Beyond the Remembered World: Predictive 4D Belief for Persistent Navigation in Evolving Worlds
cs.AI
Submitted: 2026-09-30
Updated: 2026-10-12
Code: https://github.com/ZJU4EmbodiedAI/EvolvingNav
Project page: https://zju4embodiedai.github.io/EvolvingNav
Sources
- DynaMem: Online Dynamic Spatio-Semantic Memory for Open World Mobile Manipulation
- Predictive Spatio-Temporal Scene Graphs for Semi-Static Scenes
- Personalized Embodied Navigation for Portable Object Finding
- On Evaluation of Embodied Navigation Agents
- AgentVLN: Towards Agentic Vision-and-Language Navigation
- InstructNav: Zero-shot System for Generic Instruction Navigation in Unexplored Environment
- AgenticNav: Zero-Shot Vision-and-Language Navigation as a Tool-Calling Harness
- SEEK: Semantic Reasoning for Object Goal Navigation in Real World Inspection Tasks
- FindingDory: A Benchmark to Evaluate Memory in Embodied Agents
- R4: Retrieval-Augmented Reasoning for Vision-Language Models in 4D Spatio-Temporal Space
- EmbodiedSkills: World Action Model-augmented Cascaded Skills for Vision-Language-Action Agent
- VisualThink-VLA: Visual Intermediate Reasoning for Effective and Low-Latency Vision-Language-Action Policies
- Fine-tuning Multimodal LLMs to Follow Zero-shot Demonstrative Instructions
- HyperLLaVA: Dynamic Visual and Language Expert Tuning for Multimodal Large Language Models
- Align$^2$LLaVA: Cascaded Human and Large Language Model Preference Alignment for Multi-modal Instruction Curation
- InstructSAM: Segment Any Instance with Any Instructions
- Modeling Dynamic Environments with Scene Graph Memory
- FlowMaps: Modeling Long-Term Multimodal Object Dynamics with Flow Matching
- User-Centric Object Navigation: A Benchmark with Integrated User Habits for Personalized Embodied Object Search
- LagMemo: Language 3D Gaussian Splatting Memory for Multi-modal Open-vocabulary Multi-goal Visual Navigation
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems