arXiv Machine Learning
CoVeR: Coverage-Based Token Pruning for Multi-View 3D Reasoning in VLMs
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Aug 14
CoverPrune: Coverage-Driven Token Pruning for 3D VLMs via Optimal Transport
arXiv:2608. 13226v1 Announce Type: cross Abstract: While 3D Vision-Language Models (3D VLMs) have demonstrated remarkable spatial reasoning capabilities, they suffer from massive visual token counts that create severe computational bottlenecks during inference.
Hugging Face Trending Papers
Aug 13
CoverPrune: Coverage-Driven Token Pruning for 3D VLMs via Optimal Transport
While 3D Vision-Language Models (3D VLMs) have demonstrated remarkable spatial reasoning capabilities, they suffer from massive visual token counts that create severe computational bottlenecks during inference. Existing token pruning methods primarily rely on diversity-based selection, discarding similar tokens to maximize dispersion.
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.
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.
arXiv Computation and Language
Sep 30
Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering
arXiv:2609.38177v1 Announce Type: cross Abstract: Reasoning about the 3D world from multi-view images remains a fundamental challenge for Multimodal Large Language Models (MLLMs). While modern MLLMs...
arXiv AI
Oct 12
GeoGR: Spatial-Semantic Token Compression and Group Routing for Efficient 3D VLMs
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.