StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling

Published July 10, 2026 · Category: Robotics

Overview

arXiv:2507.05240v2 Announce Type: replace Abstract: Vision-and-Language Navigation (VLN) in real-world settings requires agents to process continuous visual streams and generate actions with low latency grounded in language instructions. While Video-based Large Language Models (Video-LLMs) have driven recent progress, current VLN methods based on Video-LLM often face trade-offs among fine-grained visual understanding, long-term context modeling and computational efficiency. We introduce StreamVLN, a streaming VLN framework that employs a hybrid slow-fast context modeling strategy to support multi-modal reasoning over interleaved vision, language and action inputs. The fast-streaming dialogue context facilitates responsive action generation through a sliding-window of multi-turn dialogues, while the slow-updating memory context compresses historical visual states using a 3D-aware token pruning strategy. With this slow-fast design, StreamVLN achieves real-time dialogues through KV cache reuse, supporting long video streams with bounded context size and inference cost. Experiments on VLN-CE benchmarks show state-of-the-art performance with low latency, ensuring robustness and efficiency in real-world deployment. The project page is: https://streamvln.github.io/.

Source

Originally published at arxiv.org.

Related Articles

• Open-Vocabulary Object-Goal Navigation by Generalizing Semantic Mapping with Dense CLIP
• Physics-Guided Biomechanical Gait Adaptation for Humanoid Locomotion on Extreme Sloped Terrains
• Graph-Loc: Robust Graph-Based LiDAR Pose Tracking with Compact Structural Map Priors under Low Observability and Occlusion