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

arXiv:2603.09632 · cs.CV, cs.CL · Submitted 2026-03-10 · Read on arXiv

cs.CV, cs.CL

Submitted: 2026-03-10

Updated: 2026-09-20

Comments: 16 pages, 5 figures. Accepted to Findings of EMNLP 2026

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Gaussian Splatting — 23× in this paper · explained in 4 episodes
• Distillation — 16× in this paper · explained in 2 episodes
• Grounding — 13× in this paper · explained in 3 episodes
• 3D Gaussian Splatting — 11× in this paper · explained in 2 episodes
• Visual Grounding — 8× in this paper · explained in 2 episodes
• 3D Gaussian Splatting (3DGS) — 5× in this paper · explained in 4 episodes
• Embodied AI — 5× in this paper · explained in 2 episodes
• Quantization — 5× in this paper · explained in 12 episodes
• Vector Quantization — 5× in this paper
• Embeddings — 4× in this paper · explained in 2 episodes
• Foundation Model — 4× in this paper · explained in 3 episodes
• Foundation Models — 4× in this paper · explained in 7 episodes
• Transformer — 4× in this paper · explained in 2 episodes
• Vector Quantization (VQ) — 4× in this paper · explained in 2 episodes
• World Model — 4× in this paper · explained in 7 episodes
• Benchmark — 3× in this paper · explained in 2 episodes
• Downstream Tasks — 3× in this paper · explained in 2 episodes
• Fidelity — 3× in this paper · explained in 2 episodes
• Cosine Similarity — 2× in this paper · explained in 3 episodes
• Multimodal Reasoning — 2× in this paper · explained in 5 episodes
• Point Clouds — 2× in this paper · explained in 2 episodes
• Pruning — 2× in this paper · explained in 4 episodes
• Vision-Language Models (VLMs) — 2× in this paper · explained in 6 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Computational overhead — 1× in this paper · explained in 2 episodes
• Contrastive Learning — 1× in this paper · explained in 5 episodes
• Core — 1× in this paper · explained in 2 episodes
• Exponential Moving Averages — 1× in this paper
• Rectified Flow — 1× in this paper · explained in 3 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Transformer Architecture — 1× in this paper · explained in 2 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes

Sources

• ChatSplat: 3D Conversational Gaussian Splatting
• 7DGS: Unified Spatial-Temporal-Angular Gaussian Splatting
• Segment Anything
• EmbodiedSplat: Online Feed-Forward Semantic 3DGS for Open-Vocabulary 3D Scene Understanding
• LEGO-SLAM: Language-Embedded Gaussian Optimization SLAM
• RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
• LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450+ FPS
• WorldVLA: Towards Autoregressive Action World Model
• 3D-MoE: Towards Spatial Intelligence with Mixture-of-Experts for 3D Reasoning and Action Generation
• A Survey on Vision-Language-Action Models for Embodied AI
• OpenMonoGS-SLAM: Monocular Gaussian Splatting SLAM with Open-set Semantics
• LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
• InfiniteVGGT: Visual Geometry Grounded Transformer for Endless Streams
• Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splatting
• MobileSAMv2: Faster Segment Anything to Everything
• SplatTalk: 3D VQA with Gaussian Splatting
• EA3D: Online Open-World 3D Object Extraction from Streaming Videos
• Streaming 4D Visual Geometry Transformer
• Qwen2 Technical Report

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models