AI Paper Atlas

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

Cross from Left to Right Brain: Adaptive Text Dreamer for Vision-and-Language Navigation

Pingrui Zhang, Yifei Su, Pengyuan Wu, Dong An, Li Zhang, Zhigang Wang, Dong Wang, Bin Zhao

CVPR 2026 · Vision-language and multimodal › Robot action and navigation · approach: Reasoning-enhanced vision-language navigation · 18 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 both State Estimation LLM and Imagination LLM to the baseline (ablation)DUET-style baseline · R2R val unseenSR: 63 -> 75Improved
add both State Estimation LLM and Imagination LLM to the baseline (ablation)DUET-style baseline · R2R val unseenSPL: 52 -> 63Improved
add only one of the two LLM modules (SELLM or IMLLM) to the baseline (ablation)DUET-style baseline · R2R val unseenSR: 63 -> 72 / 73Improved
use both modules together instead of either one alone (ablation)ATD · R2R val seenSR: 71 -> 76Improved
ground imagination with state estimation (state as query) rather than reverse roles (ablation)ATD SGCA · R2R val seenSR: 71.79 -> 75.61Improved
ground imagination with state estimation (state as query) rather than reverse roles (ablation)ATD SGCA · R2R val unseenSR: 73.95 -> 74.63Improved
add SGCA cross-attention instead of parallel summation (ablation)ATD · R2R val unseenSPL: 61.89 -> 63.35Improved
increase SGCA layers from 1 to 4 (ablation)ATD · R2R val seenSPL: 63.15 -> 67.49Improved
increase SGCA layers from 1 to 4 (ablation)ATD · R2R val unseenSR: 74.54 -> 74.63No clear effect
use ATD instead of single-brain NavGPT2 (1.5B)LLM-based VLN · R2R test unseenSR: 71 -> 74Improved
keep LLM text generation ability (frozen 1.5B) instead of fully fine-tuned 7B NaviLLMLLM-based VLN · R2R test unseenSR: 68 -> 74Improved
use ATD instead of DUET in zero-shot transfer from R2Rnavigation policy · REVERIE val unseenSR: 24 -> 27Improved

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