{"total":137,"rows":[{"id":"2405.14093","title":"A Survey on Vision-Language-Action Models for Embodied AI","created":"2024-05-23","cited_by_count":279,"area":"vla"},{"id":"2507.04447","title":"DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge","created":"2025-07-06","cited_by_count":213,"area":"vla"},{"id":"2406.16855","title":"DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation","created":"2024-06-24","cited_by_count":131,"area":null},{"id":"2602.10098","title":"VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model","created":"2026-02-10","cited_by_count":118,"area":"wm"},{"id":"2405.10370","title":"Grounded 3D-LLM with Referent Tokens","created":"2024-05-16","cited_by_count":115,"area":null},{"id":"2506.03135","title":"OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models","created":"2025-06-03","cited_by_count":114,"area":"lr"},{"id":"2501.01428","title":"GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models","created":"2025-01-02","cited_by_count":109,"area":"mllm"},{"id":"2403.01439","title":"Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysis","created":"2024-03-03","cited_by_count":53,"area":null},{"id":"2502.13143","title":"SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation","created":"2025-02-18","cited_by_count":46,"area":"lr"},{"id":"2509.08643","title":"X-Part: high fidelity and structure coherent shape decomposition","created":"2025-09-10","cited_by_count":44,"area":null},{"id":"2410.08114","title":"Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learning","created":"2024-10-10","cited_by_count":43,"area":null},{"id":"2509.18905","title":"How Far are VLMs from Visual Spatial Intelligence? A Benchmark-Driven Perspective","created":"2025-09-23","cited_by_count":43,"area":"lr"},{"id":"2406.09401","title":"MMScan: A Multi-Modal 3D Scene Dataset with Hierarchical Grounded Language Annotations","created":"2024-06-13","cited_by_count":40,"area":null},{"id":"2411.16856","title":"SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE","created":"2024-11-25","cited_by_count":39,"area":"mllm"},{"id":"2506.01853","title":"ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understanding","created":"2025-06-02","cited_by_count":38,"area":"mllm"},{"id":"2406.07549","title":"A3VLM: Actionable Articulation-Aware Vision Language Model","created":"2024-06-11","cited_by_count":33,"area":"mllm"},{"id":"2404.07984","title":"View Selection for 3D Captioning via Diffusion Ranking","created":"2024-04-11","cited_by_count":32,"area":null},{"id":"2502.20041","title":"3D-AffordanceLLM: Harnessing Large Language Models for Open-Vocabulary Affordance Detection in 3D Worlds","created":"2025-02-27","cited_by_count":30,"area":null},{"id":"2405.17427","title":"Reason3D: Searching and Reasoning 3D Segmentation via Large Language Model","created":"2024-05-27","cited_by_count":28,"area":"lr"},{"id":"2506.03642","title":"Spatial Understanding from Videos: Structured Prompts Meet Simulation Data","created":"2025-06-04","cited_by_count":28,"area":null},{"id":"2510.20155","title":"PartNeXt: A Next-Generation Dataset for Fine-Grained and Hierarchical 3D Part Understanding","created":"2025-10-23","cited_by_count":26,"area":null},{"id":"2503.22420","title":"Unveiling the Mist over 3D Vision-Language Understanding: Object-centric Evaluation with Chain-of-Analysis","created":"2025-03-28","cited_by_count":23,"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":"2507.02747","title":"DexVLG: Dexterous Vision-Language-Grasp Model at Scale","created":"2025-07-03","cited_by_count":20,"area":"vla"},{"id":"2410.07155","title":"Trans4D: Realistic Geometry-Aware Transition for Compositional Text-to-4D Synthesis","created":"2024-10-09","cited_by_count":19,"area":"diffusion"},{"id":"2510.13800","title":"Reasoning in Space via Grounding in the