Fractional Rotation, Full Potential? Investigating Performance and Convergence of Partial RoPE

• URL: http://arxiv.org/abs/2603.11611v1
• Date: Thu, 12 Mar 2026 07:05:13 GMT
• Title: Fractional Rotation, Full Potential? Investigating Performance and Convergence of Partial RoPE
• Abstract summary: Rotary Positional Embedding (RoPE) is a common choice in transformer architectures for encoding relative positional information.<n>We find up to 10x memory savings over the standard RoPE cache, while achieving comparable final loss.
• Score: 18.16869367103229
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Rotary Positional Embedding (RoPE) is a common choice in transformer architectures for encoding relative positional information. Although earlier work has examined omitting RoPE in specific layers, the effect of varying the fraction of hidden dimensions that receive rotary transformations remains largely unexplored. This design choice can yield substantial memory savings, which becomes especially significant at long context lengths. We find up to 10x memory savings over the standard RoPE cache, while achieving comparable final loss. In this work, we present a systematic study examining the impact of partial RoPE on training dynamics and convergence across architectures and datasets. Our findings uncover several notable patterns: (1) applying RoPE to only a small fraction of dimensions (around 10%) achieves convergence comparable to using full RoPE; (2) these trends hold consistently across model size, sequence lengths and datasets of varying quality and architectures, with higher-quality data resulting in lower overall loss and similar benchmark performance; and (3) some models trained with NoPE (No Positional Encoding) showcase unstable learning trajectories, which can be alleviated through minimal RoPE application or QK-Norm which converges to a higher loss. Together, these results offer practical guidance for model designers aiming to balance efficiency and training stability, while emphasizing the previously overlooked importance of partial RoPE.

Related papers

• Disentangling the Expressivity of RoPE [53.85490969529292]
  We formalize accounts for fully uniform, finite-precision soft-attention transformers.<n>We find that, if every rotary component is periodic, RoPE transformers recognize exactly the languages definable in past temporal logic with modular predicates.
  arXiv  Detail & Related papers  (2026-08-12T10:37:21Z)
• Beyond Isolation: Unlocking Reinforcement Learning Component Synergy for Sample-Efficient Continuous Control [59.15149762610843]
  Reinforcement learning systems are significantly more complex than other machine learning paradigms.<n>Despite advances in individual algorithmic components, their functional interdependencies remain underexplored.<n>We propose ROSER, an RL framework that coordinates three critical dimensions: Model-based Representation, Optimization Stability, and Experience Replay.
  arXiv  Detail & Related papers  (2026-08-07T10:38:31Z)
• RoVE: Rotary Value Embeddings Attention for Relative Position-dependent Value Pathways [52.94485753759119]
  Rotary Position Embeddings (RoPE) make attention scores position-relative but leave the value pathway position-blind.<n>We propose RoVE, a parameter-free modification that makes values position-sensitive by rotating them simultaneously with keys, and show that it turns RoPE attention into attentive convolution.
  arXiv  Detail & Related papers  (2026-06-09T09:56:50Z)
• CoPE: Clipped RoPE as A Scalable Free Lunch for Long Context LLMs [18.897130541385646]
  Rotary Positional Embedding (RoPE) is a key component of context scaling in Large Language Models (LLMs)<n>In this work, we unify these seemingly distinct objectives through a minimalist intervention, namely soft clipping lowfrequency components of RoPE.<n>CoPE not only eliminates OOD outliers and refines semantic signals, but also prevents spectral leakage caused by hard clipping.
  arXiv  Detail & Related papers  (2026-02-05T03:31:14Z)
• Beyond Real: Imaginary Extension of Rotary Position Embeddings for Long-Context LLMs [72.8830548005884]
  Rotary Position Embeddings (RoPE) have become a standard for encoding sequence order in Large Language Models.<n>Standard implementations utilize only the real component of the complex-valued dot product for attention score calculation.<n>We propose an extension that re-incorporates this imaginary component.
  arXiv  Detail & Related papers  (2025-12-08T12:59:54Z)
• RoSA: Enhancing Parameter-Efficient Fine-Tuning via RoPE-aware Selective Adaptation in Large Language Models [23.726452130486496]
  Fine-tuning large language models is essential for task-specific adaptation, yet it remains computationally prohibitive.<n>We propose RoPE-aware Selective Adaptation (RoSA), a novel PEFT framework that allocates trainable parameters in a more targeted and effective manner.<n>RoSA comprises a RoPE-aware Attention Enhancement (RoAE) module, and a Dynamic Layer Selection (DLS) strategy that adaptively identifies and updates the most critical layers based on LayerNorm norms.
  arXiv  Detail & Related papers  (2025-11-21T09:55:01Z)
• A Circular Argument : Does RoPE need to be Equivariant for Vision? [45.33536249657655]
  We mathematically show RoPE to be one of the most general solutions for equivariant positional embedding in one-dimensional data.<n>We propose Spherical RoPE, a method analogous to Mixed RoPE, but assumes non-commutative generators.
  arXiv  Detail & Related papers  (2025-11-11T15:47:54Z)
• Context-aware Rotary Position Embedding [0.0]
  Rotary Positional Embeddings (RoPE) have become a widely adopted solution due to their compatibility with relative position encoding and computational efficiency.<n>We propose CARoPE (Context-Aware Rotary Positional Embedding), a novel generalization of RoPE that dynamically generates head-specific frequency patterns conditioned on token embeddings.<n>CaroPE consistently outperforms RoPE and other common positional encoding baselines, achieving significantly lower perplexity, even at longer context lengths.
  arXiv  Detail & Related papers  (2025-07-30T20:32:19Z)
• ComRoPE: Scalable and Robust Rotary Position Embedding Parameterized by Trainable Commuting Angle Matrices [25.99231204405503]
  We propose ComRoPE, which generalizes Rotary Positional PE (RoPE) by defining it in terms of trainable commuting angle matrices.<n>We present two types of trainable commuting angle matrices as sufficient solutions to the RoPE equation.<n>Our framework shows versatility in generalizing to existing RoPE formulations and offering new insights for future positional encoding research.
  arXiv  Detail & Related papers  (2025-06-04T09:10:02Z)
• Rotary Position Embedding for Vision Transformer [44.27871591624888]
  This study provides a comprehensive analysis of Rotary Position Embedding (RoPE) when applied to Vision Transformer (ViT) RoPE demonstrates impressive extrapolation performance, i.e., maintaining precision while increasing image resolution at inference. It eventually leads to performance improvement for ImageNet-1k, COCO detection, and ADE-20k segmentation.
  arXiv  Detail & Related papers  (2024-03-20T04:47:13Z)
• Enhanced Principal Component Analysis under A Collaborative-Robust Framework [89.28334359066258]
  We introduce a general collaborative-robust weight learning framework that combines weight learning and robust loss in a non-trivial way. Under the proposed framework, only a part of well-fitting samples are activated which indicates more importance during training, and others, whose errors are large, will not be ignored. In particular, the negative effects of inactivated samples are alleviated by the robust loss function.
  arXiv  Detail & Related papers  (2021-03-22T15:17:37Z)
• ROME: Robustifying Memory-Efficient NAS via Topology Disentanglement and Gradient Accumulation [106.04777600352743]
  Differentiable architecture search (DARTS) is largely hindered by its substantial memory cost since the entire supernet resides in the memory. The single-path DARTS comes in, which only chooses a single-path submodel at each step. While being memory-friendly, it also comes with low computational costs. We propose a new algorithm called RObustifying Memory-Efficient NAS (ROME) to give a cure.
  arXiv  Detail & Related papers  (2020-11-23T06:34:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.