Towards Dual-Brain Minimal Sufficient Representation for Vision-Language Navigation

2026-07-25 · Yihao Wu, Chenyi Xu, Liqi Yan, Chenhuan Cai, Geyong Min, Bin Lin, Fangli Guan, Jianhui Zhang, Pan Li arxiv

Vision-and-Language Navigation in continuous environments (VLN-CE) requires an agent to ground language in egocentric observations and plan in unseen scenes. Although recent multimodal large models and world-model-based methods have improved navigation, they often preserve excessive task-irrelevant detail, weakening generalization and increasing computational burden. We propose BrainNav, a navigation framework grounded in the Principle of Minimal Sufficiency. BrainNav consists of three components: a Logical Anchor Model that implements instruction-aware selective perception to suppress environmental noise, a Minimalist Constraint Alignment module that serves as a compact cross-modal bottleneck, efficiently synchronizing discrete linguistic intent with continuous latent dynamics while filtering out redundant information, and a Compression World Model that predicts action-conditioned states within a condensed, low-rank latent space. These modules align semantic intent with spatial perception, enhancing the agent's robustness and efficiency in complex tasks. Experiments show that BrainNav improves over prior SOTA by 2.0 % / 1.0 in SR/SPL on R2R-CE val-unseen and 0.94 % / 0.78 on RxR-CE val-unseen. These results indicate that minimally sufficient world representations provide an effective foundation for robust VLN.

📄 PDF Abstract BibTeX arXiv:2607.23181

Code (0)

등록된 구현이 없습니다.

Tasks

Vision-Language Navigation

DD-CAM: Minimal Sufficient Explanations for Vision Models Using Delta Debugging

2026-02-22 · Krishna Khadka, Yu Lei, Raghu N. Kacker, D. Richard Kuhn arxiv

We introduce a gradient-free framework for identifying minimal, sufficient, and decision-preserving explanations in vision models by isolating the smallest subset of representational units whose joint activation preserve…

Contravariance Theory: Strong Alignment for Minimal Solutions to Hard Tasks

2026-07-09 · Dan Yamins, Aran Nayebi arxiv

A series of results from the NeuroAI over the past fifteen years have raised core questions both about how to compare Deep Neural Network (DNN) models to the brain, and about how much convergent evolution to expect betwe…

Brain-mediated Transfer Learning of Convolutional Neural Networks

2019-05-24 · Satoshi Nishida, Yusuke Nakano, Antoine Blanc, Naoya Maeda 외

The human brain can effectively learn a new task from a small number of samples, which indicate that the brain can transfer its prior knowledge to solve tasks in different domains. This function is analogous to transfer …

BIG-bench Machine Learning Transfer Learning

AGD-Autoencoder: Attention Gated Deep Convolutional Autoencoder for Brain Tumor Segmentation

2021-07-07 · Tim Cvetko

Brain tumor segmentation is a challenging problem in medical image analysis. The endpoint is to generate the salient masks that accurately identify brain tumor regions in an fMRI screening. In this paper, we propose a no…

Brain Segmentation Brain Tumor Segmentation Medical Image Analysis Segmentation+1

Minimal Sufficient Representations for Self-interpretable Deep Neural Networks

2026-03-25 · Zhiyao Tan, Liu Li, Huazhen Lin arxiv

Deep neural networks (DNNs) achieve remarkable predictive performance but remain difficult to interpret, largely due to overparameterization that obscures the minimal structure required for interpretation. Here we introd…

Representation Learning