Research map / Large language models / Alignment and preferences
SMAP: Semantic Route Planning with Map-Grounded Multimodal Alignment
Wenjie Zhang, Chen Yang, Xin Lu, Zhen Wang, Yue Liu, Bobo Xi, Pengbo Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add SFT plus HDPO post-training to the base model | Qwen2.5-VL-32B · MM-Route test | RDR: 0.667 -> 0.831 | Improved |
| add SFT plus HDPO post-training to the base model | Qwen2.5-VL-32B · MM-Route test | SHR (%): 31.9 -> 14.0 | Improved |
| add SFT plus HDPO post-training to the base model | Qwen2.5-VL-32B · MM-Route test | TSPR (%): 34.5 -> 77.5 | Improved |
| add HDPO on top of SFT (ablation) | Qwen2.5-VL-32B-SFT · MM-Route test | RDR: 0.789 -> 0.831 | Improved |
| add HDPO on top of SFT (ablation) | Qwen2.5-VL-7B-SFT · MM-Route test | ORS: 3.00 -> 3.37 | Improved |
| use standard DPO (ground-truth accepted, SFT output rejected) instead of verifier-refined HDPO pairs (ablation) | Qwen2.5-VL-7B-SFT · MM-Route test | RDR: 0.763 -> 0.733 | Hurt |
| use standard DPO instead of SFT (ablation) | Qwen2.5-VL-7B-SFT · MM-Route test | SHR (%): 22.1 -> 27.6 | Hurt |
| use standard DPO instead of SFT (ablation) | Qwen2.5-VL-32B-SFT · MM-Route test | RDR: 0.789 -> 0.765 | Hurt |
| use map tile (text-image) instead of text-only input with HDPO (ablation) | Qwen2.5-VL-32B-HDPO · MM-Route test | RDR: 0.789 -> 0.831 | Improved |
| use map tile instead of text-only input with HDPO (ablation) | Qwen2.5-VL-32B-HDPO · MM-Route test | TSPR (%): 73.5 -> 77.5 | Improved |
| use map tile instead of text-only input with HDPO (ablation) | Qwen2.5-VL-7B-HDPO · MM-Route test | ORS: 3.39 -> 3.37 | No clear effect |
| use map tile instead of text-only input with SFT (ablation) | Qwen2.5-VL-7B-SFT · MM-Route test | RTPR (%): 84.8 -> 83.8 | Mixed |
Closest papers by meaning
- TraveLLaMA: A Multimodal Travel Assistant with Large-Scale Dataset and Structured Reasoning (AAAI 2026 · similarity 0.87)
- Semantic Routing via Autoregressive Modeling (NeurIPS 2024 · similarity 0.87)
- MapEval: A Map-Based Evaluation of Geo-Spatial Reasoning in Foundation Models (ICML 2025 · similarity 0.86)
- IMAIA: Interactive Maps AI Assistant for Travel Planning and Geo-Spatial Intelligence (CVPR 2026 · similarity 0.85)
- Think Before You Drive: World Model-Inspired Multimodal Grounding (CVPR 2026 · similarity 0.85)
- SpatialScore: Towards Comprehensive Evaluation for Spatial Intelligence (CVPR 2026 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