World","created":"2025-10-15","cited_by_count":19,"area":"lr"},{"id":"2412.00174","title":"SOLAMI: Social Vision-Language-Action Modeling for Immersive Interaction with 3D Autonomous Characters","created":"2024-11-29","cited_by_count":18,"area":null},{"id":"2412.01550","title":"SeqAfford: Sequential 3D Affordance Reasoning via Multimodal Large Language Model","created":"2024-12-02","cited_by_count":18,"area":"lr"},{"id":"2505.18947","title":"OpenHOI: Open-World Hand-Object Interaction Synthesis with Multimodal Large Language Model","created":"2025-05-25","cited_by_count":17,"area":"mllm"},{"id":"2502.09620","title":"Exploring the Potential of Encoder-free Architectures in 3D LMMs","created":"2025-02-13","cited_by_count":16,"area":"mllm"},{"id":"2408.11567","title":"Positional Prompt Tuning for Efficient 3D Representation Learning","created":"2024-08-21","cited_by_count":15,"area":null},{"id":"2409.00353","title":"RI-MAE: Rotation-Invariant Masked AutoEncoders for Self-Supervised Point Cloud Representation Learning","created":"2024-08-31","cited_by_count":15,"area":null},{"id":"2410.10084","title":"PointNet with KAN versus PointNet with MLP for 3D Classification and Segmentation of Point Sets","created":"2024-10-14","cited_by_count":15,"area":null},{"id":"2502.15786","title":"MindLLM: A Subject-Agnostic and Versatile Model for fMRI-to-Text Decoding","created":"2025-02-18","cited_by_count":14,"area":null},{"id":"2504.16023","title":"PointLoRA: Low-Rank Adaptation with Token Selection for Point Cloud Learning","created":"2025-04-22","cited_by_count":14,"area":null},{"id":"2411.14491","title":"A Survey on Human-Centric LLMs","created":"2024-11-20","cited_by_count":13,"area":null},{"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":"2406.11579","title":"Duoduo CLIP: Efficient 3D Understanding with Multi-View Images","created":"2024-06-17","cited_by_count":12,"area":null},{"id":"2511.13211","title":"3DAlign-DAER: Dynamic Attention Policy and Efficient Retrieval Strategy for Fine-grained 3D-Text Alignment at Scale","created":"2025-11-17","cited_by_count":12,"area":null},{"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":"2504.19500","title":"Masked Point-Entity Contrast for Open-Vocabulary 3D Scene Understanding","created":"2025-04-28","cited_by_count":10,"area":null},{"id":"2505.06176","title":"MonetGPT: Solving Puzzles Enhances MLLMs' Image Retouching Skills","created":"2025-05-09","cited_by_count":10,"area":null},{"id":"2512.10949","title":"Are We Ready for RL in Text-to-3D Generation? A Progressive Investigation","created":"2025-12-11","cited_by_count":10,"area":null},{"id":"2512.12768","title":"CoRe3D: Collaborative Reasoning as a Foundation for 3D Intelligence","created":"2025-12-14","cited_by_count":10,"area":"mllm"},{"id":"2405.18937","title":"Kestrel: 3D Multimodal LLM for Part-Aware Grounded Description","created":"2024-05-29","cited_by_count":9,"area":"mllm"},{"id":"2411.19774","title":"PerLA: Perceptive 3D Language Assistant","created":"2024-11-29","cited_by_count":9,"area":null},{"id":"2507.00490","title":"Just Noticeable Difference for Large Multimodal Models","created":"2025-07-01","cited_by_count":9,"area":"mllm"},{"id":"2411.16761","title":"Is 'Right' Right? Enhancing Object Orientation Understanding in Multimodal Large Language Models through Egocentric Instruction Tuning","created":"2024-11-24","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":"2507.18678","title":"Towards Scalable Spatial Intelligence via 2D-to-3D Data Lifting","created":"2025-07-24","cited_by_count":8,"area":null},{"id":"2603.01142","title":"ArtLLM: Generating Articulated Assets via 3D LLM","created":"2026-03-01","cited_by_count":8,"area":null},{"id":"2511.13647","title":"Part-X-MLLM: Part-aware 3D Multimodal Large Language Model","created":"2025-11-17","cited_by_count":7,"area":"mllm"},{"id":"2503.12955","title":"HIS-GPT: