{"total":160,"rows":[{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839,"area":"mllm"},{"id":"2403.14608","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","created":"2024-03-21","cited_by_count":656,"area":null},{"id":"2308.16911","title":"PointLLM: Empowering Large Language Models to Understand Point Clouds","created":"2023-08-31","cited_by_count":333,"area":null},{"id":"2310.06773","title":"Uni3D: Exploring Unified 3D Representation at Scale","created":"2023-10-10","cited_by_count":237,"area":null},{"id":"2311.18482","title":"Language Embedded 3D Gaussians for Open-Vocabulary Scene Understanding","created":"2023-11-30","cited_by_count":208,"area":null},{"id":"2305.08275","title":"ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding","created":"2023-05-14","cited_by_count":202,"area":null},{"id":"2309.00615","title":"Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following","created":"2023-09-01","cited_by_count":194,"area":null},{"id":"2211.11682","title":"PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning","created":"2022-11-21","cited_by_count":187,"area":null},{"id":"2305.10764","title":"OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding","created":"2023-05-18","cited_by_count":184,"area":null},{"id":"2312.16649","title":"Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detection","created":"2023-12-27","cited_by_count":182,"area":"diffusion"},{"id":"2211.16312","title":"PLA: Language-Driven Open-Vocabulary 3D Scene Understanding","created":"2022-11-29","cited_by_count":177,"area":null},{"id":"2306.15880","title":"Towards Open Vocabulary Learning: A Survey","created":"2023-06-28","cited_by_count":166,"area":null},{"id":"2302.02318","title":"Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining","created":"2023-02-05","cited_by_count":164,"area":null},{"id":"2406.02058","title":"OpenGaussian: Towards Point-Level 3D Gaussian-based Open Vocabulary Understanding","created":"2024-06-04","cited_by_count":145,"area":null},{"id":"2402.17766","title":"ShapeLLM: Universal 3D Object Understanding for Embodied Interaction","created":"2024-02-27","cited_by_count":137,"area":"mllm"},{"id":"2304.06906","title":"Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding","created":"2023-04-14","cited_by_count":113,"area":null},{"id":"2408.09647","title":"C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake Detection","created":"2024-08-19","cited_by_count":113,"area":null},{"id":"2411.07184","title":"SAMPart3D: Segment Any Part in 3D Objects","created":"2024-11-11","cited_by_count":97,"area":null},{"id":"2304.00962","title":"RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene Understanding","created":"2023-04-03","cited_by_count":94,"area":null},{"id":"2303.04748","title":"CLIP-FO3D: Learning Free Open-world 3D Scene Representations from 2D Dense CLIP","created":"2023-03-08","cited_by_count":89,"area":null},{"id":"2309.00616","title":"OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance Segmentation","created":"2023-09-01","cited_by_count":82,"area":null},{"id":"2401.00988","title":"Holistic Autonomous Driving Understanding by Bird's-Eye-View Injected Multi-Modal Large Models","created":"2024-01-02","cited_by_count":76,"area":"mllm"},{"id":"2312.02980","title":"GPT4Point: A Unified Framework for Point-Language Understanding and Generation","created":"2023-12-05","cited_by_count":71,"area":"mllm"},{"id":"2212.00836","title":"UniT3D: A Unified Transformer for 3D Dense Captioning and Visual Grounding","created":"2022-12-01","cited_by_count":69,"area":null},{"id":"2303.12417","title":"CLIP$^2$: Contrastive Language-Image-Point Pretraining from Real-World Point Cloud Data","created":"2023-03-22","cited_by_count":69,"area":null},{"id":"2304.07221","title":"Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models","created":"2023-04-14","cited_by_count":68,"area":null},{"id":"2312.17232","title":"Segment3D: Learning