised Pretraining for Decision Foundation Model: Formulation, Pipeline and Challenges","created":"2023-12-29","cited_by_count":2,"area":null},{"id":"2412.13071","title":"CLASP: Contrastive Language-Speech Pretraining for Multilingual Multimodal Information Retrieval","created":"2024-12-17","cited_by_count":2,"area":null},{"id":"2502.05615","title":"XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion","created":"2025-02-08","cited_by_count":2,"area":null},{"id":"2502.06836","title":"CAST: Cross Attention based multimodal fusion of Structure and Text for materials property prediction","created":"2025-02-06","cited_by_count":2,"area":null},{"id":"2502.19513","title":"Mixtraining: A Better Trade-Off Between Compute and Performance","created":"2025-02-26","cited_by_count":2,"area":null},{"id":"2503.10287","title":"MACS: Multi-source Audio-to-image Generation with Contextual Significance and Semantic Alignment","created":"2025-03-13","cited_by_count":2,"area":null},{"id":"2508.03776","title":"Revisiting Heat Flux Analysis of Tungsten Monoblock Divertor on EAST using Physics-Informed Neural Network","created":"2025-08-05","cited_by_count":2,"area":null},{"id":"2508.04050","title":"DOMR: Establishing Cross-View Segmentation via Dense Object Matching","created":"2025-08-06","cited_by_count":2,"area":null},{"id":"2410.07857","title":"SNN-PAR: Energy Efficient Pedestrian Attribute Recognition via Spiking Neural Networks","created":"2024-10-10","cited_by_count":1,"area":null},{"id":"2411.17898","title":"On the ERM Principle in Meta-Learning","created":"2024-11-26","cited_by_count":1,"area":null},{"id":"2508.02411","title":"HGTS-Former: Hierarchical HyperGraph Transformer for Multivariate Time Series Analysis","created":"2025-08-04","cited_by_count":1,"area":null},{"id":"2308.16474","title":"Enhancing Subtask Performance of Multi-modal Large Language Model","created":"2023-08-31","cited_by_count":0,"area":null},{"id":"2310.07093","title":"Argumentative Stance Prediction: An Exploratory Study on Multimodality and Few-Shot Learning","created":"2023-10-11","cited_by_count":0,"area":null},{"id":"2411.15251","title":"Optimized Vessel Segmentation: A Structure-Agnostic Approach with Small Vessel Enhancement and Morphological Correction","created":"2024-11-22","cited_by_count":0,"area":null},{"id":"2502.02234","title":"Mask-informed Deep Contrastive Incomplete Multi-view Clustering","created":"2025-02-04","cited_by_count":0,"area":null},{"id":"2512.20097","title":"A Novel Graph-Sequence Learning Model for Inductive Text Classification","created":"2025-12-23","cited_by_count":0,"area":null},{"id":"2603.19565","title":"PFM-VEPAR: Prompting Foundation Models for RGB-Event Camera based Pedestrian Attribute Recognition","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2606.09430","title":"LargeMonitor: Monitoring Online Task-Free Continual Learning via Large Pretrained Models","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.29357","title":"Dynamic Parsing and Updating Natural Language Specification using VLMs for Robust Vision-Language Tracking","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2606.31574","title":"Temperature Field Reconstruction of Tungsten Monoblock Divertor on EAST using Physics-aware Neural Operator Transformer","created":"2026-06-30","cited_by_count":0,"area":null}],"next_cursor":null}