Call for Papers

Submission Types

We welcome two types of submissions:

• General Papers: Original ideas, perspectives, research visions, and open challenges related to evaluation approaches for explainable recommender systems.

• Featured Papers: Previously published papers or summaries of existing publications from leading conferences and high-impact journals that are relevant to the workshop theme.

We will select three oral papers that have the chance to present the work in our workshop. One of the oral papers will be voted as the Best Paper Award, which will be announced during the workshop.

Topics of Interest

We invite submissions of original research contributions related to, but not limited to, the following topics:

1. Multimodal Spatial Understanding

1. • Multimodal Large Language Models with Spatial Awareness

   • (3D) Vision-Language-Action Alignment

   • 3D Scene Perception (Detection, Segmentation)

   • 3D Semantic Occupancy Prediction

   • Multimodal Spatial Reasoning (Images, Videos, Point Clouds, Text, Audio, etc.)

   • 3D Spatial Grounding

   • Multimodal Affordance Learning

2. 3D/3D-Aware Generative Models

1. • 3D-Aware Diffusion Models and Variational Autoencoders (VAEs)

   • 3D Generative Adversarial Networks (3D GANs)

   • Multi-view Consistent 3D Generation

   • Camera View and Motion Controllability in Generation

3. 3D Geometric Reconstruction

1. • 3D Reconstruction from Multimodal Inputs

   • Neural Implicit Representations for 3D Reconstruction

   • 3D Gaussian Splatting for High-fidelity Scene Reconstruction

   • Integration of Geometric Priors in Deep Learning Models

   • SLAM and Semantic SLAM

   • Scalable 3D Reconstruction for Large-Scale Datasets

4. Foundation Models for Embodied Tasks

1. • Navigation

   • Manipulation

   • Active Perception/Reconstruction

   • World Models for Robotics and Autonomous Vehicles

   • Vision-Language-Action Models

5. Data and Benchmarks for Deep Spatial Analysis

1. • Benchmarks for Spatial Intelligence

   • Large-Scale Datasets for Multimodal Spatial Reasoning

   • Standardized Evaluation Protocols for 3D Generative Models

   • Novel Multimodal Annotation Techniques and Crowdsourced Datasets

   • Multimodal Learning for World Simulation

6. Trustworthy Spatial Intelligence

1. • Ethical Considerations in 3D Generative Models

   • Trustworthy and Robust 3D Foundation Models

   • Fairness and Bias in 3D and Multimodal Datasets and Foundation Models

Submission Instructions

• Submissions must follow the ACM two-column conference format and be written in English. 

• Please use the “sigconf” LaTeX template or the Interim Word Template available on the ACM website (https://www.acm.org/publications/proceedings-template). 

• Papers should be 4-8 pages, with up to an additional 2 pages of references. Authors must anonymize submissions.

• The submission site has already been launched！ 

Please click: Submission Site

Important Dates

• Paper Submission Deadline: July 11, 2025 (AoE)

• Notification of Acceptance: August 1, 2025 (AoE)

• Camera-ready Submission: August 11, 2025 (AoE) [Firm Deadline]

• Workshop Date: October 27/28, 2025 (AoE) 

Review Process

All submissions will undergo peer review by at least two experts in the field, following a double-anonymized review process. Acceptance decisions will be based on technical quality, originality, and relevance to the workshop topics. There is no rebuttal for this call. Reviews and paper decisions will be sent back to the authors on the date specified above.