This checkpoint is designed for SwiftVLN on SatNav, the continuous-state vision-and-language navigation benchmark over satellite imagery. It divides visual history into temporal segments and clusters tokens within each segment.

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 plus the available visual history
Prediction horizon: 4 actions
Memory: eight temporal segments compressed to 512 total output tokens

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
sgtc-k512: applies segment token clustering with 512 total output tokens
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	38.35	77.28	68.26	67.85
`val_unseen`	8,756	65.54	66.17	54.47	54.12

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 a long-term-memory ablation in the SwiftVLN SatNav Ablation Model Zoo.

Eku127/swiftvln-satnav-3b-1ep-f32s4-overlap0-sgtc-k512-noembed

SwiftVLN for SatNav — Segment Token Clustering

Related Repositories

Model

Repository name

Reference Results

Usage

Eku127/
swiftvln-satnav-3b-1ep-f32s4-overlap0-sgtc-k512-noembed