NeurIPS 2025PastRoboticsComputer vision
NeurIPS 2025 Workshop on Space in Vision, Language, and Embodied AI
SpaVLE
- Submission deadline
- Sep 3, 2025, 11:59 UTCimported from OpenReview — check the website for extensions
- Submission portal
- OpenReview
- Notes
- Topics were auto-suggested and may be imprecise — edits welcome.
Accepted papers (56)
Fetched from OpenReview (v2) on 2026-06-10.
An Emergent Symbolic Representation of Space as a Bridge Between Language and Reinforcement Learning in Continuous Environments
Avi: A 3D Vision-Language Action Model Architecture generating Action from Volumetric Inference
BEAST: Efficient Tokenization of B-Splines Encoded Action Sequences for Imitation Learning
Breaking Down and Building Up: Mixture of Skill-Based Vision-and-Language Navigation Agents
Bridging Embodiment Gaps: Deploying Vision-Language-Action Models on Soft Robots
COREVQA: Spatial Reasoning and Multi-Step Visual Entailment in Crowded Environments
DenseScan: Advancing 3D Scene Understanding with 2D Dense Annotation
Evaluation of Vision-LLMs in Surveillance Video
Every Camera Effect, Every Time, All at Once: 4D Gaussian Ray Tracing for Physics-based Camera Effect Data Generation
FINDINGDORY: A Benchmark to Evaluate Memory in Embodied Agents
Flow Equivariant World Models: Structured Dynamics Outside the Field of View
FoR-SALE: Frame of Reference-guided Spatial Adjustment in LLM-based Diffusion Editing
From Static Domain Adaptation to State-Adaptive Perception in Embodied Agents
GeoGrid-Bench: Can Foundation Models Understand Multimodal Gridded Geo-Spatial Data?
Grounding Foundational Vision Models with 3D Human Poses for Robust Action Recognition
Hierarchical Equivariant Policy via Frame Transfer
Hierarchical Object-Oriented POMDP Planning for Object Rearrangement
I Know Kung Fu: Synthetic Dexterous Hand Demonstration Collection via VR Teleoperation
Improving Vision-and-Language Navigation with Explicit Sub-Instruction Alignment
LayerFusion: Harmonized Multi-Layer Text-to-Image Generation with Generative Priors
LayoutAgent: A Vision-Language Agent Guided Compositional Diffusion for Spatial Layout Planning
Learning Dynamics of Multitask Training Data in Vision Language Models
Look and Tell: A Dataset for Multimodal Grounding Across Egocentric and Exocentric Views
Maestro: Orchestrating Robotics Modules with Vision-Language Models for Zero-Shot Generalist Robots
Measuring Physical-World Privacy Awareness of Large Language Models: An Evaluation Benchmark
MetaVLA: Unified Meta Co-Training for Efficient Embodied Adaptation
Motion as Language: Towards a Situation–Motion Language for Spatio-Temporal Learning
NePTune: A Neuro-Pythonic Framework for Tunable Compositional Reasoning on Vision-Language
NinA: Normalizing Flows in Action. Training VLA Models with Normalizing Flows
Object-Centric Agentic Robot Policies
Probing the Limits of Embodied Spatial Planning in LLMs
Rethinking the Simulation vs. Rendering Dichotomy: No Free Lunch in Spatial World Modelling
Revisiting Depth Representations for Feed-Forward 3D Gaussian Splatting
RIV-CoT: Retrieval-Based Interleaved Visual Chain-of-Thought for Multimodal Reasoning
RoboMemory: A Brain-inspired Multi-memory Agentic Framework for Lifelong Learning in Physical Embodied Systems
ROSE: Reconstructing Objects, Scenes, and Trajectories from Casual Videos for Robotic Manipulation
See it. Say it. Sorted: Agentic System for Compositional Diagram Generation
Seeing Beyond the Scene: Analyzing and Mitigating Background Bias in Action Recognition
Self-Augmented Learning of Differentiable Object Models for Compositional Interpretation of Complex Scenes
SITCOM: Scaling Inference-Time COMpute for VLAs
Spatial Reasoning in Foundation Models: Benchmarking Object-Centric Spatial Understanding
SpatialBoost: Enhancing Visual Representation through Language-Guided Reasoning
SpatialThinker: Reinforcing 3D Reasoning in Multimodal LLMs via Spatial Rewards
Spatio-Temporal Grounding of Large Language Models from Perception Streams
SpinBench: Perspective and Rotation as a Lens on Spatial Reasoning in VLMs
TC-LoRA: Temporally Modulated Conditional LoRA for Adaptive Diffusion Control
Think, Remember, Navigate: Zero-Shot Object-Goal Navigation with VLM-Powered Reasoning
TimeRewarder: Learning Dense Reward from Passive Videos via Frame-wise Temporal Distance
Towards Understanding Multimodal Fine-Tuning: A Case Study into Spatial Features
TriFusion-AE: Language-Guided Depth and LiDAR Fusion for Robust Point Cloud Processing
VFSI: Validity First Spatial Intelligence for Constraint-Guided Traffic Diffusion
Viewpoint-Invariant Latent Action Learning from Human Video Demonstrations
VIKI-R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning
ViPRA: Video Prediction for Robot Actions
Weakly-supervised Latent Models for Task-specific Visual-Language Control
Wholly Unsupervised! Segmenting Objects by Contrast and Context