Geometric Encoding for Spatial Reasoning in Vision-Language Models

arXiv:2609.34148 · cs.CV · Submitted 2026-09-28 · Read on arXiv

cs.CV

Submitted: 2026-09-28

Updated: 2026-09-28

Code: https://github.com/QwenLM/Qwen3.5

Terminology

• Accuracy — 14× in this paper · explained in 1 episode
• Ablation — 4× in this paper · explained in 1 episode
• Benchmark — 4× in this paper · explained in 2 episodes
• Fine-Tuning — 4× in this paper · explained in 5 episodes
• Point Clouds — 4× in this paper · explained in 2 episodes
• Alignment — 3× in this paper · explained in 1 episode
• World Model — 3× in this paper · explained in 7 episodes
• Ablation Studies — 2× in this paper · explained in 1 episode
• Adaptation — 2× in this paper · explained in 1 episode
• Training-Free Framework — 2× in this paper · explained in 2 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Hybrid Approach — 1× in this paper · explained in 4 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Principal Component Analysis (PCA) — 1× in this paper · explained in 4 episodes
• Segmentation Masks — 1× in this paper · explained in 2 episodes
• Semantic Understanding — 1× in this paper · explained in 2 episodes
• Vision-Language Models (VLMs) — 1× in this paper · explained in 6 episodes
• alpha — 1× in this paper · explained in 1 episode

Sources

• V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
• Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces
• Beyond Semantics: Rediscovering Spatial Awareness in Vision-Language Models
• SAM 3: Segment Anything with Concepts
• Depth Anything 3: Recovering the Visual Space from Any Views
• Thinking with Spatial Code for Physical-World Video Reasoning
• InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
• YOLO-World: Real-Time Open-Vocabulary Object Detection
• ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models
• SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models
• Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence
• SpaceR: Reinforcing MLLMs in Video Spatial Reasoning
• Qwen2.5-VL Technical Report
• Qwen3 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