Trendoday

ZeroVLN: Learning to Navigate without Supervised Fine-Tuning of the VLM Brain

Representative vision-language navigation (VLN) methods typically couple a vision-language model (VLM) brain with a learnable action head and fine-tune the VLM brain on navigation-domain data to predi

  • Upvotes8
#13Rank now –
#10Peak rank
3Days on list
350Score · 7d
Nov 20, 2026First seen
Rank · 7 days

About this paper

ZeroVLN is a slow-fast vision-language navigation framework that avoids navigation-domain supervised fine-tuning of the VLM brain by using a semantic tool-calling interface and closed-loop reinforcement learning to coordinate a language-based brain with an action expert, improving VLN-CE…

Representative vision-language navigation (VLN) methods typically couple a vision-language model (VLM) brain with a learnable action head and fine-tune the VLM brain on navigation-domain data to predict geometric goals. However, such adaptation can substantially alter base VLM weights and degrade general visual capabilities. We introduce ZeroVLN, a slow-fast navigation framework that achieves effective navigation with zero navigation-domain SFT of the VLM brain. Rather than teaching the brain to predict geometric goals, we equip it with a semantic tool-calling interface for conveying movement decisions to an action expert in natural language. We first adapt the action expert to carry out…

vision-language navigation (VLN)vision-language model (VLM)action headfine-tuningnavigation-domain datageometric goalsbase VLM weightsslow-fast navigation frameworkzero navigation-domain SFTsemantic tool-calling interface
Upvotes
8
Authors
11
Published
Nov 19, 2026

Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.

Trending history

ZeroVLN: Learning to Navigate without Supervised Fine-Tuning of the VLM Brain was first seen on Hugging Face · Daily papers on Nov 20, 2026. Since then it has appeared in 28 checks on 3 different days. Its best position was #10 of 30, reached on Nov 20, 11:29 UTC. It is #13 right now, holding steady at #13 over the last 6 checks.

Rank history

Position on Hugging Face · Daily papers at every check (lower is better).

#1#11#20#30 Nov 20Nov 20Nov 21Nov 22Nov 22 Nov 20, 09:29 UTC · #22Nov 20, 11:29 UTC · #10Nov 20, 13:29 UTC · #10Nov 20, 15:29 UTC · #11Nov 20, 17:29 UTC · #12Nov 20, 19:29 UTC · #12Nov 20, 21:29 UTC · #12Nov 20, 23:29 UTC · #12Nov 21, 01:29 UTC · #12Nov 21, 03:29 UTC · #12Nov 21, 05:29 UTC · #13Nov 21, 07:29 UTC · #13Nov 21, 09:29 UTC · #13Nov 21, 11:29 UTC · #13Nov 21, 13:29 UTC · #13Nov 21, 15:29 UTC · #13Nov 21, 17:29 UTC · #13Nov 21, 19:29 UTC · #13Nov 21, 21:29 UTC · #13Nov 21, 23:29 UTC · #13Nov 22, 01:29 UTC · #13Nov 22, 03:29 UTC · #13Nov 22, 05:29 UTC · #13Nov 22, 07:29 UTC · #13Nov 22, 09:29 UTC · #13Nov 22, 11:29 UTC · #13Nov 22, 13:29 UTC · #13Nov 22, 15:29 UTC · #13

Last 14 days

Best rank per day (UTC).

Nov 9today

Metric history

▲ as reported by Hugging Face.

071522 Nov 20Nov 20Nov 21Nov 22Nov 22 Nov 20, 09:29 UTC · 8Nov 20, 11:29 UTC · 17Nov 20, 13:29 UTC · 19Nov 20, 15:29 UTC · 19Nov 20, 17:29 UTC · 20Nov 20, 19:29 UTC · 21Nov 20, 21:29 UTC · 21Nov 20, 23:29 UTC · 21Nov 21, 01:29 UTC · 21Nov 21, 03:29 UTC · 21Nov 21, 05:29 UTC · 21Nov 21, 07:29 UTC · 21Nov 21, 09:29 UTC · 21Nov 21, 11:29 UTC · 21Nov 21, 13:29 UTC · 21Nov 21, 15:29 UTC · 22Nov 21, 17:29 UTC · 22Nov 21, 19:29 UTC · 22Nov 21, 21:29 UTC · 22Nov 21, 23:29 UTC · 22Nov 22, 01:29 UTC · 22Nov 22, 03:29 UTC · 22Nov 22, 05:29 UTC · 22Nov 22, 07:29 UTC · 22Nov 22, 09:29 UTC · 22Nov 22, 11:29 UTC · 22Nov 22, 13:29 UTC · 22Nov 22, 15:29 UTC · 22

Questions

Is ZeroVLN: Learning to Navigate without Supervised Fine-Tuning of the VLM Brain trending on HF Daily Papers right now?

Yes. As of Nov 22, 15:29 UTC it is #13, holding steady at #13 over the last 6 checks.

What is the highest rank ZeroVLN: Learning to Navigate without Supervised Fine-Tuning of the VLM Brain reached?

#10 on Hugging Face · Daily papers, on Nov 20, 11:29 UTC. Trendoday checks this list every 120 minutes.

How long has ZeroVLN: Learning to Navigate without Supervised Fine-Tuning of the VLM Brain been trending?

It was first seen on Nov 20, 2026 and has been on the list on 3 days (28 checks) since.