SATURN: Symbolic Spatial Reasoning for Multi-Perspective Grounding
cs.CV, cs.SC
Submitted: 2026-06-21
Updated: 2026-09-21
Code: https://github.com/HLR/SATURN
Terminology
Sources
- Geometrically-Constrained Agent for Spatial Reasoning
- Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
- Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs
- EmbSpatial-Bench: Benchmarking Spatial Understanding for Embodied Tasks with Large Vision-Language Models
- VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction
- Seeing Across Views: Benchmarking Spatial Reasoning of Vision-Language Models in Robotic Scenes
- ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models
- BLINK: Multimodal Large Language Models Can See but Not Perceive
- SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models
- Spatial Reasoning with Vision-Language Models in Ego-Centric Multi-View Scenes
- SpaCE-10: A Comprehensive Benchmark for Multimodal Large Language Models in Compositional Spatial Intelligence
- IndustryNav: Exploring Spatial Reasoning of Embodied Agents in Dynamic Industrial Navigation
- Depth Anything 3: Recovering the Visual Space from Any Views
- pySpatial: Generating 3D Visual Programs for Zero-Shot Spatial Reasoning
- OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models
- 3DSRBench: A Comprehensive 3D Spatial Reasoning Benchmark
- Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning
- Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs
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