| 3D-SceneQ: Empowering 3D LLM With Query-Guided Adaptive Pruning and Multi-Modal Feature Enhancement | | 67.0 | 3D-SceneQ | 2026-10-27 |
| Modeling Cross-vision Synergy for Unified Large Vision Model | | 64.8 | PolyV | 2026-03-03 |
| Learning Geometric Representations from Videos for Spatial Intelligent Multimodal Large Language Models | ✓ Link | 63.9 | GeoVR-4B | 2026-06-04 |
| Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering | | 63.8 | Imagine3D-LLM | 2026-09-29 |
| CVP: Central-Peripheral Vision-Inspired Multimodal Model for Spatial Reasoning | | 62.3 | CVP | 2025-12-09 |
| 3D Aware Region Prompted Vision Language Model | | 62.2 | SR-3D-8B | 2025-09-16 |
| Learning Geometric Representations from Videos for Spatial Intelligent Multimodal Large Language Models | ✓ Link | 61.4 | GeoVR-2B | 2026-06-04 |
| Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding | ✓ Link | 61.3 | VEGA-3D | 2026-03-19 |
| SpaceMind: Camera-Guided Modality Fusion for Spatial Reasoning in Vision-Language Models | | 61.1 | SpaceMind | 2025-11-28 |
| V-LynX: Token Interface Alignment for Video+X LLMs | ✓ Link | 60.5 | V-LynX-7B | 2026-05-30 |
| Vision-Language Memory for Spatial Reasoning | | 60.4 | VLM2-7B | 2025-11-25 |
| LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness | | 60.1 | LLaVA-3D | 2024-09-26 |
| Reasoning in Space via Grounding in the World | ✓ Link | 59.9 | GS-Reasoner | 2025-10-15 |
| Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding | ✓ Link | 58.6 | Video-3D LLM | 2024-11-30 |
| Distilling Neuro-Symbolic Programs into 3D Multi-modal LLMs | ✓ Link | 58.6 | APEIRIA | 2026-05-31 |
| CAIRN: Cross-Room 3D Scene Understanding with Topology-Aware Large Multimodal Models | | 58.1 | CAIRN | 2026-07-07 |
| C^2ROPE: Causal Continuous Rotary Positional Encoding for 3D Large Multimodal-Models Reasoning | | 56.8 | C^2ROPE | 2026-02-11 |
| Qwen-3D: A Generalist 3D Vision-Language Model for Spatial Understanding | | 56.8 | Qwen-3D (7B) | 2026-08-04 |
| CAPruner: Conceptual-Adjacent Scene Graph Pruner for Enhancing 3D Spatial Reasoning of Large Language Models | ✓ Link | 56.3 | CAPruner + Llama-3-8B | 2026-04-21 |
| MoE3D: Mixture of Experts meets Multi-Modal 3D Understanding | | 56.0 | MoE3D | 2025-11-27 |
| Qwen-3D: A Generalist 3D Vision-Language Model for Spatial Understanding | | 55.8 | Qwen-3D (3B) | 2026-08-04 |
| Descrip3D: Enhancing Large Language Model-based 3D Scene Understanding with Object-Level Text Descriptions | | 55.7 | Descrip3D (Vicuna-7B) | 2025-07-19 |
| SceneScaffold: Active Scene-State Construction for Unified 3D Scene Understanding | ✓ Link | 55.5 | SceneScaffold | 2026-09-27 |
| Scalable Object Relation Encoding for Better 3D Spatial Reasoning in Large Language Models | ✓ Link | 55.2 | 3DGraphLLM-7B + QuatRoPE | 2026-03-25 |
| Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers | ✓ Link | 54.7 | Chat-3D v2 | 2023-12-13 |
| Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers | ✓ Link | 54.6 | ChatScene | 2023-12-13 |
| PAR3D: A Unified 3D-MLLM with Part-Aware Representation for Scene Understanding | | 54.6 | PAR3D | 2026-06-04 |
| Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning | | 54.2 | Scene-LLM | 2024-03-18 |
| Scalable Object Relation Encoding for Better 3D Spatial Reasoning in Large Language Models | ✓ Link | 53.2 | 3DGraphLLM-1B + QuatRoPE | 2026-03-25 |
| CAPruner: Conceptual-Adjacent Scene Graph Pruner for Enhancing 3D Spatial Reasoning of Large Language Models | ✓ Link | 52.8 | CAPruner + Llama-3.2-1B | 2026-04-21 |
| POMA-3D: The Point Map Way to 3D Scene Understanding | | 51.1 | POMA-3D (spec) | 2025-11-20 |
| An Embodied Generalist Agent in 3D World | ✓ Link | 50.0 | LEO | 2023-11-18 |
| Memory Tree Guided Key Frame Querying for Efficient 3D Question Answering | ✓ Link | 49.6 | MemTree3D (w/ LLaVA-OneVision-7B) | 2026-08-18 |
| Scene-R1: Video-Grounded Large Language Models for 3D Scene Reasoning without 3D Annotations | | 49.4 | Scene-R1 | 2025-06-21 |
| 3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment | ✓ Link | 48.5 | 3D-VisTA | 2023-08-08 |
| Video Instruction Tuning With Synthetic Data | | 48.5 | LLaVA-Video | 2024-10-03 |
| ScanQA: 3D Question Answering for Spatial Scene Understanding | ✓ Link | 47.2 | ScanQA | 2021-12-20 |
| Unifying 3D Vision-Language Understanding via Promptable Queries | | 47.1 | PQ3D | 2024-05-19 |
| Scan2Cap: Context-aware Dense Captioning in RGB-D Scans | | 41.0 | Scan2Cap | 2020-12-03 |
| MVBench: A Comprehensive Multi-modal Video Understanding Benchmark | ✓ Link | 37.3 | VideoChat2 | 2023-11-28 |
| LLaVA-OneVision: Easy Visual Task Transfer | ✓ Link | 34.2 | LLaVA-NeXT-Video | 2024-08-06 |