This checkpoint is designed for SwiftVLN on SatNav, the continuous-state vision-and-language navigation benchmark over satellite imagery. It predicts short navigation-action sequences from an instruction, the current RGB window, and sampled visual memory.

Model

Starting checkpoint: Qwen/Qwen2.5-VL-3B-Instruct
Training data: SatNav-v0.1 offline expert trajectories
Training: 1 epoch, full-parameter fine-tuning, learning rate 2e-5
Context: 32 RGB frames, up to 8 uniformly sampled history frames
Prediction horizon: 4 actions
Memory: per-frame average pooling with stride 2

Repository name

swiftvln-satnav: SwiftVLN trained and evaluated on SatNav
3b: Qwen2.5-VL 3B backbone
1ep: trained for one epoch
f32s4: uses a 32-frame window and predicts four actions
overlap0: uses non-overlapping training windows
pf-h8: uses per-frame memory with up to eight history frames
pool-s2: applies average pooling with stride 2
noembed: uses no embedding enhancement

Reference Results

Evaluated in SatSim on the full splits with a 500-step cap.

Split	Episodes	NE	OS	SR	SPL
`val_seen`	4,574	34.05	75.49	65.87	65.50
`val_unseen`	8,756	62.29	64.13	53.71	53.27

Usage

Use this checkpoint with the SwiftVLN evaluation guide. Keep the full repository name unchanged because SwiftVLN derives the evaluation configuration from it.

This checkpoint is the reference model in the SwiftVLN SatNav Ablation Model Zoo.

Eku127/swiftvln-satnav-3b-1ep-f32s4-overlap0-pf-h8-pool-s2-noembed

SwiftVLN for SatNav — Reference

Related Repositories

Model

Repository name

Reference Results

Usage

Eku127/
swiftvln-satnav-3b-1ep-f32s4-overlap0-pf-h8-pool-s2-noembed