CVPR 2026PastMultimodal
CVPR 2026: 2nd Workshop on Multimodal Spatial Intelligence
MUSI
- Submission deadline
- Mar 14, 2026, 11:59 UTCOpenReview-synced 2026-03-14 11:59 UTC (as of 2026-06-23) — extensions on OpenReview are applied automatically; verify on the website.
- Submission portal
- OpenReview
- Notes
- Topics were auto-suggested and may be imprecise — edits welcome.
Accepted papers (18)
Fetched from OpenReview (v2) on 2026-06-10.
A Diagnostic Benchmark for Embodied Spatial Reasoning of Vision-Language Models
ARGOS: Who, Where, and When in Agentic Multi-Camera Person Search
Beyond 3D VQAs: Injecting 3D Spatial Priors into Vision-Language Models for Enhanced Geometric Reasoning
Bridging the Granularity Gap: Object-Centric Masking for Contextual Visual Learning
Can VLMs Handle Multi-hop Compositional Spatial Reasoning?
CoT-PL: Chain-of-Thought Pseudo-Labeling for Open-Vocabulary Object Detection
Hear you are: Teaching LLMs Spatial Reasoning with Vision and Spatial Sound
Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models
Improving Scene Text Recognition in Multimodal Large Language Models using Visual Text Grounding
MindBlock: Probing Spatial Assembly and Structure in Unified Multimodal Models
Multi-Modal Manipulation via Multi-Modal Policy Consensus
Name That Part: 3D Part Segmentation and Naming
SeeThrough3D: Occlusion Aware 3D Control in Text-to-Image Generation
SpaceTools: Tool-Augmented Spatial Reasoning via Double Interactive RL
SPOT: Structured Prompting with Object-centric Tokens for open-world scene graphs
Synthesis of Interactive and Expansive Apartment Environments
Synthetic Counterfactual World Models for Multimodal Spatial Reasoning in Low-Resource 3D Domains
Theory of Space: Evaluating Multimodal Spatial Belief through Active Exploration