Towards 3D Human-In-Scene Multimodal Understanding","created":"2025-03-17","cited_by_count":6,"area":null},{"id":"2503.18368","title":"MoST: Efficient Monarch Sparse Tuning for 3D Representation Learning","created":"2025-03-24","cited_by_count":6,"area":null},{"id":"2506.09952","title":"UniPre3D: Unified Pre-training of 3D Point Cloud Models with Cross-Modal Gaussian Splatting","created":"2025-06-11","cited_by_count":6,"area":null},{"id":"2510.09320","title":"Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance for Self-supervised Monocular Depth Estimation","created":"2025-10-10","cited_by_count":6,"area":null},{"id":"2501.01119","title":"Leverage Cross-Attention for End-to-End Open-Vocabulary Panoptic Reconstruction","created":"2025-01-02","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":"2602.03890","title":"4DPC$^2$hat: Towards Dynamic Point Cloud Understanding with Failure-Aware Bootstrapping","created":"2026-02-03","cited_by_count":5,"area":"mllm"},{"id":"2409.10350","title":"Point2Graph: An End-to-end Point Cloud-based 3D Open-Vocabulary Scene Graph for Robot Navigation","created":"2024-09-16","cited_by_count":4,"area":null},{"id":"2503.20663","title":"ARMO: Autoregressive Rigging for Multi-Category Objects","created":"2025-03-26","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":"2605.00663","title":"Affordance Agent Harness: Verification-Gated Skill Orchestration","created":"2026-05-01","cited_by_count":4,"area":null},{"id":"2503.12834","title":"PASTA: Part-Aware Sketch-to-3D Shape Generation with Text-Aligned Prior","created":"2025-03-17","cited_by_count":3,"area":null},{"id":"2506.10816","title":"Occlusion-Aware 3D Hand-Object Pose Estimation with Masked AutoEncoders","created":"2025-06-12","cited_by_count":3,"area":null},{"id":"2510.04978","title":"Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI","created":"2025-10-06","cited_by_count":3,"area":"wm"},{"id":"2511.19119","title":"MonoSR: Open-Vocabulary Spatial Reasoning from Monocular Images","created":"2025-11-24","cited_by_count":3,"area":"lr"},{"id":"2512.15160","title":"EagleVision: A Dual-Stage Framework with BEV-grounding-based Chain-of-Thought for Spatial Intelligence","created":"2025-12-17","cited_by_count":3,"area":"lr"},{"id":"2602.22284","title":"BrepCoder: A Unified Multimodal Large Language Model for Multi-task B-rep Reasoning","created":"2026-02-25","cited_by_count":3,"area":"lr"},{"id":"2605.16745","title":"EVA01: Unified Native 3D Understanding and Generation via Mixture-of-Transformers","created":"2026-05-16","cited_by_count":3,"area":"mllm"},{"id":"2412.10908","title":"Do large language vision models understand 3D shapes?","created":"2024-12-14","cited_by_count":2,"area":"mllm"},{"id":"2502.14142","title":"Token Adaptation via Side Graph Convolution for Efficient Fine-tuning of 3D Point Cloud Transformers","created":"2025-02-19","cited_by_count":2,"area":null},{"id":"2506.08194","title":"GIQ: Benchmarking 3D Geometric Reasoning of Vision Foundation Models with Simulated and Real Polyhedra","created":"2025-06-09","cited_by_count":2,"area":"lr"},{"id":"2507.09334","title":"Fast3D: Accelerating 3D Multi-modal Large Language Models for Efficient 3D Scene Understanding","created":"2025-07-12","cited_by_count":2,"area":"mllm"},{"id":"2509.07825","title":"Point Linguist Model: Segment Any Object via Bridged Large 3D-Language Model","created":"2025-09-09","cited_by_count":2,"area":null},{"id":"2510.21746","title":"Avi: Action from Volumetric Inference","created":"2025-10-07","cited_by_count":2,"area":"lr"},{"id":"2601.03030","title":"Flow Matching and Diffusion Models via PointNet for Generating Fluid Fields on Irregular Geometries","created":"2026-01-06","cited_by_count":2,"area":"diffusion"},{"id":"2601.16538","title":"OnlineSI: Taming Large