Research map / Vision-language and multimodal / Robot action and navigation
OmniNav: A Unified Framework for Prospective Exploration and Visual-Language Navigation
Xinda Xue, Junjun Hu, Minghua Luo, Xie Shichao, Jintao Chen, Zixun Xie, Quan Kuichen, GuoWei, Zedong Chu, Mu Xu, Zhengzhou Zhu
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 flow-matching policy head (continuous waypoints) instead of autoregressive action chunks (ablation) | OmniNav · HM3D-OVON Val-Unseen | SR: 35.3 -> 43.5 | Improved |
| add flow-matching policy head (ablation) | OmniNav · R2R-CE Val-Unseen | SR: 59.8 -> 69.5 | Improved |
| add flow-matching policy head (ablation) | OmniNav · RxR-CE Val-Unseen | SR: 64.1 -> 73.6 | Improved |
| add slow system with frontier exploration and visual memory (ablation) | OmniNav · HM3D-OVON Val-Unseen | SR: 43.5 -> 55.9 | Improved |
| add general MLLM, grounding and embodied QA data (ablation) | OmniNav* · HM3D-OVON Val-Unseen | SR: 55.9 -> 57.7 | Improved |
| add explicit chain-of-thought to slow system (ablation) | OmniNav* · HM3D-OVON Val-Unseen | SR: 57.7 -> 59.2 | Improved |
| scale backbone from 3B to 7B without additional data (ablation) | OmniNav* · HM3D-OVON Val-Unseen | SR: 55.9 -> 57.2 | Improved |
| scale backbone from 3B to 7B with additional data (ablation) | OmniNav* · HM3D-OVON Val-Unseen | SR: 57.7 -> 57.9 | No clear effect |
| add Embodied QA data to grounding and general data (ablation) | OmniNav* · HM3D-OVON Val-Unseen | SR: 56.5 -> 57.7 | Improved |
Later papers that compared with this method
1 later accepted paper reports OmniNav as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- One Scan is Enough: Demonstration-Free Adaptation for Language-Guided Navigation (NeurIPS 2026 · better on 1 of 1 shared result)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- CorrectNav — CorrectNav: Self-Correction Flywheel Empowers Vision-Language-Action Navigation Model (AAAI 2026) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- NavBench: Probing Multimodal Large Language Models for Embodied Navigation (NeurIPS 2025 · similarity 0.90)
- NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models (AAAI 2024 · similarity 0.90)
- NavForesee: A Unified Vision-Language World Model for Hierarchical Planning and Dual-Horizon Navigation Prediction (CVPR 2026 · similarity 0.90)
- ImagineNav: Prompting Vision-Language Models as Embodied Navigator through Scene Imagination (ICLR 2025 · similarity 0.90)
- CoNavBench: Collaborative Long-Horizon Vision-Language Navigation Benchmark (ICLR 2026 · similarity 0.90)
- RAO-Nav: Probing Omni-Language Models for Zero-shot Semantic Audio-Visual Navigation (NeurIPS 2026 · similarity 0.89)
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.
