MIV-XJTU/JanusVLN
JanusVLN
[ICLR2026] Official implementation for "JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigation"
Builder
MIV-XJTU
MIV-XJTU • individual
Stars
525
Using upstream star count
Forks
37
Using upstream fork count
Open Issues
0
Activity Score
0/100
0 commits in 30d
Created
Sep 26, 2025
Project creation date
README Summary
JanusVLN is the official implementation of a vision-language navigation model that uses dual implicit memory to separate semantic and spatial information processing. The approach aims to improve navigation performance by decoupling these two critical aspects of understanding in embodied AI tasks. This work was accepted to ICLR 2026 and represents an advancement in how AI agents process multimodal instructions for navigation.
AI Dev Skills
Unmapped
Tags
Taxonomy
Recent Activity
Updated 2 months ago
7 Days
0
30 Days
0
90 Days
0
Quality
research- Quality
- high
- Maturity
- research
Categories
PM Skills
Languages
Timeline
- Project created
- Sep 26, 2025
- Forked
- Mar 31, 2026
- Your last push
- 2 months ago
- Upstream last push
- 2 months ago
- Tracked since
- Jan 26, 2026
Similar Repos
pgvector cosine similarity · $0
Loading…