Language Model for Online 3D Understanding and Grounding","created":"2026-01-23","cited_by_count":2,"area":"lr"},{"id":"2602.09638","title":"VideoAfford: Grounding 3D Affordance from Human-Object-Interaction Videos via Multimodal Large Language Model","created":"2026-02-10","cited_by_count":2,"area":"mllm"},{"id":"2603.00412","title":"PointAlign: Feature-Level Alignment Regularization for 3D Vision-Language Models","created":"2026-02-28","cited_by_count":2,"area":"mllm"},{"id":"2603.09173","title":"Point Cloud as a Foreign Language for Multi-modal Large Language Model","created":"2026-03-10","cited_by_count":2,"area":"mllm"},{"id":"2603.26646","title":"Beyond Language: Grounding Referring Expressions with Hand Pointing in Egocentric Vision","created":"2026-03-27","cited_by_count":2,"area":null},{"id":"2605.08064","title":"Proxy3D: Efficient 3D Representations for Vision-Language Models via Semantic Clustering and Alignment","created":"2026-05-08","cited_by_count":2,"area":"mllm"},{"id":"2605.12167","title":"From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot Manipulation","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2607.06565","title":"ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation","created":"2026-07-07","cited_by_count":2,"area":null},{"id":"2608.19567","title":"Block3D: Efficient Text-to-3D Generation via Block-Wise Diffusion","created":"2026-08-20","cited_by_count":2,"area":null},{"id":"2407.00905","title":"Learning Robust 3D Representation from CLIP via Dual Denoising","created":"2024-07-01","cited_by_count":1,"area":"mllm"},{"id":"2503.21668","title":"Cognitive Science-Inspired Evaluation of Core Capabilities for Object Understanding in AI","created":"2025-03-27","cited_by_count":1,"area":"wm"},{"id":"2504.14471","title":"Efficient Implicit Neural Compression of Point Clouds via Learnable Activation in Latent Space","created":"2025-04-20","cited_by_count":1,"area":null},{"id":"2507.08262","title":"CLAR: Learning 3D Representations for Robotic Manipulation by Fusing Masked Reconstruction with Multi-Level Contrastive Alignment","created":"2025-07-11","cited_by_count":1,"area":null},{"id":"2510.17095","title":"GSPlane: Concise and Accurate Planar Reconstruction via Structured Representation","created":"2025-10-20","cited_by_count":1,"area":null},{"id":"2512.12822","title":"Lemon: A Unified and Scalable 3D Multimodal Model for Universal Spatial Understanding","created":"2025-12-14","cited_by_count":1,"area":"mllm"},{"id":"2512.16413","title":"BrepLLM: Enabling Large Language Models to Understand Boundary Representations","created":"2025-12-18","cited_by_count":1,"area":null},{"id":"2601.19247","title":"TIGaussian: Disentangle Gaussians for Spatial-Awared Text-Image-3D Alignment","created":"2026-01-27","cited_by_count":1,"area":null},{"id":"2602.13912","title":"From Pixels to Policies: Reinforcing Spatial Reasoning in Language Models for Content-Aware Layout Design","created":"2026-02-14","cited_by_count":1,"area":"lr"},{"id":"2602.23153","title":"Efficient Encoder-Free Fourier-based 3D Large Multimodal Model","created":"2026-02-26","cited_by_count":1,"area":"mllm"},{"id":"2603.02329","title":"HAMMER: Harnessing MLLM via Cross-Modal Integration for Intention-Driven 3D Affordance Grounding","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2603.16781","title":"IOSVLM: A 3D Vision-Language Model for Unified Dental Diagnosis from Intraoral Scans","created":"2026-03-17","cited_by_count":1,"area":"mllm"},{"id":"2605.17131","title":"A Survey on Deep Learning Architectures for Point Cloud Classification and Segmentation","created":"2026-05-16","cited_by_count":1,"area":null},{"id":"2607.01784","title":"SpaceEra++: A Unified Framework Towards 3D Spatial Reasoning in Video","created":"2026-07-02","cited_by_count":1,"area":"lr"}],"next_cursor":"100"}