{"total":129,"rows":[{"id":"2311.12871","title":"An Embodied Generalist Agent in 3D World","created":"2023-11-18","cited_by_count":365,"area":"agents"},{"id":"2401.13601","title":"MM-LLMs: Recent Advances in MultiModal Large Language Models","created":"2024-01-24","cited_by_count":278,"area":"mllm"},{"id":"2309.10020","title":"Multimodal Foundation Models: From Specialists to General-Purpose Assistants","created":"2023-09-18","cited_by_count":247,"area":null},{"id":"2505.23747","title":"Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence","created":"2025-05-29","cited_by_count":217,"area":"mllm"},{"id":"2312.08168","title":"Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers","created":"2023-12-13","cited_by_count":175,"area":null},{"id":"2412.00493","title":"Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding","created":"2024-11-30","cited_by_count":138,"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":"2406.04339","title":"RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation","created":"2024-06-06","cited_by_count":103,"area":"vla"},{"id":"2312.14074","title":"LiDAR-LLM: Exploring the Potential of Large Language Models for 3D LiDAR Understanding","created":"2023-12-21","cited_by_count":95,"area":"mllm"},{"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":"2504.01901","title":"Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness","created":"2025-04-02","cited_by_count":63,"area":"mllm"},{"id":"2503.00513","title":"Inst3D-LMM: Instance-Aware 3D Scene Understanding with Multi-modal Instruction Tuning","created":"2025-03-01","cited_by_count":51,"area":"mllm"},{"id":"2504.05786","title":"How to Enable LLM with 3D Capacity? A Survey of Spatial Reasoning in LLM","created":"2025-04-08","cited_by_count":42,"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":"2309.12276","title":"LLMR: Real-time Prompting of Interactive Worlds using Large Language Models","created":"2023-09-21","cited_by_count":39,"area":null},{"id":"2407.11895","title":"OmniBind: Large-scale Omni Multimodal Representation via Binding Spaces","created":"2024-07-16","cited_by_count":39,"area":null},{"id":"2412.01292","title":"LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual Preferences","created":"2024-12-02","cited_by_count":38,"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":"2406.05132","title":"3D-GRAND: A Million-Scale Dataset for 3D-LLMs with Better Grounding and Less Hallucination","created":"2024-06-07","cited_by_count":36,"area":null},{"id":"2509.13317","title":"3D Aware Region Prompted Vision Language Model","created":"2025-09-16","cited_by_count":33,"area":"mllm"},{"id":"2510.25760","title":"Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks","created":"2025-10-29","cited_by_count":33,"area":"lr"},{"id":"2312.10763","title":"M3DBench: Let's Instruct Large Models with Multi-modal 3D Prompts","created":"2023-12-17","cited_by_count":32,"area":null},{"id":"2401.03201","title":"3DMIT: 3D Multi-modal Instruction Tuning for Scene Understanding","created":"2024-01-06","cited_by_count":32,"area":"mllm"},{"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":"2403.11835","title":"Agent3D-Zero: An Agent for Zero-shot 3D Understanding","created":"2024-03-18","cited_by_count":29,"area":"agents"},{"id":"2410.03878","title":"SPARTUN3D: Situated Spatial Understanding of 3D World in Large Language Models","created":"2024-10-04","cited_by_count":27,"area":null},{"id":"2410.00255","title":"Robin3D: Improving 3D Large Language Model via Robust Instruction Tuning","created":"2024-09-30","cited_by_count":26,"area":null},{"id":"2503.06271","title":"SplatTalk: 3D VQA with Gaussian Splatting","created":"2025-03-08","cited_by_count":24,"area":null},{"id":"2407.10341","title":"Affordance-Guided Reinforcement Learning via Visual Prompting","created":"2024-07-14","cited_by_count":23,"area":null},{"id":"2412.11258","title":"GaussianProperty: Integrating Physical Properties to 3D Gaussians with LMMs","created":"2024-12-15","cited_by_count":23,"area":null},{"id":"2310.08884","title":"Extending Multi-modal Contrastive Representations","created":"2023-10-13","cited_by_count":21,"area":null},{"id":"2405.17418","title":"A Self-Correcting Vision-Language-Action Model for Fast and Slow System Manipulation","created":"2024-05-27","cited_by_count":21,"area":"mllm"},{"id":"2405.04883","title":"FreeBind: Free Lunch in Unified Multimodal Space via Knowledge Fusion","created":"2024-05-08","cited_by_count":19,"area":null},{"id":"2407.06842","title":"Chat-Edit-3D: Interactive 3D