arXiv AI October 12, 2026 By Yongxin Zheng, Hao Wu, Fang Li, Hu Fu, Peiran Yin, Xudong Wang, Haozhe Hu, Xinghao Chen, Yunpu Ma, Wei Zhang, Xiaoyu Shen

GeoGR: Spatial-Semantic Token Compression and Group Routing for Efficient 3D VLMs

Read the original on arXiv AI →

GeoGR introduces a two‑stage framework for efficient 3D vision‑language models. The first stage, GeoSemZip, compresses multi‑view visual tokens into compact 3D voxel representations while preserving important scene information through contextual anchors. The second stage, GroupRoute, dynamically routes tokens through the language model, allowing low‑relevance tokens to skip layers and rejoin later, thereby reducing computation without significant loss of performance.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Hugging Face Trending Papers

Aug 5

HiSC: Hierarchical Spatial Clustering Token Compression for Efficient 3D Scene Understanding

3D vision-language models (3D VLMs) enable spatial reasoning over multi-view scenes but suffer from substantial token redundancy due to duplicated observations and large uninformative regions, leading to high computational cost. Although visual token compression has shown promise in accelerating 2D VLMs, it fails to capture the structured nature of 3D scenes and leads to incomplete spatial coverage and loss of fine-grained details.

llms efficiency multimodal benchmarks

arXiv Machine Learning

Sep 10

CoVeR: Coverage-Based Token Pruning for Multi-View 3D Reasoning in VLMs

arXiv:2609.08345v1 Announce Type: cross Abstract: Representing a 3D scene as multi-view images allows 2D VLMs to reason in 3D by reusing priors from pre-training, sidestepping the scarcity of annotat...

By Nhat-Tan Bui, Varshini Elangovan, Arun Reddy Anugu, Sreyas Mohan, Wei Ye, Dilin Wang, JQ Huang, Rakesh Ranjan, Aviral Chharia, Fernando De la Torre

efficiency benchmarks

arXiv AI

Aug 6

CARVE: Cross-Slice Anisotropic Reallocation of Visual Evidence for Efficient 3D Medical Volume Understanding

arXiv:2608. 04515v1 Announce Type: cross Abstract: Slice-based MLLMs leverage mature 2D encoders by representing 3D volumes as sequences of 2D slices.

By Zhenyu Yi, Qiang Hu, Zhenhao Li, Jiaxuan Zhao, Yusong Sun, Lichi Zhang

llms benchmarks

arXiv Machine Learning

Aug 4

3DZip: Spatial-Aware Feature Diversity-Guided Token Compression for 3D Question Answering

arXiv:2608. 01185v1 Announce Type: cross Abstract: Recent 3D vision-language models (3D VLMs) construct geometry aware tokens by projecting 2D visual features into world coordinates, enabling spatial reasoning for tasks such as 3D question answering.

By Changwoo Baek, Kyeongbo Kong

llms nlp efficiency multimodal benchmarks

arXiv Computer Vision

Sep 22

VGGT-Prime: Compute-Adaptive Mixture-of-Heads for Efficient Visual Geometry Transformers

arXiv:2609.23733v1 Announce Type: new Abstract: Feed-forward visual geometry models such as the Visual Geometry Grounded Transformer (VGGT) have recently enabled direct 3D reconstruction from multi-v...

By Abteen Arab, Guile Wu, Chengjie Huang, Dongfeng Bai

llms efficiency

arXiv AI

2d ago

HIMMEL: Hierarchical Interleaved Multi-stream Motion Encoding for Long Video Understanding

arXiv:2605.08158v2 Announce Type: replace-cross Abstract: Long video understanding with multimodal language models suffers from three compounding bottlenecks: heavy decode cost to obtain dense RGB fr...

By Haopeng Jin, Wenlong Zhao, Tao Yu, Tiankun Yang, Zhenyu Guan, ShiQuan Dong, Yujia Yang, Shani Ye, Chubin Chen, Hongzhu Yi, Jinwen Luo

llms fine-tuning multimodal safety