# Cross-attention for State-based model RWKV-7

arXiv: https://arxiv.org/abs/2504.14260 · HTML: https://mlsanity.com/paper/2504.14260/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 19 references that are in the map.
- First posted on arXiv 19 Apr 2025.

## Builds on (most cited first, 8 of 8)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Perceiver: General Perception with Iterative Attention](https://mlsanity.com/paper/2103.03206/) (2021)
- [Perceiver IO: A General Architecture for Structured Inputs & Outputs](https://mlsanity.com/paper/2107.14795/) (2021)
- [Gate-Variants of Gated Recurrent Unit (GRU) Neural Networks](https://mlsanity.com/paper/1701.05923/) (2017)
- [RWKV-7 "Goose" with Expressive Dynamic State Evolution](https://mlsanity.com/paper/2503.14456/) (2025)
- [Cross-attention Inspired Selective State Space Models for Target Sound Extraction](https://mlsanity.com/paper/2409.04803/) (2024)

## Abstract (arXiv)

We introduce CrossWKV, a novel cross-attention mechanism for the state-based RWKV-7 model, designed to enhance the expressive power of text-to-image generation. Leveraging RWKV-7's linear-complexity Weighted Key-Value (WKV) architecture, CrossWKV integrates text and image modalities in a single pass, utilizing a generalized delta rule with vector-valued gating and low-rank adaptations (LoRA) to achieve superior cross-modal alignment. Unlike Transformer-based models, CrossWKV's non-diagonal, input-dependent transition matrix enables it to represent complex functions beyond the TC0 complexity class, including all regular languages, as demonstrated by its ability to perform state-tracking tasks like S5 permutation modeling. Evaluated within the Diffusion in RWKV-7 (DIR-7) on datasets such as LAION-5B and ImageNet, CrossWKV achieves a Frechet Inception Distance (FID) of 2.88 and a CLIP score of 0.33 on ImageNet 256x256, matching state-of-the-art performance while offering robust generalization across diverse prompts. The model's enhanced expressivity, combined with constant memory usage and linear scaling, positions it as a powerful solution for advanced cross-modal tasks, with potential applications in high-resolution generation and dynamic state manipulation.Code at https://github.com/TorchRWKV/flash-linear-attention