{"ID":2889843,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.20110","arxiv_id":"2507.20110","title":"NeuroVoxel-LM: Language-Aligned 3D Perception via Dynamic Voxelization and Meta-Embedding","abstract":"Recent breakthroughs in Visual Language Models (VLMs) and Multimodal Large Language Models (MLLMs) have significantly advanced 3D scene perception towards language-driven cognition. However, existing 3D language models struggle with sparse, large-scale point clouds due to slow feature extraction and limited representation accuracy. To address these challenges, we propose NeuroVoxel-LM, a novel framework that integrates Neural Radiance Fields (NeRF) with dynamic resolution voxelization and lightweight meta-embedding. Specifically, we introduce a Dynamic Resolution Multiscale Voxelization (DR-MSV) technique that adaptively adjusts voxel granularity based on geometric and structural complexity, reducing computational cost while preserving reconstruction fidelity. In addition, we propose the Token-level Adaptive Pooling for Lightweight Meta-Embedding (TAP-LME) mechanism, which enhances semantic representation through attention-based weighting and residual fusion. Experimental results demonstrate that DR-MSV significantly improves point cloud feature extraction efficiency and accuracy, while TAP-LME outperforms conventional max-pooling in capturing fine-grained semantics from NeRF weights.","short_abstract":"Recent breakthroughs in Visual Language Models (VLMs) and Multimodal Large Language Models (MLLMs) have significantly advanced 3D scene perception towards language-driven cognition. However, existing 3D language models struggle with sparse, large-scale point clouds due to slow feature extraction and limited representat...","url_abs":"https://arxiv.org/abs/2507.20110","url_pdf":"https://arxiv.org/pdf/2507.20110v1","authors":"[\"Shiyu Liu\",\"Lianlei Shan\"]","published":"2025-07-27T03:11:08Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\",\"cs.LG\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}