paper-with-me

Papers

MANAR: Memory-augmented Attention with Navigational Abstract Conceptual Representation

2026-03-19 · Zuher Jahshan, Ben Ben Ishay, Leonid Yavits arxiv

MANAR (Memory-augmented Attention with Navigational Abstract Conceptual Representation), contextualization layer generalizes standard multi-head attention (MHA) by instantiating the principles of Global Workspace Theory (GWT). While MHA enables unconstrained all-to-all communication, it lacks the functional bottleneck and global integration mechanisms hypothesized in cognitive models of consciousness. MANAR addresses this by implementing a central workspace through a trainable memory of abstract concepts and an Abstract Conceptual Representation (ACR). The architecture follows a two-stage logic that maps directly to GWT mechanics: (i) an integration phase, where retrieved memory concepts converge to form a collective "mental image" (the ACR) based on input stimuli; and (ii) a broadcasting phase, where this global state navigates and informs the contextualization of individual local tokens. We demonstrate that efficient linear-time scaling is a fundamental architectural byproduct of instantiating GWT functional bottleneck, as routing global information through a constant-sized ACR resolves the quadratic complexity inherent in standard attention. MANAR is a compatible re-parameterization of MHA with identical semantic roles for its projections, enabling knowledge transfer from pretrained transformers via weight-copy and thus overcoming the adoption barriers of structurally incompatible linear-time alternatives. MANAR enables non-convex contextualization, synthesizing representations that provably lie outside the convex hull of input tokens - a mathematical reflection of the creative synthesis described in GWT. Empirical evaluations confirm that MANAR matches or exceeds strong baselines across language (GLUE score of 85.1), vision (83.9% ImageNet-1K), and speech (2.7% WER on LibriSpeech), positioning it as an efficient and expressive alternative to quadratic attention.

📄 PDF Abstract BibTeX arXiv:2603.18676

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Virtual Guidance as a Mid-level Representation for Navigation with Augmented Reality

2023-03-05 · Hsuan-Kung Yang, Tsung-Chih Chiang, Jou-Min Liu, Ting-Ru Liu 외

In the context of autonomous navigation, effectively conveying abstract navigational cues to agents in dynamic environments presents significant challenges, particularly when navigation information is derived from divers…

Autonomous NavigationUnity

Flexible and Creative Chinese Poetry Generation Using Neural Memory

2017-05-10 · ACL 2017 7 · Jiyuan Zhang, Yang Feng, Dong Wang, Yang Wang 외

It has been shown that Chinese poems can be successfully generated by sequence-to-sequence neural models, particularly with the attention mechanism. A potential problem of this approach, however, is that neural models ca…

Talk2Nav: Long-Range Vision-and-Language Navigation with Dual Attention and Spatial Memory

2019-10-04 · Arun Balajee Vasudevan, Dengxin Dai, Luc van Gool

The role of robots in society keeps expanding, bringing with it the necessity of interacting and communicating with humans. In order to keep such interaction intuitive, we provide automatic wayfinding based on verbal nav…

Autonomous DrivingVision and Language NavigationVisual Navigation

A Deep Learning Based Behavioral Approach to Indoor Autonomous Navigation

2018-03-12 · Gabriel Sepulveda, Juan Carlos Niebles, Alvaro Soto

We present a semantically rich graph representation for indoor robotic navigation. Our graph representation encodes: semantic locations such as offices or corridors as nodes, and navigational behaviors such as enter offi…

Autonomous NavigationDeep Learning

The Library Theorem: How External Organization Governs Agentic Reasoning Capacity

2026-03-22 · Zachary F. Mainen arxiv

Externalized reasoning is already exploited by transformer-based agents through chain-of-thought, but structured retrieval -- indexing over one's own reasoning state -- remains underexplored. We formalize the transformer…