Imagen de Portada

A Circular Argument : Does RoPE need to be Equivariant for Vision?

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	van de Geijn, Chase, Lüddecke, Timo, Turishcheva, Polina, Ecker, Alexander S.
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

RoPECraft: Training-Free Motion Transfer with Trajectory-Guided RoPE Optimization on Diffusion Transformers
por: Gokmen, Ahmet Berke, et al.
Publicado: (2025)

Do traveling waves make good positional encodings?
por: van de Geijn, Chase, et al.
Publicado: (2025)

ReRoPE: Repurposing RoPE for Relative Camera Control
por: Li, Chunyang, et al.
Publicado: (2026)

Charting New Territories: Exploring the Geographic and Geospatial Capabilities of Multimodal LLMs
por: Roberts, Jonathan, et al.
Publicado: (2023)

Learning the RoPEs: Better 2D and 3D Position Encodings with STRING
por: Schenck, Connor, et al.
Publicado: (2025)

Untwisting RoPE: Frequency Control for Shared Attention in DiTs
por: Mikaeili, Aryan, et al.
Publicado: (2026)

FishRoPE: Projective Rotary Position Embeddings for Omnidirectional Visual Perception
por: Ahuja, Rahul, et al.
Publicado: (2026)

Spiral RoPE: Rotate Your Rotary Positional Embeddings in the 2D Plane
por: Liu, Haoyu, et al.
Publicado: (2026)

ID-Align: RoPE-Conscious Position Remapping for Dynamic High-Resolution Adaptation in Vision-Language Models
por: Li, Bozhou, et al.
Publicado: (2025)

ComRoPE: Scalable and Robust Rotary Position Embedding Parameterized by Trainable Commuting Angle Matrices
por: Yu, Hao, et al.
Publicado: (2025)

Diffusion MRI Transformer with a Diffusion Space Rotary Positional Embedding (D-RoPE)
por: Kung, Gustavo Chau Loo, et al.
Publicado: (2026)

ExtraVAR: Stage-Aware RoPE Remapping for Resolution Extrapolation in Visual Autoregressive Models
por: Yan, Feihong, et al.
Publicado: (2026)

Infinity-RoPE: Action-Controllable Infinite Video Generation Emerges From Autoregressive Self-Rollout
por: Yesiltepe, Hidir, et al.
Publicado: (2025)

RoPeSLR: 3D RoPE-driven Sparse-LowRank Attention for Efficient Diffusion Transformers
por: Liu, Yuxi, et al.
Publicado: (2026)

FreeFlux: Understanding and Exploiting Layer-Specific Roles in RoPE-Based MMDiT for Versatile Image Editing
por: Wei, Tianyi, et al.
Publicado: (2025)

Relaxed Rotational Equivariance via $G$-Biases in Vision
por: Wu, Zhiqiang, et al.
Publicado: (2024)

Anchor Forcing: Anchor Memory and Tri-Region RoPE for Interactive Streaming Video Diffusion
por: Yang, Yang, et al.
Publicado: (2026)

Periodic RoPE for Infinite Context LLMs
por: Huo, Simin
Publicado: (2026)

Scaling Laws of RoPE-based Extrapolation
por: Liu, Xiaoran, et al.
Publicado: (2023)

Zero-Shot Multi-Animal Tracking in the Wild
por: Meier, Jan Frederik, et al.
Publicado: (2025)

Octic Vision Transformers: Quicker ViTs Through Equivariance
por: Nordström, David, et al.
Publicado: (2025)

Scaling Vision Models Does Not Consistently Improve Localisation-Based Explanation Quality
por: Cedro, Mateusz, et al.
Publicado: (2026)

RoMA: Scaling up Mamba-based Foundation Models for Remote Sensing
por: Wang, Fengxiang, et al.
Publicado: (2025)

RoGA: Towards Generalizable Deepfake Detection through Robust Gradient Alignment
por: Qiu, Lingyu, et al.
Publicado: (2025)

Equivariant Flow Matching for Point Cloud Assembly
por: Wang, Ziming, et al.
Publicado: (2025)

RoSe: Robust Self-supervised Stereo Matching under Adverse Weather Conditions
por: Wang, Yun, et al.
Publicado: (2025)

RoBus: A Multimodal Dataset for Controllable Road Networks and Building Layouts Generation
por: Li, Tao, et al.
Publicado: (2024)

MoPE-CLIP: Structured Pruning for Efficient Vision-Language Models with Module-wise Pruning Error Metric
por: Lin, Haokun, et al.
Publicado: (2024)

RoCOCO: Robustness Benchmark of MS-COCO to Stress-test Image-Text Matching Models
por: Park, Seulki, et al.
Publicado: (2023)

RoDE: Linear Rectified Mixture of Diverse Experts for Food Large Multi-Modal Models
por: Jiao, Pengkun, et al.
Publicado: (2024)

Vision Transformers: the threat of realistic adversarial patches
por: Cools, Kasper, et al.
Publicado: (2025)

Few-shot Implicit Function Generation via Equivariance
por: Huang, Suizhi, et al.
Publicado: (2025)

Learning Generalizable Shape Completion with SIM(3) Equivariance
por: Wang, Yuqing, et al.
Publicado: (2025)

Normalization Equivariance for Arbitrary Backbones, with Application to Image Denoising
por: Saied, Youssef, et al.
Publicado: (2026)

Does Bigger Mean Better? Comparitive Analysis of CNNs and Biomedical Vision Language Modles in Medical Diagnosis
por: Tong, Ran, et al.
Publicado: (2025)

Does Visual Information Play a Decisive Role in Vision-Language-Action Model Driving Behavior?
por: He, Jingtao, et al.
Publicado: (2026)

GeoPE:A Unified Geometric Positional Embedding for Structured Tensors
por: Yao, Yupu, et al.
Publicado: (2025)

Demystifying the Slash Pattern in Attention: The Role of RoPE
por: Cheng, Yuan, et al.
Publicado: (2026)

Does AI See like Art Historians? Interpreting How Vision Language Models Recognize Artistic Style
por: Limpijankit, Marvin, et al.
Publicado: (2026)

A Simple Efficiency Incremental Learning Framework via Vision-Language Model with Nonlinear Multi-Adapters
por: Luo, Haihua, et al.
Publicado: (2026)