Fine-Grained Class-Agnostic 3D Segmentation without Manual Labels","created":"2023-12-28","cited_by_count":64,"area":null},{"id":"2403.12532","title":"UniBind: LLM-Augmented Unified and Balanced Representation Space to Bind Them All","created":"2024-03-19","cited_by_count":49,"area":null},{"id":"2311.14960","title":"Point Cloud Pre-training with Diffusion Models","created":"2023-11-25","cited_by_count":47,"area":"diffusion"},{"id":"2501.13787","title":"Parameter-Efficient Fine-Tuning for Foundation Models","created":"2025-01-23","cited_by_count":45,"area":null},{"id":"2406.01476","title":"DreamPhysics: Learning Physics-Based 3D Dynamics with Video Diffusion Priors","created":"2024-06-03","cited_by_count":41,"area":"diffusion"},{"id":"2312.06439","title":"DreamControl: Control-Based Text-to-3D Generation with 3D Self-Prior","created":"2023-12-11","cited_by_count":39,"area":"diffusion"},{"id":"2308.00353","title":"Lowis3D: Language-Driven Open-World Instance-Level 3D Scene Understanding","created":"2023-08-01","cited_by_count":38,"area":null},{"id":"2403.20079","title":"SGD: Street View Synthesis with Gaussian Splatting and Diffusion Prior","created":"2024-03-29","cited_by_count":36,"area":"wm"},{"id":"2411.19235","title":"InstanceGaussian: Appearance-Semantic Joint Gaussian Representation for 3D Instance-Level Perception","created":"2024-11-28","cited_by_count":35,"area":null},{"id":"2303.08134","title":"Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis","created":"2023-03-14","cited_by_count":34,"area":null},{"id":"2212.06858","title":"LidarCLIP or: How I Learned to Talk to Point Clouds","created":"2022-12-13","cited_by_count":33,"area":null},{"id":"2407.11351","title":"Learning Modality-agnostic Representation for Semantic Segmentation from Any Modalities","created":"2024-07-16","cited_by_count":31,"area":null},{"id":"2402.18490","title":"TAMM: TriAdapter Multi-Modal Learning for 3D Shape Understanding","created":"2024-02-28","cited_by_count":27,"area":null},{"id":"2404.01491","title":"SUGAR: Pre-training 3D Visual Representations for Robotics","created":"2024-04-01","cited_by_count":26,"area":null},{"id":"2305.10714","title":"Vision-Language Pre-training with Object Contrastive Learning for 3D Scene Understanding","created":"2023-05-18","cited_by_count":25,"area":"mllm"},{"id":"2309.09456","title":"Object2Scene: Putting Objects in Context for Open-Vocabulary 3D Detection","created":"2023-09-18","cited_by_count":24,"area":null},{"id":"2305.15957","title":"DiffCLIP: Leveraging Stable Diffusion for Language Grounded 3D Classification","created":"2023-05-25","cited_by_count":23,"area":"diffusion"},{"id":"2403.10801","title":"Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples","created":"2024-03-16","cited_by_count":21,"area":null},{"id":"2403.13556","title":"Find n' Propagate: Open-Vocabulary 3D Object Detection in Urban Environments","created":"2024-03-20","cited_by_count":21,"area":null},{"id":"2510.13219","title":"Prompt-based Adaptation in Large-scale Vision Models: A Survey","created":"2025-10-15","cited_by_count":21,"area":null},{"id":"2305.19812","title":"A Survey of Label-Efficient Deep Learning for 3D Point Clouds","created":"2023-05-31","cited_by_count":20,"area":null},{"id":"2405.08458","title":"Rethinking Prior Information Generation with CLIP for Few-Shot Segmentation","created":"2024-05-14","cited_by_count":20,"area":null},{"id":"2405.16108","title":"OmniBind: Teach to Build Unequal-Scale Modality Interaction for Omni-Bind of All","created":"2024-05-25","cited_by_count":20,"area":null},{"id":"2502.00848","title":"RealRAG: Retrieval-augmented Realistic Image Generation via Self-reflective Contrastive Learning","created":"2025-02-02","cited_by_count":20,"area":"rag"},{"id":"2212.04098","title":"EPCL: Frozen CLIP Transformer is An Efficient Point Cloud