Sparse Video Generation Propels Real-World Beyond-the-View Vision-Language Navigation
cs.CV, cs.RO
Submitted: 2026-02-05
Updated: 2026-11-16
Code: https://github.com/OpenDriveLab/SparseVideoNav
Project page: https://internrobotics.github.io
Terminology
Sources
- Learning Video Generation for Robotic Manipulation with Collaborative Trajectory Control
- MagicDrive-V2: High-Resolution Long Video Generation for Autonomous Driving with Adaptive Control
- Stairway to Success: An Online Floor-Aware Zero-Shot Object-Goal Navigation Framework via LLM-Driven Coarse-to-Fine Exploration
- Depth Anything 3: Recovering the Visual Space from Any Views
- Is Diversity All You Need for Scalable Robotic Manipulation?
- Wan: Open and Advanced Large-Scale Video Generative Models
- TrackVLA: Embodied Visual Tracking in the Wild
- StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling
- HunyuanVideo 1.5 Technical Report
- VLN-Game: Vision-Language Equilibrium Search for Zero-Shot Semantic Navigation
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs