SwiftVLN for Habitat — Qwen2.5-VL 3B

Related Repositories

• SwiftVLN: training and evaluation code for this checkpoint.

Model

• Starting checkpoint: Qwen/Qwen2.5-VL-3B-Instruct
• Training data: R2R, RxR, and EnvDrop 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-habitat: SwiftVLN trained and evaluated in Habitat
• 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

Usage