Encoder","created":"2022-12-08","cited_by_count":18,"area":null},{"id":"2311.01734","title":"Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-training","created":"2023-11-03","cited_by_count":18,"area":null},{"id":"2408.16768","title":"SAM2Point: Segment Any 3D as Videos in Zero-shot and Promptable Manners","created":"2024-08-29","cited_by_count":18,"area":null},{"id":"2407.13362","title":"Open Vocabulary 3D Scene Understanding via Geometry Guided Self-Distillation","created":"2024-07-18","cited_by_count":17,"area":"distill"},{"id":"2503.16282","title":"Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Model","created":"2025-03-20","cited_by_count":17,"area":"mllm"},{"id":"2401.11395","title":"UniM-OV3D: Uni-Modality Open-Vocabulary 3D Scene Understanding with Fine-Grained Feature Representation","created":"2024-01-21","cited_by_count":15,"area":null},{"id":"2406.11189","title":"Frozen CLIP: A Strong Backbone for Weakly Supervised Semantic Segmentation","created":"2024-06-17","cited_by_count":15,"area":null},{"id":"2403.04294","title":"A$^{3}$lign-DFER: Pioneering Comprehensive Dynamic Affective Alignment for Dynamic Facial Expression Recognition with CLIP","created":"2024-03-07","cited_by_count":14,"area":null},{"id":"2312.02244","title":"Geometrically-driven Aggregation for Zero-shot 3D Point Cloud Understanding","created":"2023-12-04","cited_by_count":13,"area":"mllm"},{"id":"2503.16707","title":"Cross-Modal and Uncertainty-Aware Agglomeration for Open-Vocabulary 3D Scene Understanding","created":"2025-03-20","cited_by_count":13,"area":"mllm"},{"id":"2505.04119","title":"GAPrompt: Geometry-Aware Point Cloud Prompt for 3D Vision Model","created":"2025-05-07","cited_by_count":13,"area":null},{"id":"2308.10421","title":"UniM$^2$AE: Multi-modal Masked Autoencoders with Unified 3D Representation for 3D Perception in Autonomous Driving","created":"2023-08-21","cited_by_count":12,"area":null},{"id":"2310.15676","title":"Recent Advances in Multi-modal 3D Intelligence: A Comprehensive Survey and Evaluation","created":"2023-10-24","cited_by_count":12,"area":null},{"id":"2406.11579","title":"Duoduo CLIP: Efficient 3D Understanding with Multi-View Images","created":"2024-06-17","cited_by_count":12,"area":null},{"id":"2307.09815","title":"LDP: Language-driven Dual-Pixel Image Defocus Deblurring Network","created":"2023-07-19","cited_by_count":11,"area":null},{"id":"2311.18402","title":"MV-CLIP: Multi-View CLIP for Zero-shot 3D Shape Recognition","created":"2023-11-30","cited_by_count":11,"area":null},{"id":"2404.11605","title":"VG4D: Vision-Language Model Goes 4D Video Recognition","created":"2024-04-17","cited_by_count":11,"area":"mllm"},{"id":"2512.08330","title":"PointDico: Contrastive 3D Representation Learning Guided by Diffusion Models","created":"2025-12-09","cited_by_count":11,"area":"diffusion"},{"id":"2408.15966","title":"More Text, Less Point: Towards 3D Data-Efficient Point-Language Understanding","created":"2024-08-28","cited_by_count":10,"area":null},{"id":"2411.14869","title":"BIP3D: Bridging 2D Images and 3D Perception for Embodied Intelligence","created":"2024-11-22","cited_by_count":10,"area":null},{"id":"2309.17175","title":"TextField3D: Towards Enhancing Open-Vocabulary 3D Generation with Noisy Text Fields","created":"2023-09-29","cited_by_count":9,"area":null},{"id":"2312.03026","title":"Uni3DL: Unified Model for 3D and Language Understanding","created":"2023-12-05","cited_by_count":9,"area":null},{"id":"2404.16538","title":"OpenDlign: Open-World Point Cloud Understanding with Depth-Aligned Images","created":"2024-04-25","cited_by_count":9,"area":"mllm"},{"id":"2411.18066","title":"GLS: Geometry-aware 3D Language Gaussian Splatting","created":"2024-11-27","cited_by_count":9,"area":null},{"id":"2502.17053","title":"PointSea: Point Cloud Completion via Self-structure Augmentation","created":"2025-02-24","cited_by_count":9,"area":null},{"id":"2502.19128","title":"SCA3D: Enhancing Cross-modal 3D Retrieval via 3D Shape and Caption Paired Data