[2603.03739] PROSPECT: Unified Streaming Vision-Language Navigation via Semantic--Spatial Fusion and Latent Predictive Representation

Computer Science > Computer Vision and Pattern Recognition arXiv:2603.03739 (cs) [Submitted on 4 Mar 2026] Title:PROSPECT: Unified Streaming Vision-Language Navigation via Semantic--Spatial Fusion and Latent Predictive Representation Authors:Zehua Fan, Wenqi Lyu, Wenxuan Song, Linge Zhao, Yifei Yang, Xi Wang, Junjie He, Lida Huang, Haiyan Liu, Bingchuan Sun, Guangjun Bao, Xuanyao Mao, Liang Xu, Yan Wang, Feng Gao View a PDF of the paper titled PROSPECT: Unified Streaming Vision-Language Navigation via Semantic--Spatial Fusion and Latent Predictive Representation, by Zehua Fan and 14 other authors View PDF HTML (experimental) Abstract:Multimodal large language models (MLLMs) have advanced zero-shot end-to-end Vision-Language Navigation (VLN), yet robust navigation requires not only semantic understanding but also predictive modeling of environment dynamics and spatial structure. We propose PROSPECT, a unified streaming navigation agent that couples a streaming Vision-Language-Action (VLA) policy with latent predictive representation learning. PROSPECT uses CUT3R as a streaming 3D foundation spatial encoder to produce long-context, absolute-scale spatial features, and fuses them with SigLIP semantic features via cross-attention. During training, we introduce learnable stream query tokens that query the streaming context and predict next-step 2D and 3D latent features (rather than pixels or explicit modalities), supervised in the latent spaces of frozen SigLIP and CUT3R teach...