Adaptive 3D-RoPE: Physics-Aligned Rotary Positional Encoding for Wireless Foundation Models
eess.SP, cs.AI
Submitted: 2026-05-01
Updated: 2026-09-14
Comments: 13 pages
Code: https://github.com/zcy8998/adaptive-3d-rope
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- WiFo-2: a generalist foundation model unifies heterogeneous wireless system design
- VideoRoPE: What Makes for Good Video Rotary Position Embedding?
- Noise-Aware Mixed-State Quantum Computation via Parameterized Quantum Channels
- ChannelGPT: A Large Model to Generate Digital Twin Channel for 6G Environment Intelligence
- BERT4MIMO: A Foundation Model using BERT Architecture for Massive MIMO Channel State Information Prediction
- LVM4CSI: Enabling Direct Application of Pre-Trained Large Vision Models for Wireless Channel Tasks
- WiFo-CF: Wireless Foundation Model for CSI Feedback
- HeterCSI: Channel-Adaptive Heterogeneous CSI Pretraining Framework for Generalized Wireless Foundation Models
- LWM-Temporal: Sparse Spatio-Temporal Attention for Wireless Channel Representation Learning
- Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation
- Round and Round We Go! What makes Rotary Positional Encodings useful?
- Extending Context Window of Large Language Models via Positional Interpolation
- Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
- HoPE: Hybrid of Position Embedding for Long Context Vision-Language Models
- LieRE: Lie Rotational Positional Encodings
- LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens
- Context-aware Rotary Position Embedding
- Bridging the Modality Gap: Enhancing Channel Prediction with Semantically Aligned LLMs and Knowledge Distillation
Related papers
- Runtime Assurance Under Measurement Attack: Necessary and Sufficient Observability Conditions for Learned Control in Radio Access Networks
- Physics-Constrained Deep Learning Model for Contactless Blood Pressure Monitoring from Triaxial Bodyseismography
- Uncertainty Quantification in Machine Learning for Biosignal Applications -- A Review
- Continuous Orthogonal Mode Decomposition: Haptic Signal Prediction in Tactile Internet
- Generative Models for Modeling and Synthesizing MIMO Channels in Adverse Weather Conditions
- Deep-Learning-Based Pixelated Microwave Filter Design and Characterization using Electro-Optical Electric-Field Measurements