DepthEvidence: Unifying Metric Depth Prediction and Geometric Reasoning in Multimodal Language Models

arXiv:2609.31103 · cs.CV, cs.AI · Submitted 2026-09-25 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-09-25

Updated: 2026-09-25

Code: https://github.com/embodiedreasoning/ERQA

Terminology

• Benchmark — 43× in this paper · explained in 2 episodes
• Grounding — 13× in this paper · explained in 3 episodes
• Accuracy — 10× in this paper · explained in 1 episode
• Ablation — 9× in this paper · explained in 1 episode
• Instruction Tuning — 5× in this paper · explained in 2 episodes
• Alignment — 4× in this paper · explained in 1 episode
• Calibration — 3× in this paper · explained in 7 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Embeddings — 2× in this paper · explained in 2 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• Multimodal Dataset — 1× in this paper · explained in 2 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Pairwise Comparisons — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Transfer Learning — 1× in this paper · explained in 10 episodes

Sources

• GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
• Perceptio: Perception Enhanced Vision Language Models via Spatial Token Generation
• OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models
• Masked Depth Modeling for Spatial Perception
• Youtu-VL: Unleashing Visual Potential via Unified Vision-Language Supervision
• Unlocking Dense Metric Depth Estimation in VLMs
• MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark

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