Image de couverture de livre

Beyond the Permutation Symmetry of Transformers: The Role of Rotation for Model Fusion

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhang, Binchi, Zheng, Zaiyi, Chen, Zhengzhang, Li, Jundong
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Resolving Editing-Unlearning Conflicts: A Knowledge Codebook Framework for Large Language Model Updating
par: Zhang, Binchi, et autres
Publié: (2025)

PerFormer: A Permutation Based Vision Transformer for Remaining Useful Life Prediction
par: Fan, Zhengyang, et autres
Publié: (2025)

Instruction-Guided Fusion of Multi-Layer Visual Features in Large Vision-Language Models
par: Li, Xu, et autres
Publié: (2024)

Beyond Simple Fusion: Adaptive Gated Fusion for Robust Multimodal Sentiment Analysis
par: Wu, Han, et autres
Publié: (2025)

Exploring Magnitude Preservation and Rotation Modulation in Diffusion Transformers
par: Bill, Eric Tillman, et autres
Publié: (2025)

Eff-GRot: Efficient and Generalizable Rotation Estimation with Transformers
par: Mathioulakis, Fanis, et autres
Publié: (2025)

Investigating the Role of Bilateral Symmetry for Inpainting Brain MRI
par: Kuznetsov, Sergey, et autres
Publié: (2025)

A Transformer-based Multimodal Fusion Model for Efficient Crowd Counting Using Visual and Wireless Signals
par: Cui, Zhe, et autres
Publié: (2025)

Rotation-Robust Regression with Convolutional Model Trees
par: Li, Hongyi, et autres
Publié: (2026)

Hausdorff Distance Matching with Adaptive Query Denoising for Rotated Detection Transformer
par: Lee, Hakjin, et autres
Publié: (2023)

DiRotQ: Rotation-Aware Quantization for 4-bit Diffusion Transformers
par: Sharify, Sayeh, et autres
Publié: (2026)

Adaptive Transformer Attention and Multi-Scale Fusion for Spine 3D Segmentation
par: Xiang, Yanlin, et autres
Publié: (2025)

MMInference: Accelerating Pre-filling for Long-Context VLMs via Modality-Aware Permutation Sparse Attention
par: Li, Yucheng, et autres
Publié: (2025)

Relating CNN-Transformer Fusion Network for Change Detection
par: Gao, Yuhao, et autres
Publié: (2024)

Investigating Permutation-Invariant Discrete Representation Learning for Spatially Aligned Images
par: Stirling, Jamie S. J., et autres
Publié: (2026)

DualSwinFusionSeg: Multimodal Martian Landslide Segmentation via Dual Swin Transformer with Multi-Scale Fusion and UNet++
par: Kabir, Shahriar, et autres
Publié: (2026)

Beyond Fixed Formulas: Data-Driven Linear Predictor for Efficient Diffusion Models
par: Shen, Zhirong, et autres
Publié: (2026)

TinyFusion: Diffusion Transformers Learned Shallow
par: Fang, Gongfan, et autres
Publié: (2024)

Improving Robustness of LiDAR-Camera Fusion Model against Weather Corruption from Fusion Strategy Perspective
par: Huang, Yihao, et autres
Publié: (2024)

TDEC: Deep Embedded Image Clustering with Transformer and Distribution Information
par: Zhang, Ruilin, et autres
Publié: (2026)

Symmetry-Robust 3D Orientation Estimation
par: Scarvelis, Christopher, et autres
Publié: (2024)

Permutation Learning with Only N Parameters: From SoftSort to Self-Organizing Gaussians
par: Barthel, Kai Uwe, et autres
Publié: (2025)

The Role of Masking for Efficient Supervised Knowledge Distillation of Vision Transformers
par: Son, Seungwoo, et autres
Publié: (2023)

CrossFuse: Learning Infrared and Visible Image Fusion by Cross-Sensor Top-K Vision Alignment and Beyond
par: Shi, Yukai, et autres
Publié: (2025)

AFN: Adaptive Fusion Normalization via an Encoder-Decoder Framework
par: Zhou, Zikai, et autres
Publié: (2023)

Beyond Gaussian Bottlenecks: Topologically Aligned Encoding of Vision-Transformer Feature Spaces
par: Bond, Andrew, et autres
Publié: (2026)

Enhancing 3D Human Pose Estimation Amidst Severe Occlusion with Dual Transformer Fusion
par: Ghafoor, Mehwish, et autres
Publié: (2024)

DashFusion: Dual-stream Alignment with Hierarchical Bottleneck Fusion for Multimodal Sentiment Analysis
par: Wen, Yuhua, et autres
Publié: (2025)

Predictive Dynamic Fusion
par: Cao, Bing, et autres
Publié: (2024)

TerDiT: Ternary Diffusion Models with Transformers
par: Lu, Xudong, et autres
Publié: (2024)

Soft Mixture Denoising: Beyond the Expressive Bottleneck of Diffusion Models
par: Li, Yangming, et autres
Publié: (2023)

Rethinking Attention: Polynomial Alternatives to Softmax in Transformers
par: Saratchandran, Hemanth, et autres
Publié: (2024)

In-Context Symmetries: Self-Supervised Learning through Contextual World Models
par: Gupta, Sharut, et autres
Publié: (2024)

DeFusion: An Effective Decoupling Fusion Network for Multi-Modal Pregnancy Prediction
par: Ouyang, Xueqiang, et autres
Publié: (2025)

ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy
par: Vishniakov, Kirill, et autres
Publié: (2023)

Expanding the Role of Diffusion Models for Robust Classifier Training
par: Huang, Pin-Han, et autres
Publié: (2026)

HiPART: Hierarchical Pose AutoRegressive Transformer for Occluded 3D Human Pose Estimation
par: Zheng, Hongwei, et autres
Publié: (2025)

Beyond DAGs: A Latent Partial Causal Model for Multimodal Learning
par: Liu, Yuhang, et autres
Publié: (2024)

Restructuring Vector Quantization with the Rotation Trick
par: Fifty, Christopher, et autres
Publié: (2024)

SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention
par: Zhang, Jintao, et autres
Publié: (2025)