{"total":71,"rows":[{"id":"2401.16420","title":"InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model","created":"2024-01-29","cited_by_count":326,"area":"mllm"},{"id":"2405.10370","title":"Grounded 3D-LLM with Referent Tokens","created":"2024-05-16","cited_by_count":115,"area":null},{"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":"2411.07184","title":"SAMPart3D: Segment Any Part in 3D Objects","created":"2024-11-11","cited_by_count":97,"area":null},{"id":"2412.02193","title":"LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Models","created":"2024-12-03","cited_by_count":96,"area":"lr"},{"id":"2505.16278","title":"DriveMoE: Mixture-of-Experts for Vision-Language-Action Model in End-to-End Autonomous Driving","created":"2025-05-22","cited_by_count":86,"area":"vla"},{"id":"2506.01946","title":"3DRS: MLLMs Need 3D-Aware Representation Supervision for Scene Understanding","created":"2025-06-02","cited_by_count":70,"area":"lr"},{"id":"2409.02389","title":"Multi-modal Situated Reasoning in 3D Scenes","created":"2024-09-04","cited_by_count":51,"area":"lr"},{"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":"2405.10255","title":"When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models","created":"2024-05-16","cited_by_count":43,"area":"mllm"},{"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":"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":"2501.02765","title":"Visual Large Language Models for Generalized and Specialized Applications","created":"2025-01-06","cited_by_count":36,"area":"mllm"},{"id":"2407.06191","title":"Tailor3D: Customized 3D Assets Editing and Generation with Dual-Side Images","created":"2024-07-08","cited_by_count":35,"area":null},{"id":"2407.13761","title":"SegPoint: Segment Any Point Cloud via Large Language Model","created":"2024-07-18","cited_by_count":35,"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":"2405.17427","title":"Reason3D: Searching and Reasoning 3D Segmentation via Large Language Model","created":"2024-05-27","cited_by_count":28,"area":"lr"},{"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":"2406.05785","title":"A Survey on Text-guided 3D Visual Grounding: Elements, Recent Advances, and Future Directions","created":"2024-06-09","cited_by_count":25,"area":null},{"id":"2511.00940","title":"URDF-Anything: Constructing Articulated Objects with 3D Multimodal Language Model","created":"2025-11-02","cited_by_count":21,"area":"wm"},{"id":"2408.16662","title":"Space3D-Bench: Spatial 3D Question Answering Benchmark","created":"2024-08-29","cited_by_count":17,"area":null},{"id":"2412.01824","title":"X-Prompt: Towards Universal In-Context Image Generation in Auto-Regressive Vision Language Foundation Models","created":"2024-12-02","cited_by_count":15,"area":"mllm"},{"id":"2503.17690","title":"CountLLM: Towards Generalizable Repetitive Action Counting via Large Language Model","created":"2025-03-22","cited_by_count":14,"area":null},{"id":"2503.15898","title":"Reconstructing In-the-Wild Open-Vocabulary Human-Object Interactions","created":"2025-03-20","cited_by_count":13,"area":null},{"id":"2503.21745","title":"3DGen-Bench: Comprehensive Benchmark Suite for 3D Generative Models","created":"2025-03-27","cited_by_count":12,"area":null},{"id":"2503.14694","title":"HaploVL: A Single-Transformer Baseline for Multi-Modal Understanding","created":"2025-03-12","cited_by_count":11,"area":"mllm"},{"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":"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":"2503.17827","title":"4D-Bench: Benchmarking Multi-modal Large Language Models for 4D Object Understanding","created":"2025-03-22","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":"2510.16714","title":"SceneCOT: Eliciting Grounded Chain-of-Thought Reasoning in 3D Scenes","created":"2025-10-19","cited_by_count":8,"area":"lr"},{"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":"2603.19235","title":"Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding","created":"2026-03-19","cited_by_count":7,"area":"lr"},{"id":"2406.11840","title":"LLaNA: Large Language and NeRF Assistant","created":"2024-06-17","cited_by_count":6,"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":"2503.23024","title":"Empowering Large Language Models with 3D Situation Awareness","created":"2025-03-29","cited_by_count":6,"area":null},{"id":"2604.11789","title":"LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generation","created":"2026-04-13","cited_by_count":6,"area":"lr"},{"id":"2506.09935","title":"LEO-VL: Efficient Scene Representation for Scalable 3D Vision-Language Learning","created":"2025-06-11","cited_by_count":5,"area":"mllm"},{"id":"2508.13739","title":"Enhancing Targeted Adversarial Attacks on Large Vision-Language Models via Intermediate Projector","created":"2025-08-19","cited_by_count":5,"area":"mllm"},{"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":"2408.14253","title":"Text3DAug -- Prompted Instance Augmentation for LiDAR Perception","created":"2024-08-26","cited_by_count":4,"area":null},{"id":"2505.21079","title":"Uni3D-MoE: Scalable Multimodal 3D Scene Understanding via Mixture of Experts","created":"2025-05-27","cited_by_count":4,"area":"mllm"},{"id":"2407.04180","title":"Slice-100K: A Multimodal Dataset for Extrusion-based 3D Printing","created":"2024-07-04","cited_by_count":3,"area":null},{"id":"2506.05689","title":"Pts3D-LLM: Studying the Impact of Token Structure for 3D Scene Understanding With Large Language Models","created":"2025-06-06","cited_by_count":3,"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":"2512.16461","title":"SNOW: Spatio-Temporal Scene Understanding with World Knowledge for Open-World Embodied Reasoning","created":"2025-12-18","cited_by_count":2,"area":"lr"},{"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":"2507.20110","title":"NeuroVoxel-LM: Language-Aligned 3D Perception via Dynamic Voxelization and Meta-Embedding","created":"2025-07-27","cited_by_count":1,"area":"mllm"},{"id":"2603.04976","title":"3D-RFT: Reinforcement Fine-Tuning for Video-based 3D Scene Understanding","created":"2026-03-05","cited_by_count":1,"area":"lr"},{"id":"2604.10772","title":"HOG-Layout: Hierarchical 3D Scene Generation, Optimization and Editing via Vision-Language Models","created":"2026-04-12","cited_by_count":1,"area":"mllm"},{"id":"2606.06485","title":"PAR3D: A Unified 3D-MLLM with Part-Aware Representation for Scene Understanding","created":"2026-06-04","cited_by_count":1,"area":"mllm"},{"id":"2606.11568","title":"4DP-QA: Scalable QA for 4D Perception in Vision Language Models","created":"2026-06-10","cited_by_count":1,"area":"mllm"},{"id":"2608.08053","title":"PhysX-CoT: Structured Physical Reasoning from a Single Image to Simulation-Ready 3D Assets","created":"2026-08-08","cited_by_count":1,"area":"lr"},{"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":"2407.10743","title":"Scaling 3D Reasoning with LMMs to Large Robot Mission Environments Using Datagraphs","created":"2024-07-15","cited_by_count":0,"area":"mllm"},{"id":"2502.09623","title":"Weight Space Representation Learning on Diverse NeRF Architectures","created":"2025-02-13","cited_by_count":0,"area":null},{"id":"2504.13995","title":"Scaling LLaNA: Advancing NeRF-Language Understanding Through Large-Scale Training","created":"2025-04-18","cited_by_count":0,"area":"mllm"},{"id":"2508.17595","title":"TinyGiantVLM: A Lightweight Vision-Language Architecture for Spatial Reasoning under Resource Constraints","created":"2025-08-25","cited_by_count":0,"area":"lr"},{"id":"2511.11777","title":"Large Language Models and 3D Vision for Intelligent Robotic Perception and Autonomy","created":"2025-11-14","cited_by_count":0,"area":null},{"id":"2511.18817","title":"Disc3D: Automatic Curation of High-Quality 3D Dialog Data via Discriminative Object Referring","created":"2025-11-24","cited_by_count":0,"area":"mllm"},{"id":"2601.06464","title":"On the Adversarial Robustness of 3D Large Vision-Language Models","created":"2026-01-10","cited_by_count":0,"area":"mllm"},{"id":"2604.02689","title":"Efficient3D: A Unified Framework for Adaptive and Debiased Token Reduction in 3D MLLMs","created":"2026-04-03","cited_by_count":0,"area":"lr"},{"id":"2606.19776","title":"Occ-VLM: Occupancy Grounded Vision Language Model for Indoor Scene Understanding","created":"2026-06-18","cited_by_count":0,"area":"mllm"},{"id":"2606.19828","title":"3D-PLOT-LLM: Part-Level Object Tokens for 3D Large Language Models","created":"2026-06-18","cited_by_count":0,"area":"mllm"},{"id":"2607.03661","title":"From Geometric Labels to Semantic Understanding of Indoor Building Components Using Multimodal Large Language Models","created":"2026-07-04","cited_by_count":0,"area":"mllm"},{"id":"2607.15054","title":"Beyond Single Expert: Harmonizing Diverse Visual Priors in MLLMs for Spatial Understanding","created":"2026-07-16","cited_by_count":0,"area":"mllm"},{"id":"2608.01185","title":"3DZip: Spatial-Aware Feature Diversity-Guided Token Compression for 3D Question Answering","created":"2026-08-02","cited_by_count":0,"area":"lr"},{"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":"2609.08345","title":"CoVeR: Coverage-Based Token Pruning for Multi-View 3D Reasoning in VLMs","created":"2026-09-08","cited_by_count":0,"area":"inference"},{"id":"2610.02388","title":"Octrees as an Explicit 3D Language","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.17844","title":"What Makes a Good Visual Representation for Spatial Understanding in MLLMs?","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}