{"total":75,"rows":[{"id":"2406.16855","title":"DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation","created":"2024-06-24","cited_by_count":131,"area":null},{"id":"2405.10370","title":"Grounded 3D-LLM with Referent Tokens","created":"2024-05-16","cited_by_count":115,"area":null},{"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":"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":"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":"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":"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":"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":"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":"2411.19774","title":"PerLA: Perceptive 3D Language Assistant","created":"2024-11-29","cited_by_count":9,"area":null},{"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":"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":"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":"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":"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":"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":"2605.12167","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":"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":"2512.16413","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":"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":"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":"2607.28394","title":"Hand-Object Interaction in the Age of Large Foundation Models:Reconstruction, Generation, and Embodied Transfer","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2608.15710","title":"Beyond Single Object: Learning 3D Relations with Large Language Models","created":"2026-08-16","cited_by_count":1,"area":null},{"id":"2506.09954","title":"Vision Generalist Model: A Survey","created":"2025-06-11","cited_by_count":0,"area":null},{"id":"2507.18997","title":"UPP: Unified Point-Level Prompting for Robust Point Cloud Analysis","created":"2025-07-25","cited_by_count":0,"area":null},{"id":"2508.05064","title":"A Study of the Framework and Real-World Applications of Language Embedding for 3D Scene Understanding","created":"2025-08-07","cited_by_count":0,"area":null},{"id":"2509.17207","title":"Point-RTD: Replaced Token Denoising for Pretraining Transformer Models on Point Clouds","created":"2025-09-21","cited_by_count":0,"area":null},{"id":"2511.14567","title":"SweeperBot: Making 3D Browsing Accessible through View Analysis and Visual Question Answering","created":"2025-11-18","cited_by_count":0,"area":null},{"id":"2603.17647","title":"Part-Aware Open-Vocabulary 3D Affordance Grounding via Prototypical Semantic and Geometric Alignment","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2604.02583","title":"FusionBERT: Multi-View Image--3D Retrieval via Cross-Attention Visual Fusion and Normal-Aware 3D Encoder","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2605.01365","title":"VoxAfford: Multi-Scale Voxel-Token Fusion for Open-Vocabulary 3D Affordance Detection","created":"2026-05-02","cited_by_count":0,"area":null},{"id":"2605.09352","title":"The Wittgensteinian Representation Hypothesis: Is Language the Attractor of Multimodal Convergence?","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2605.28241","title":"PointQ-Bench: Benchmarking Diagnostic and Interpretable Point Cloud Quality Assessment","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.01334","title":"HOLA: Holistic Multi-Modal Alignment for Open-Set 3D Recognition","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2607.28581","title":"ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2607.29136","title":"On the Efficacy of Self-Supervised Point Cloud Encoders for Efficient 3D Large Language Models","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.02711","title":"Hunyuan3D-Buffalo 1.0: A Unified Multimodal Model for Scalable 3D Generation, Understanding, and Editing","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2609.12898","title":"UniPart: Towards Zero-shot Language-Grounded 3D Part Segmentation for Embodied Interaction","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.19716","title":"GAPrompt++: Multi-Granular Geometry-Aware Point Cloud Prompt for 3D Vision Model","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2610.02388","title":"Octrees as an Explicit 3D Language","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.04602","title":"Organize Primitives into Semantic Parts: Reinforcement Reasoning for 3D Segmentation","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.18604","title":"LLM2R: From Large Language Models to 3D Reassemblers","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}