Scene Editing via Text Prompts","created":"2024-07-09","cited_by_count":19,"area":"mllm"},{"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":"2505.12253","title":"LLaVA-4D: Embedding SpatioTemporal Prompt into LMMs for 4D Scene Understanding","created":"2025-05-18","cited_by_count":17,"area":"mllm"},{"id":"2405.18295","title":"Intent3D: 3D Object Detection in RGB-D Scans Based on Human Intention","created":"2024-05-28","cited_by_count":16,"area":null},{"id":"2501.04670","title":"Are They the Same? Exploring Visual Correspondence Shortcomings of Multimodal LLMs","created":"2025-01-08","cited_by_count":16,"area":"lr"},{"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":"2503.18135","title":"MLLM-For3D: Adapting Multimodal Large Language Model for 3D Reasoning Segmentation","created":"2025-03-23","cited_by_count":16,"area":"lr"},{"id":"2312.09738","title":"3DAxiesPrompts: Unleashing the 3D Spatial Task Capabilities of GPT-4V","created":"2023-12-15","cited_by_count":15,"area":null},{"id":"2407.10993","title":"The Effects of Embodiment and Personality Expression on Learning in LLM-based Educational Agents","created":"2024-06-24","cited_by_count":13,"area":"agents"},{"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":"2408.12093","title":"LLM-enhanced Scene Graph Learning for Household Rearrangement","created":"2024-08-22","cited_by_count":12,"area":null},{"id":"2507.00886","title":"GaussianVLM: Scene-centric 3D Vision-Language Models using Language-aligned Gaussian Splats for Embodied Reasoning and Beyond","created":"2025-07-01","cited_by_count":12,"area":"lr"},{"id":"2409.19650","title":"Grounding 3D Scene Affordance From Egocentric Interactions","created":"2024-09-29","cited_by_count":11,"area":null},{"id":"2412.02402","title":"RG-SAN: Rule-Guided Spatial Awareness Network for End-to-End 3D Referring Expression Segmentation","created":"2024-12-03","cited_by_count":11,"area":null},{"id":"2507.07781","title":"SURPRISE3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes","created":"2025-07-10","cited_by_count":11,"area":"lr"},{"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":"2506.04220","title":"Struct2D: A Perception-Guided Framework for Spatial Reasoning in MLLMs","created":"2025-06-04","cited_by_count":10,"area":"lr"},{"id":"2404.03836","title":"PARIS3D: Reasoning-based 3D Part Segmentation Using Large Multimodal Model","created":"2024-04-04","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":"2505.24870","title":"GenSpace: Benchmarking Spatially-Aware Image Generation","created":"2025-05-30","cited_by_count":9,"area":null},{"id":"2603.23523","title":"Do 3D Large Language Models Really Understand 3D Spatial Relationships?","created":"2026-03-06","cited_by_count":9,"area":null},{"id":"2410.02406","title":"ELLMA-T: an Embodied LLM-agent for Supporting English Language Learning in Social VR","created":"2024-10-03","cited_by_count":8,"area":"agents"},{"id":"2505.12703","title":"SpatialLLM: From Multi-modality Data to Urban Spatial Intelligence","created":"2025-05-19","cited_by_count":8,"area":null},{"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":"2601.11442","title":"Map2Thought: Explicit 3D Spatial Reasoning via Metric Cognitive Maps","created":"2026-01-16","cited_by_count":8,"area":"lr"},{"id":"2405.17104","title":"LLM-Optic: Unveiling the Capabilities of Large Language Models for Universal Visual Grounding","created":"2024-05-27","cited_by_count":7,"area":null},{"id":"2502.02441","title":"LLMER: Crafting Interactive Extended Reality Worlds with JSON Data Generated by Large Language Models","created":"2025-02-04","cited_by_count":7,"area":null},{"id":"2505.04911","title":"SpatialPrompting: Keyframe-driven Zero-Shot Spatial Reasoning with Off-the-Shelf Multimodal Large Language Models","created":"2025-05-08","cited_by_count":7,"area":"lr"},{"id":"2508.20758","title":"SeqVLM: Proposal-Guided Multi-View Sequences Reasoning via VLM for Zero-Shot 3D Visual Grounding","created":"2025-08-28","cited_by_count":7,"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":"2506.23120","title":"Enhancing Spatial Reasoning in Multimodal Large Language Models through Reasoning-based Segmentation","created":"2025-06-29","cited_by_count":6,"area":"lr"},{"id":"2508.07251","title":"Understanding Dynamic Scenes in Ego Centric 4D Point Clouds","created":"2025-08-10","cited_by_count":6,"area":"lr"},{"id":"2511.19430","title":"Cook and Clean Together: Teaching Embodied Agents for Parallel Task Execution","created":"2025-11-24","cited_by_count":6,"area":"agents"},{"id":"2602.21186","title":"Spa3R: