SpatialSpeak: QA-Native Reconstruction with Local and Global Context for Spatial Chain-of-Thought Reasoning

arXiv:2609.33616 · cs.CV, cs.AI · Submitted 2026-09-27 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-09-27

Updated: 2026-09-27

Project page: https://yangcaoai.github.io/SpatialSpeak

Terminology

• Alignment — 13× in this paper · explained in 1 episode
• Visual Compensation — 13× in this paper
• Ablation — 8× in this paper · explained in 1 episode
• Transformer — 5× in this paper · explained in 2 episodes
• Adam — 3× in this paper · explained in 2 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• Chain-of-Thought (CoT) — 2× in this paper · explained in 4 episodes
• Distillation — 2× 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
• Grounding — 2× in this paper · explained in 3 episodes
• Vision-Language Models (VLMs) — 2× in this paper · explained in 6 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Anisotropy — 1× in this paper · explained in 3 episodes
• Annotation Errors — 1× in this paper · explained in 1 episode
• Gaussian Splatting — 1× in this paper · explained in 4 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Reasoning Traces — 1× in this paper · explained in 3 episodes
• Test-time Scaling — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Two-Stage Framework — 1× in this paper · explained in 2 episodes
• Two-stage training — 1× in this paper · explained in 2 episodes

Sources

• Qwen3-VL Technical Report
• Qwen2.5-VL Technical Report
• Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling
• InstantSplat: Sparse-view Gaussian Splatting in Seconds
• Map2Thought: Explicit 3D Spatial Reasoning via Metric Cognitive Maps
• Gemini: A Family of Highly Capable Multimodal Models
• Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model
• Does Your 3D Encoder Really Work? When Pretrain-SFT from 2D VLMs Meets 3D VLMs
• SpaceR: Reinforcing MLLMs in Video Spatial Reasoning
• OpenAI GPT-5 System Card
• Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs
• Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
• N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models
• UniUGG: Unified 3D Understanding and Generation via Geometric-Semantic Encoding
• Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass
• Visual Spatial Tuning
• Visibility-aware Multi-view Stereo Network
• Long Context Transfer from Language to Vision
• LLaVA-Video: Video Instruction Tuning With Synthetic Data
• PartLLM: A Unified Multimodal Foundation for 3D Part Segmentation

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