GaugeVLM: Structuring Spatial Supervision with Measured Geometric Interventions

arXiv:2609.38285 · cs.CV, cs.AI · Submitted 2026-09-29 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-09-29

Updated: 2026-09-29

Code: https://github.com/andrewliao11/Q-Spatial-Bench-code

Project page: https://wafer-bob.github.io/GaugeVLM/dist

Terminology

• Accuracy — 23× in this paper · explained in 1 episode
• Benchmark — 19× in this paper · explained in 2 episodes
• Ablation — 9× in this paper · explained in 1 episode
• Generalization — 9× in this paper · explained in 13 episodes
• Quantization — 9× in this paper · explained in 12 episodes
• Robustness — 7× in this paper · explained in 5 episodes
• Consistency — 5× in this paper · explained in 3 episodes
• Direct Preference Optimization — 4× in this paper
• Aggregation — 3× in this paper · explained in 1 episode
• Benchmarking — 3× in this paper · explained in 3 episodes
• Fine-Tuning — 3× in this paper · explained in 5 episodes
• Hallucination — 3× in this paper · explained in 3 episodes
• Verification — 3× in this paper · explained in 2 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• Foundation Models — 2× in this paper · explained in 7 episodes
• Multimodal Reasoning — 2× in this paper · explained in 5 episodes
• Vision-Language Models (VLMs) — 2× in this paper · explained in 6 episodes
• Agentic AI — 1× in this paper · explained in 1 episode
• Bradley-Terry model — 1× in this paper · explained in 2 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Core — 1× in this paper · explained in 2 episodes
• Direct Preference Optimization (DPO) — 1× in this paper · explained in 9 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• Pixtral 12B
• Qwen2.5-VL Technical Report
• Consistent Yet Wrong: Evidence Insensitivity in Spatial Vision-Language Models
• BlenderProc
• GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
• Scaling Spatial Reasoning in MLLMs through Programmatic Data Synthesis
• Smooth Operator: Smooth Verifiable Reward Activates Spatial Reasoning Ability of Vision-Language Model
• ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models
• Visual Agentic AI for Spatial Reasoning with a Dynamic API
• GPT-4 Technical Report
• CVT-Bench: Counterfactual Viewpoint Transformations Reveal Unstable Spatial Representations in Multimodal LLMs
• MindEdit-Bench: Benchmarking Object-Level Counterfactual Spatial Reasoning in VLMs from In-the-Wild Photos
• From Flatland to Space: Teaching Vision-Language Models to Perceive and Reason in 3D

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