Predictive Spatial Field Modeling for 3D Visual Reasoning","created":"2026-02-24","cited_by_count":6,"area":"lr"},{"id":"2607.12477","title":"Self in Space: Benchmarking Self-Awareness and Spatial Cognition in UAV Embodied Intelligence","created":"2026-07-14","cited_by_count":6,"area":null},{"id":"2406.09126","title":"3D-AVS: LiDAR-based 3D Auto-Vocabulary Segmentation","created":"2024-06-13","cited_by_count":5,"area":null},{"id":"2412.06613","title":"3D Spatial Understanding in MLLMs: Disambiguation and Evaluation","created":"2024-12-09","cited_by_count":5,"area":"mllm"},{"id":"2503.05949","title":"Bayesian Fields: Task-driven Open-Set Semantic Gaussian Splatting","created":"2025-03-07","cited_by_count":5,"area":null},{"id":"2504.04540","title":"The Point, the Vision and the Text: Does Point Cloud Boost Spatial Reasoning of Large Language Models? A Bias-Controlled Study","created":"2025-04-06","cited_by_count":5,"area":"lr"},{"id":"2511.20644","title":"Vision-Language Memory for Spatial Reasoning","created":"2025-11-25","cited_by_count":5,"area":"lr"},{"id":"2512.01223","title":"S$^2$-MLLM: Boosting Spatial Reasoning Capability of MLLMs for 3D Visual Grounding with Structural Guidance","created":"2025-12-01","cited_by_count":5,"area":"lr"},{"id":"2603.08592","title":"Boosting MLLM Spatial Reasoning with Geometrically Referenced 3D Scene Representations","created":"2026-03-09","cited_by_count":5,"area":"lr"},{"id":"2503.17044","title":"ExCap3D: Expressive 3D Scene Understanding via Object Captioning with Varying Detail","created":"2025-03-21","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":"2506.20134","title":"From 2D to 3D Cognition: A Brief Survey of General World Models","created":"2025-06-25","cited_by_count":4,"area":"wm"},{"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":"2605.24456","title":"EgoProx: Evaluating MLLMs on Egocentric 3D Proximity Reasoning Across a Cognitive Hierarchy","created":"2026-05-23","cited_by_count":4,"area":"lr"},{"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":"2507.14555","title":"Descrip3D: Enhancing Large Language Model-based 3D Scene Understanding with Object-Level Text Descriptions","created":"2025-07-19","cited_by_count":3,"area":null},{"id":"2512.01821","title":"Seeing through Imagination: Learning Scene Geometry via Implicit Spatial World Modeling","created":"2025-12-01","cited_by_count":3,"area":"wm"},{"id":"2604.03318","title":"EgoMind: Activating Spatial Cognition through Linguistic Reasoning in MLLMs","created":"2026-04-01","cited_by_count":3,"area":"lr"},{"id":"2503.12974","title":"Exploring 3D Reasoning-Driven Planning: From Implicit Human Intentions to Route-Aware Activity Planning","created":"2025-03-17","cited_by_count":2,"area":null},{"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":"2602.10551","title":"C^2ROPE: Causal Continuous Rotary Positional Encoding for 3D Large Multimodal-Models Reasoning","created":"2026-02-11","cited_by_count":2,"area":"lr"},{"id":"2602.22716","title":"SoPE: Spherical Coordinate-Based Positional Embedding for Enhancing Spatial Perception of 3D LVLMs","created":"2026-02-26","cited_by_count":2,"area":"mllm"},{"id":"2603.27507","title":"Chat-Scene++: Exploiting Context-Rich Object Identification for 3D LLM","created":"2026-03-29","cited_by_count":2,"area":"mllm"},{"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":"2509.16721","title":"Text-Scene: A Scene-to-Language Parsing Framework for 3D Scene Understanding","created":"2025-09-20","cited_by_count":1,"area":null},{"id":"2511.14086","title":"Error-Driven Scene Editing for 3D Grounding in Large Language Models","created":"2025-11-18","cited_by_count":1,"area":null},{"id":"2602.19063","title":"Direction-aware 3D Large Multimodal Models","created":"2026-02-22","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":"2603.23447","title":"3DCity-LLM: Empowering Multi-modality Large Language Models for 3D City-scale Perception and Understanding","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2604.03296","title":"3D-IDE: 3D Implicit Depth Emergent","created":"2026-03-28","cited_by_count":1,"area":"mllm"},{"id":"2605.19528","title":"Towards Camera-Robust 3D Localization: Equation-Anchored Tool-Use for MLLMs","created":"2026-05-19","cited_by_count":1,"area":"mllm"},{"id":"2605.30231","title":"Beyond 3D VQAs: Injecting 3D Spatial Priors into Vision-Language Models for Enhanced Geometric Reasoning","created":"2026-05-28","cited_by_count":1,"area":"lr"}],"next_cursor":"100"}