AdaToken-3D: Dynamic Spatial Gating for Efficient 3D Large Multimodal-Models Reasoning

• URL: http://arxiv.org/abs/2505.12782v1
• Date: Mon, 19 May 2025 07:11:07 GMT
• Title: AdaToken-3D: Dynamic Spatial Gating for Efficient 3D Large Multimodal-Models Reasoning
• Authors: Kai Zhang, Xingyu Chen, Xiaofeng Zhang,
• Abstract summary: Large Multimodal Models (LMMs) have become a pivotal research focus in deep learning.<n>Currently, 3D LMMs employing thousands of spatial tokens for multimodal reasoning suffer from critical inefficiencies.<n>We propose AdaToken-3D, an adaptive spatial token optimization framework that dynamically prunes redundant tokens.
• Score: 27.40106634796608
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Multimodal Models (LMMs) have become a pivotal research focus in deep learning, demonstrating remarkable capabilities in 3D scene understanding. However, current 3D LMMs employing thousands of spatial tokens for multimodal reasoning suffer from critical inefficiencies: excessive computational overhead and redundant information flows. Unlike 2D VLMs processing single images, 3D LMMs exhibit inherent architectural redundancy due to the heterogeneous mechanisms between spatial tokens and visual tokens. To address this challenge, we propose AdaToken-3D, an adaptive spatial token optimization framework that dynamically prunes redundant tokens through spatial contribution analysis. Our method automatically tailors pruning strategies to different 3D LMM architectures by quantifying token-level information flows via attention pattern mining. Extensive experiments on LLaVA-3D (a 7B parameter 3D-LMM) demonstrate that AdaToken-3D achieves 21\% faster inference speed and 63\% FLOPs reduction while maintaining original task accuracy. Beyond efficiency gains, this work systematically investigates redundancy patterns in multimodal spatial information flows through quantitative token interaction analysis. Our findings reveal that over 60\% of spatial tokens contribute minimally ($<$5\%) to the final predictions, establishing theoretical foundations for efficient 3D multimodal learning.

Related papers

• Fast3D: Accelerating 3D Multi-modal Large Language Models for Efficient 3D Scene Understanding [24.964149224068027]
  We propose Fast3D, a plug-and-play visual token pruning framework for 3D MLLMs.<n>Global Attention Prediction (GAP) learns to predict the global attention distributions of the target model, enabling efficient token importance estimation.<n>SAP, introduces dynamic token budgets through attention-based complexity assessment, automatically adjusting layer-wise pruning ratios.
  arXiv  Detail & Related papers  (2025-07-12T16:29:02Z)
• VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction [86.82819259860186]
  We introduce VLM-3R, a unified framework for Vision-Language Models (VLMs) that incorporates 3D Reconstructive instruction tuning.<n>VLM-3R processes monocular video frames by employing a geometry encoder to derive implicit 3D tokens that represent spatial understanding.
  arXiv  Detail & Related papers  (2025-05-26T17:56:30Z)
• econSG: Efficient and Multi-view Consistent Open-Vocabulary 3D Semantic Gaussians [56.85804719947]
  We propose econSG for open-vocabulary semantic segmentation with 3DGS.<n>Our econSG shows state-of-the-art performance on four benchmark datasets compared to the existing methods.
  arXiv  Detail & Related papers  (2025-04-08T13:12:31Z)
• MLLM-For3D: Adapting Multimodal Large Language Model for 3D Reasoning Segmentation [87.30919771444117]
  Reasoning segmentation aims to segment target objects in complex scenes based on human intent and spatial reasoning.<n>Recent multimodal large language models (MLLMs) have demonstrated impressive 2D image reasoning segmentation.<n>We introduce MLLM-For3D, a framework that transfers knowledge from 2D MLLMs to 3D scene understanding.
  arXiv  Detail & Related papers  (2025-03-23T16:40:20Z)
• 3UR-LLM: An End-to-End Multimodal Large Language Model for 3D Scene Understanding [49.15555885075644]
  We develop pipeline based on open-source 2D MLLMs and LLMs to generate high-quality 3D-text pairs.<n>We introduce the 3UR-LLM model, an end-to-end 3D MLLM designed for precise interpretation of 3D scenes.
  arXiv  Detail & Related papers  (2025-01-14T03:50:23Z)
• Optimized CNNs for Rapid 3D Point Cloud Object Recognition [2.6462438855724826]
  This study introduces a method for efficiently detecting objects within 3D point clouds using convolutional neural networks (CNNs)<n>Our approach adopts a unique feature-centric voting mechanism to construct convolutional layers that capitalize on the typical sparsity observed in input data.<n>The Vote3Deep models, with just three layers, outperform the previous state-of-the-art in both laser-only approaches and combined laser-vision methods.
  arXiv  Detail & Related papers  (2024-12-03T21:42:30Z)
• LLMI3D: MLLM-based 3D Perception from a Single 2D Image [77.13869413871028]
  multimodal large language models (MLLMs) excel in general capacity but underperform in 3D tasks.<n>In this paper, we propose solutions for weak 3D local spatial object perception, poor text-based geometric numerical output, and inability to handle camera focal variations.<n>We employ parameter-efficient fine-tuning for a pre-trained MLLM and develop LLMI3D, a powerful 3D perception MLLM.
  arXiv  Detail & Related papers  (2024-08-14T10:00:16Z)
• Coarse Correspondences Boost Spatial-Temporal Reasoning in Multimodal Language Model [51.83436609094658]
  We introduce Coarse Correspondences, a simple lightweight method that enhances MLLMs' spatial-temporal reasoning with 2D images as input. Our method uses a lightweight tracking model to identify primary object correspondences between frames in a video or across different image viewpoints. We demonstrate that this simple training-free approach brings substantial gains to GPT4-V/O consistently on four benchmarks.
  arXiv  Detail & Related papers  (2024-08-01T17:57:12Z)
• MMScan: A Multi-Modal 3D Scene Dataset with Hierarchical Grounded Language Annotations [55.022519020409405]
  This paper builds the first largest ever multi-modal 3D scene dataset and benchmark with hierarchical grounded language annotations, MMScan.<n>The resulting multi-modal 3D dataset encompasses 1.4M meta-annotated captions on 109k objects and 7.7k regions as well as over 3.04M diverse samples for 3D visual grounding and question-answering benchmarks.
  arXiv  Detail & Related papers  (2024-06-13T17:59:30Z)
• Spatiotemporal Modeling Encounters 3D Medical Image Analysis: Slice-Shift UNet with Multi-View Fusion [0.0]
  We propose a new 2D-based model dubbed Slice SHift UNet which encodes three-dimensional features at 2D CNN's complexity. More precisely multi-view features are collaboratively learned by performing 2D convolutions along the three planes of a volume. The effectiveness of our approach is validated in Multi-Modality Abdominal Multi-Organ axis (AMOS) and Multi-Atlas Labeling Beyond the Cranial Vault (BTCV) datasets.
  arXiv  Detail & Related papers  (2023-07-24T14:53:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.