WorldMind: Test-Time Scaling for Visual Spatial Reasoning through Latent World Simulation
cs.AI
Submitted: 2026-11-06
Updated: 2026-11-06
Terminology
Sources
- Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Beyond Visual Memory: Mechanistic Diagnostics of Latent Visual Reasoning
- Enhancing Spatial Reasoning in Vision-Language Models via Chain-of-Thought Prompting and Reinforcement Learning
- AI2-THOR: An Interactive 3D Environment for Visual AI
- SpatialMosaic: A Multiview VLM Dataset for Partial Visibility
- LLaVA-OneVision: Easy Visual Task Transfer
- Imagination Helps Visual Reasoning, But Not Yet in Latent Space
- Spatial Reasoning in Multimodal Large Language Models: A Survey of Tasks, Benchmarks and Methods
- SQA3D: Situated Question Answering in 3D Scenes
- SAT: Dynamic Spatial Aptitude Training for Multimodal Language Models
- Solving math word problems with process- and outcome-based feedback
- Demystifying Video Reasoning
- In-Context VLA: Endowing Vision-Language-Action Models with Language via In-Context Post-Training and Agentic Tool Use
- When and How Much to Imagine: Adaptive Test-Time Scaling with World Models for Visual Spatial Reasoning
- Can World Models Benefit VLMs for World Dynamics?
- LLaVA-Video: Video Instruction Tuning With Synthetic Data
- WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric Memories
- Thinking with Novel Views: A Systematic Analysis of Generative-Augmented Spatial Intelligence
- Think3D: Thinking with Space for Spatial Reasoning
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents