AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

Path-level Hindsight Instructions for Semantic Exploration in Vision-Language Navigation

Sungjune Kim, Sangpil Kim, Honglak Lee

ECCV 2026 · Vision-language and multimodal › Robot action and navigation · approach: Reasoning-enhanced vision-language navigation · 0 citations (OpenAlex)

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 Phi-Nav hindsight instructions (DAgger)CMA-D-P-A · R2R-CE val unseenSR: 32.10 -> 34.08Improved
add Phi-Nav hindsight instructions (DAgger)CMA-D · R2R-CE val unseenSR: 26.64 -> 27.62Improved
add Phi-Nav (scheduled sampling)ETPNav · R2R-CE val unseenSR: 57.21 -> 62.58Improved
add Phi-Nav (scheduled sampling)ETPNav · R2R-CE val unseenSPL: 49.15 -> 52.74Improved
add Phi-NavETPNav · RxR-CE val unseenSR: 54.79 -> 55.83Improved
add Phi-NavETPNav · RxR-CE val unseenNE: 5.64 -> 5.67Hurt
add alignment-weighted hindsight loss (TIAW) instead of fixed lambda=1.0 (ablation)Phi-Nav on ETPNav · R2R-CE val unseenSPL: 46.32 -> 51.32Improved
use fixed lambda=0.1 instead of lambda=1.0 (ablation)Phi-Nav on ETPNav · R2R-CE val unseenSPL: 46.32 -> 48.66Improved
add landmark-aware scoring to TIAW (ablation)Phi-Nav on ETPNav · R2R-CE val unseenSR: 61.18 -> 62.58Improved
use Qwen2.5-VL-7B instead of 3B speaker (ablation)Phi-Nav on ETPNav · R2R-CE val unseenSPL: 47.32 -> 52.74Improved
use Qwen2.5-VL-7B instead of Qwen3-VL-8B speaker (ablation)Phi-Nav on ETPNav · R2R-CE val unseenSR: 60.05 -> 62.58Improved
add expert-in-context example to zero-shot speaker (ablation)Phi-Nav on ETPNav · R2R-CE val unseenSPL: 50.55 -> 52.74Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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