# Zero-Shot 3D Question Answering via Hierarchical View-to-Token Transportation

arXiv: https://arxiv.org/abs/2606.03100 · HTML: https://mlsanity.com/paper/2606.03100/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 53 of its 65 references that are in the map.
- First posted on arXiv 2 Jun 2026.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)
- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 30 of 53)

- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes](https://mlsanity.com/paper/2308.11417/) (2023)
- [Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces](https://mlsanity.com/paper/2412.14171/) (2024)
- [LLaVA-Video: Video Instruction Tuning With Synthetic Data](https://mlsanity.com/paper/2410.02713/) (2024)
- [ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data](https://mlsanity.com/paper/2111.08897/) (2021)
- [LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models](https://mlsanity.com/paper/2403.15388/) (2024)
- [LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding](https://mlsanity.com/paper/2410.17434/) (2024)
- [ScanQA: 3D Question Answering for Spatial Scene Understanding](https://mlsanity.com/paper/2112.10482/) (2021)
- [PointLLM: Empowering Large Language Models to Understand Point Clouds](https://mlsanity.com/paper/2308.16911/) (2023)
- [SQA3D: Situated Question Answering in 3D Scenes](https://mlsanity.com/paper/2210.07474/) (2022)
- [VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos](https://mlsanity.com/paper/2405.19209/) (2024)
- [Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence](https://mlsanity.com/paper/2505.23747/) (2025)
- [LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning](https://mlsanity.com/paper/2311.18651/) (2023)
- [3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment](https://mlsanity.com/paper/2308.04352/) (2023)
- [DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models](https://mlsanity.com/paper/2503.02175/) (2025)
- [Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers](https://mlsanity.com/paper/2312.08168/) (2023)
- [Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams](https://mlsanity.com/paper/2406.08085/) (2024)
- [Adaptive Keyframe Sampling for Long Video Understanding](https://mlsanity.com/paper/2502.21271/) (2025)
- [Video Summarization with Long Short-term Memory](https://mlsanity.com/paper/1605.08110/) (2016)
- [Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding](https://mlsanity.com/paper/2412.00493/) (2024)
- [Grounded 3D-LLM with Referent Tokens](https://mlsanity.com/paper/2405.10370/) (2024)
- [FastVGGT: Training-Free Acceleration of Visual Geometry Transformer](https://mlsanity.com/paper/2509.02560/) (2025)
- [Q-Frame: Query-aware Frame Selection and Multi-Resolution Adaptation for Video-LLMs](https://mlsanity.com/paper/2506.22139/) (2025)
- [BOLT: Boost Large Vision-Language Model Without Training for Long-form Video Understanding](https://mlsanity.com/paper/2503.21483/) (2025)
- [MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs](https://mlsanity.com/paper/2503.13111/) (2025)

## Abstract (arXiv)

Recently, zero-shot 3D scene understanding via 2D Vision-Language Models (VLMs) has gained increasing research interest due to their promising spatial reasoning capabilities. Typically, multiple 2D views are sampled from a 3D point cloud and fed into pre-trained VLMs to answer a given question. This paradigm highlights the critical role of input context quality and raises the challenge of retaining as many task-relevant 3D details as possible under a limited input budget. We propose textttKeyVT, a hierarchical approach for input context collection at both the view and token levels. Specifically, we combine pixel features with camera parameters and assess view importance based on both semantic content and geometric position, resulting in spatially consistent and task-relevant views. Furthermore, we address redundancy among patches across selected views by identifying representative tokens under the optimal transport (OT) framework, where view tokens and key tokens are formulated as two discrete distributions in the embedding space. These key tokens are expected to cover all view features by minimizing the OT distance. We evaluate our framework on three widely used benchmarks, demonstrating significant improvements over existing tuning-free methods and performance comparable to training-based approaches.