arXiv Computer Vision

CoRef-GS: Cooperative Referring Gaussian Splatting for Multi-Agent Scene Understanding

CoRef-GS introduces a cooperative referring Gaussian splatting framework for multi‑agent scene understanding, enabling robots to ground object‑ and relation‑centric language queries across independently reconstructed maps. The method builds local open‑vocabulary instance‑aware Gaussian maps, aligns them using a cross‑agent module that enforces geometric and semantic consistency, and grounds queries with a view‑conditioned mask relation graph. Experiments on a new dual‑quadruped benchmark show significant improvements, reducing rotation error from 2.58° to 0.15° and raising real‑world referring mIoU from 52.6% to 68.8%.

arXiv Computer Vision

Sep 16

DGSG-Mind: Dynamic 3D Gaussian Scene Graphs for Long-Term Scene Understanding and Grounding

DGSG-Mind introduces a hybrid instance-aware 3D Gaussian dynamic scene graph system that integrates open‑vocabulary semantic information into dynamic 3D scene representations. By coupling a probabilistic voxel grid with explicit 3D Gaussians, it achieves robust cross‑modal instance fusion, incremental semantic mapping, and dynamic change handling through Gaussian‑based relocalization and masked refinement. The system builds a hierarchical scene graph and a 3D Gaussian Mind for multimodal reasoning, achieving state‑of‑the‑art zero‑shot 3D visual grounding and strong performance in open‑vocabulary semantic segmentation and scene reconstruction, and is demonstrated on real‑world robots.

By Luzhou Ge, Xiangyu Zhu, Jinyan Liu, Xuesong Li

agents computer-vision robotics multimodal

arXiv Computer Vision

5d ago

DSSR-3D: Decoupled Reasoning for View-Dependent Referring in 3D Gaussians

arXiv:2610.00040v1 Announce Type: new Abstract: Recent advances in 3D Gaussian Splatting have enabled open-vocabulary and referring segmentation by distilling semantic knowledge from 2D foundation mo...

By Thanh-Khoi Nguyen, Thien-Phuc Tran, Minh-Triet Tran

computer-vision benchmarks

arXiv Computer Vision

Sep 14

AnchorVLN: Geometry-Anchored Vision-Language Grounding Reasoning for Open-Vocabulary Navigation

AnchorVLN is an open‑vocabulary vision‑language navigation system that separates semantic proposals from geometric metrics. It uses a VLM to generate semantics while a geometry module supplies reliable metric quantities such as range and bearing, all within a Model Context Protocol server. The system achieves 64.4% on instruction following and improves object‑reference accuracy, reducing median center error from 3.37 m to 2.48 m.

By Long Giang Vu, Chengkai Yao, Yuxin Liu, FNU Aryan, Rajath Chandrashekar Aralikatti

llms agents robotics multimodal benchmarks

arXiv AI

Jun 24

G$^3$VLA: Geometric inductive bias for Vision-Language-Action Models

arXiv:2606. 24472v1 Announce Type: cross Abstract: Vision-language-action (VLA) models have made rapid progress in generalist robot manipulation by harnessing semantic knowledge from pretrained vision-language backbones, but their visual tokens remain grounded in 2D image coordinates rather than the calibrated geometry of the robot's cameras -- a mismatch especially pronounced in multi-camera setups, where views are coupled by known intrinsics and extrinsics yet processed as independent images.

By Yue Peng, Yongzhe Zhao, Artur Habuda, Khuyen Pham, Yanheng Zhu, Tran Nguyen Le, Fares Abu-Dakka, Li Guo

rag robotics multimodal safety

Hugging Face Trending Papers

Aug 17

GaussianDWM++: Language-Grounded 3D Gaussian Driving World Model for Unified Scene Understanding, Editing, and Multi-Modal Generation

Driving World Models (DWMs) have recently advanced rapidly with generative models, yet most existing methods mainly focus on conditional scene generation and lack explicit 3D scene understanding, lang...

nlp robotics multimodal benchmarks safety

arXiv Computer Vision

Sep 30

SphMind: Towards Robust, Training-Free VLM-based Spatial Reasoning with a 360 Camera

arXiv:2609.33462v2 Announce Type: replace Abstract: Omnidirectional or 360 cameras provide embodied AI agents with a holistic, wide field-of-view (FoV) view of their surroundings, motivating the use...

By Shriram Damodaran, Soumyaratna Debnath, Cheston Tan, Lin Wang

llms agents robotics multimodal benchmarks

arXiv AI

Jun 29

Not All Relations Rotate Alike: Transformation-Aware Decoupling for Viewpoint-Robust 3D Scene Graph Generation

arXiv:2606. 27412v1 Announce Type: cross Abstract: 3D Scene Graph Generation (3DSGG) represents 3D scenes as structured object-relation-object graphs, providing a compact relational abstraction for spatial understanding.

By Jingjun Sun, Chaowei Wang, Zhirui Liu, Jiaxu Tian, Ming Yang, Yaoxing Wang, Shan Gao

agents robotics benchmarks

Hugging Face Trending Papers

Aug 6

Prior-SG: Task and Prior Driven Region Segmentation for Scene Graphs in Arbitrarily-Structured Environments

Hierarchical 3D scene graphs are a promising representation for high-level spatial reasoning in autonomous mobile platforms. However, existing extraction frameworks typically rely on purely local visual clustering or strict geometric heuristics, such as wall-separated rooms, which fail in open-plan or arbitrarily-structured environments.

llms agents computer-vision robotics benchmarks safety

arXiv Machine Learning

Jul 8

PoseVLA: Universal Pose Pretraining for Generalizable Vision-Language-Action Policies

arXiv:2602. 19710v3 Announce Type: replace-cross Abstract: Existing Vision-Language-Action (VLA) models often suffer from feature collapse and low training efficiency because they entangle high-level perception with sparse, embodiment-specific action supervision.

By Haitao Lin, Hanyang Yu, Jingshun Huang, He Zhang, Yonggen Ling, Ping Tan, Xiangyang Xue, Yanwei Fu

nlp robotics multimodal benchmarks safety

arXiv Computer Vision

6d ago

HIGS: Hierarchical Implicit Grids for Joint Geometric and Semantic Scene Understanding

arXiv:2609.38620v1 Announce Type: new Abstract: Neural implicit representations have had a significant impact on scene reconstruction by enabling robots to build continuous, differentiable, and high-...

By Hanwen Cao, Wenqiang Wu, Kuang-Ting Tu, Mathias Otnes, Jeffrey Delmerico, Rui Wang, Yulun Tian, Nikolay Atanasov

robotics multimodal benchmarks

arXiv Computation and Language

Sep 22

X-GS: An Extensible Framework for Perceiving and Thinking with 3D Gaussian Splatting

arXiv:2603.09632v5 Announce Type: replace-cross Abstract: 3D Gaussian Splatting (3DGS) has emerged as a powerful technique for novel view synthesis, subsequently extending into numerous spatial AI ap...

By Yueen Ma, Zenglin Xu, Irwin King

efficiency multimodal benchmarks

arXiv Machine Learning

Sep 10

Contextual Observer Grounding: Evaluating Situated Spatial Reasoning in Vision-Language Models

arXiv:2609.06880v1 Announce Type: cross Abstract: Reasoning over language instructions in embodied tasks such as robotics often requires understanding spatial relations from a speaker's situated pers...

By Mimo Shirasaka, Haochen Zhang, Yonatan Bisk

llms robotics multimodal benchmarks

Related stories