Augmentation","created":"2025-02-26","cited_by_count":9,"area":null},{"id":"2404.00931","title":"GOV-NeSF: Generalizable Open-Vocabulary Neural Semantic Fields","created":"2024-04-01","cited_by_count":8,"area":"mllm"},{"id":"2503.10529","title":"PiSA: A Self-Augmented Data Engine and Training Strategy for 3D Understanding with Large Models","created":"2025-03-13","cited_by_count":8,"area":"mllm"},{"id":"2506.05318","title":"Does Your 3D Encoder Really Work? When Pretrain-SFT from 2D VLMs Meets 3D VLMs","created":"2025-06-05","cited_by_count":8,"area":"mllm"},{"id":"2310.14374","title":"OV-VG: A Benchmark for Open-Vocabulary Visual Grounding","created":"2023-10-22","cited_by_count":7,"area":null},{"id":"2412.19142","title":"CLIP-GS: Unifying Vision-Language Representation with 3D Gaussian Splatting","created":"2024-12-26","cited_by_count":7,"area":null},{"id":"2405.04103","title":"COM3D: Leveraging Cross-View Correspondence and Cross-Modal Mining for 3D Retrieval","created":"2024-05-07","cited_by_count":6,"area":null},{"id":"2407.14007","title":"Multi-modal Relation Distillation for Unified 3D Representation Learning","created":"2024-07-19","cited_by_count":6,"area":null},{"id":"2407.16682","title":"SAM-CP: Marrying SAM with Composable Prompts for Versatile Segmentation","created":"2024-07-23","cited_by_count":6,"area":null},{"id":"2401.07572","title":"Exploiting GPT-4 Vision for Zero-shot Point Cloud Understanding","created":"2024-01-15","cited_by_count":5,"area":null},{"id":"2502.17860","title":"UniGS: Unified Language-Image-3D Pretraining with Gaussian Splatting","created":"2025-02-25","cited_by_count":5,"area":null},{"id":"2502.19782","title":"Open-Vocabulary Semantic Part Segmentation of 3D Human","created":"2025-02-27","cited_by_count":5,"area":null},{"id":"2505.16663","title":"CoNav: Collaborative Cross-Modal Reasoning for Embodied Navigation","created":"2025-05-22","cited_by_count":5,"area":"lr"},{"id":"2507.21489","title":"Describe, Adapt and Combine: Empowering CLIP Encoders for Open-set 3D Object Retrieval","created":"2025-07-29","cited_by_count":5,"area":null},{"id":"2312.02483","title":"EtC: Temporal Boundary Expand then Clarify for Weakly Supervised Video Grounding with Multimodal Large Language Model","created":"2023-12-05","cited_by_count":4,"area":"mllm"},{"id":"2312.07039","title":"Open-Pose 3D Zero-Shot Learning: Benchmark and Challenges","created":"2023-12-12","cited_by_count":4,"area":null},{"id":"2410.22306","title":"Multi-Object 3D Grounding with Dynamic Modules and Language-Informed Spatial Attention","created":"2024-10-29","cited_by_count":4,"area":null},{"id":"2504.06908","title":"UKBOB: One Billion MRI Labeled Masks for Generalizable 3D Medical Image Segmentation","created":"2025-04-09","cited_by_count":4,"area":null},{"id":"2507.19908","title":"TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking","created":"2025-07-26","cited_by_count":4,"area":null},{"id":"2511.16567","title":"POMA-3D: The Point Map Way to 3D Scene Understanding","created":"2025-11-20","cited_by_count":4,"area":null},{"id":"2602.24181","title":"A Mixed Diet Makes DINO An Omnivorous Vision Encoder","created":"2026-02-27","cited_by_count":4,"area":null},{"id":"2404.10146","title":"Cross-Modal Self-Training: Aligning Images and Pointclouds to Learn Classification without Labels","created":"2024-04-15","cited_by_count":3,"area":"mllm"},{"id":"2404.19168","title":"PEVA-Net: Prompt-Enhanced View Aggregation Network for Zero/Few-Shot Multi-View 3D Shape Recognition","created":"2024-04-30","cited_by_count":3,"area":"mllm"},{"id":"2408.03790","title":"Vision-Language Guidance for LiDAR-based Unsupervised 3D Object Detection","created":"2024-08-07","cited_by_count":3,"area":null},{"id":"2410.05799","title":"SeeClear: Semantic Distillation Enhances Pixel Condensation for Video Super-Resolution","created":"2024-10-08","cited_by_count":3,"area":"diffusion"}],"next_cursor":"100"}