AI Paper Atlas

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

ICLR 2026 · Vision-language and multimodal › Robot action and navigation · approach: Embodied multimodal LLM agents

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 changedWhereMeasuredEffect
add flow-matching policy head (continuous waypoints) instead of autoregressive action chunks (ablation)OmniNav · HM3D-OVON Val-UnseenSR: 35.3 -> 43.5Improved
add flow-matching policy head (ablation)OmniNav · R2R-CE Val-UnseenSR: 59.8 -> 69.5Improved
add flow-matching policy head (ablation)OmniNav · RxR-CE Val-UnseenSR: 64.1 -> 73.6Improved
add slow system with frontier exploration and visual memory (ablation)OmniNav · HM3D-OVON Val-UnseenSR: 43.5 -> 55.9Improved
add general MLLM, grounding and embodied QA data (ablation)OmniNav* · HM3D-OVON Val-UnseenSR: 55.9 -> 57.7Improved
add explicit chain-of-thought to slow system (ablation)OmniNav* · HM3D-OVON Val-UnseenSR: 57.7 -> 59.2Improved
scale backbone from 3B to 7B without additional data (ablation)OmniNav* · HM3D-OVON Val-UnseenSR: 55.9 -> 57.2Improved
scale backbone from 3B to 7B with additional data (ablation)OmniNav* · HM3D-OVON Val-UnseenSR: 57.7 -> 57.9No clear effect
add Embodied QA data to grounding and general data (ablation)OmniNav* · HM3D-OVON Val-UnseenSR: 56.5 -> 57.7Improved

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.

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy