Image de couverture de livre

SpiralFormer: Looped Transformers Can Learn Hierarchical Dependencies via Multi-Resolution Recursion

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yu, Chengting, Shu, Xiaobo, Wang, Yadao, Zhang, Yizhen, Wu, Haoyi, Wu, You, Long, Rujiao, Chen, Ziheng, Xu, Yuchi, Su, Wenbo, Zheng, Bo
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

MeSH: Memory-as-State-Highways for Recursive Transformers
par: Yu, Chengting, et autres
Publié: (2025)

YOCO++: Enhancing YOCO with KV Residual Connections for Efficient LLM Inference
par: Wu, You, et autres
Publié: (2026)

Expert Divergence Learning for MoE-based Language Models
par: Li, Jiaang, et autres
Publié: (2026)

Reasoning Palette: Modulating Reasoning via Latent Contextualization for Controllable Exploration for (V)LMs
par: Long, Rujiao, et autres
Publié: (2025)

Ink Spiral: Symbolic Transformation from The Thinker to the Four Gentlemen
par: Peng, Lingyu, et autres
Publié: (2026)

HIP: Hierarchical Point Modeling and Pre-training for Visual Information Extraction
par: Long, Rujiao, et autres
Publié: (2024)

RAVR: Reference-Answer-guided Variational Reasoning for Large Language Models
par: Lin, Tianqianjin, et autres
Publié: (2025)

LoopQ: Quantization for Recursive Transformers
par: Fang, Rui, et autres
Publié: (2026)

Transforming Image Super-Resolution: A ConvFormer-based Efficient Approach
par: Wu, Gang, et autres
Publié: (2024)

A Systematic Study of Cross-Layer KV Sharing for Efficient LLM Inference
par: Wu, You, et autres
Publié: (2024)

A Residual Variance Matching Recursive Least Squares Filter for Real-time UAV Terrain Following
par: Wu, Xiaobo, et autres
Publié: (2025)

SDiT: Spiking Diffusion Model with Transformer
par: Yang, Shu, et autres
Publié: (2024)

Hierarchical Side-Tuning for Vision Transformers
par: Lin, Weifeng, et autres
Publié: (2023)

Weight Spectra Induced Efficient Model Adaptation
par: Si, Chongjie, et autres
Publié: (2025)

A flexible framework for identifying urban villages using Sentinel-2 observations and deep learning
par: Wu, Yizhen
Publié: (2025)

The Franc Spiral Equation: Recursive Harmonic Identity
par: Benjamin D. Franc
Publié: (2025)

LoopFormer: Elastic-Depth Looped Transformers for Latent Reasoning via Shortcut Modulation
par: Jeddi, Ahmadreza, et autres
Publié: (2026)

Recursive Generalization Transformer for Image Super-Resolution
par: Chen, Zheng, et autres
Publié: (2023)

HiMemFormer: Hierarchical Memory-Aware Transformer for Multi-Agent Action Anticipation
par: Wang, Zirui, et autres
Publié: (2024)

Exploring the Potential of Probabilistic Transformer for Time Series Modeling: A Report on the ST-PT Framework
par: Xiong, Zhangzhi, et autres
Publié: (2026)

NAN: A Training-Free Solution to Coefficient Estimation in Model Merging
par: Si, Chongjie, et autres
Publié: (2025)

Power-Law-Exponential Interaction Induced Quantum Spiral Phases
par: Tian, Guoqing, et autres
Publié: (2024)

SuperFormer: Volumetric Transformer Architectures for MRI Super-Resolution
par: Forigua, Cristhian, et autres
Publié: (2024)

EventFormer: A Node-graph Hierarchical Attention Transformer for Action-centric Video Event Prediction
par: Su, Qile, et autres
Publié: (2025)

Scaling Probabilistic Transformer via Efficient Cross-Scale Hyperparameter Transfer
par: Kuang, Penghao, et autres
Publié: (2026)

Minor Allele Frequency Filtering Can Strongly Bias Uniqueness Estimates Within and Across Species
par: Yuchi Zheng
Publié: (2026)

ComplexFormer: Disruptively Advancing Transformer Inference Ability via Head-Specific Complex Vector Attention
par: Shao, Jintian, et autres
Publié: (2025)

Understanding and Detecting Peer Dependency Resolving Loop in npm Ecosystem
par: Wang, Xingyu, et autres
Publié: (2025)

Spiral and Mixed Plaquette-Dimer Phases in the $S=1$ and $3/2$ Shastry-Sutherland Heisenberg Model
par: Wu, Han-Qing, et autres
Publié: (2026)

Towards Mitigating API Hallucination in Code Generated by LLMs with Hierarchical Dependency Aware
par: Chen, Yujia, et autres
Publié: (2025)

What Makes Looped Transformers Perform Better Than Non-Recursive Ones
par: Gong, Zixuan, et autres
Publié: (2025)

ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation
par: Wang, Shu, et autres
Publié: (2025)

The Minkowski problem of $p$-affine dual curvature measures
par: Lin, Youjiang, et autres
Publié: (2026)

The $L_p$ Minkowski problems on affine dual quermassintegrals
par: Lin, Youjiang, et autres
Publié: (2025)

TimeFormer: Capturing Temporal Relationships of Deformable 3D Gaussians for Robust Reconstruction
par: Jiang, DaDong, et autres
Publié: (2024)

MixFormerV2: Efficient Fully Transformer Tracking
par: Cui, Yutao, et autres
Publié: (2023)

DuoFormer: Leveraging Hierarchical Representations by Local and Global Attention Vision Transformer
par: Tang, Xiaoya, et autres
Publié: (2025)

HGTS-Former: Hierarchical HyperGraph Transformer for Multivariate Time Series Analysis
par: Si, Hao, et autres
Publié: (2025)

RigidFormer: Learning Rigid Dynamics using Transformers
par: Dou, Zhiyang, et autres
Publié: (2026)

TouchFormer: A Robust Transformer-based Framework for Multimodal Material Perception
par: Lyu, Kailin, et autres
Publié: (2025)