mlsanityData to 7 Oct 2026

VisualRWKV: Exploring Recurrent Neural Networks for Visual Language Models

arXiv 2406.13362 ↗First posted 19 Jun 2024cs.CV cs.CL cs.LGcited by 10

On the map: Multimodal LLMs / vision-language models → MLLM training and visual instruction tuning

Abstract (arXiv)

Visual Language Models (VLMs) have rapidly progressed with the recent success of large language models. However, there have been few attempts to incorporate efficient linear Recurrent Neural Networks (RNNs) architectures into VLMs. In this study, we introduce VisualRWKV, the first application of a linear RNN model to multimodal learning tasks, leveraging the pre-trained RWKV language model. We propose a data-dependent recurrence and sandwich prompts to enhance our modeling capabilities, along with a 2D image scanning mechanism to enrich the processing of visual sequences. Extensive experiments demonstrate that VisualRWKV achieves competitive performance compared to Transformer-based models like LLaVA-1.5 on various benchmarks. Compared to LLaVA-1.5, VisualRWKV has a speed advantage of 3.98 times and can save 54% of GPU memory when reaching an inference length of 24K tokens. To facilitate further research and analysis, we have made the checkpoints and the associated code publicly accessible at the following GitHub repository: see https://github.com/howard-hou/VisualRWKV.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 29 of its 46 references that are in the map. First posted on arXiv 19 Jun 2024.

Builds on

29 of 46 references.

Closest ancestors · 7

Same direction, newest first

  1. 2024VL-Mamba: Exploring State Space Models for Multimodal Learning20 Mar
  2. 2023Improved Baselines with Visual Instruction Tuning5 Oct
  3. 2023MMBench: Is Your Multi-modal Model an All-around Player?12 Jul
  4. 2023Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic27 Jun
  5. 2023MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models23 Jun
  6. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning11 May
  7. 2023Otter: A Multi-Modal Model with In-Context Instruction Tuning5 May

Other references · 22

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  5. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  6. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  7. 2016Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answeringcited by 2,498
  8. 2020Transformers are RNNs: Fast Autoregressive Transformers with Linear Attentioncited by 1,979
  9. 2022Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answeringcited by 1,881
  10. 2019Towards VQA Models That Can Readcited by 1,696
  11. 2023LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Daycited by 1,287
  12. 2019OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledgecited by 1,114
10 more
  1. 2023Kosmos-2: Grounding Multimodal Large Language Models to the Worldcited by 1,075
  2. 2023mPLUG-Owl: Modularization Empowers Large Language Models with Multimodalitycited by 1,038
  3. 2023RWKV: Reinventing RNNs for the Transformer Eracited by 814
  4. 2024Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Modelscited by 336
  5. 2020XCOPA: A Multilingual Dataset for Causal Commonsense Reasoningcited by 330
  6. 2024Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrencecited by 155
  7. 2024LLaVA-Phi: Efficient Multi-Modal Assistant with Small Language Modelcited by 128
  8. 2023MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devicescited by 120
  9. 2021It's All in the Heads: Using Attention Heads as a Baseline for Cross-Lingual Transfer in Commonsense Reasoningcited by 69
  10. 2024RWKV-TS: Beyond Traditional Recurrent Neural Network for Time Series Taskscited by 22

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 6; 2026: 1.

10 papers.

  1. 2025Multimodal Mamba: Decoder-only Multimodal State Space Model via Quadratic to Linear Distillationcited by 11
  2. 2025AuroraLong: Bringing RNNs Back to Efficient Open-Ended Video Understandingcited by 9
  3. 2025InfiniteVL: Synergizing Linear and Sparse Attention for Highly-Efficient, Unlimited-Input Vision-Language Modelscited by 9
  4. 2024A Review of Human Emotion Synthesis Based on Generative Technologycited by 7
  5. 2024A Survey of RWKVcited by 5
  6. 2024VisualRWKV-HD and UHD: Advancing High-Resolution Processing for Visual Language Modelscited by 1
  7. 2025Exploring Linear Attention Alternative for Single Image Super-Resolutioncited by 0
  8. 2025RWKV-UI: UI Understanding with Enhanced Perception and Reasoningcited by 0
  9. 2025Exploring Diffusion with Test-Time Training on Efficient Image Restorationcited by 0
  10. 2026LinMU: Multimodal Understanding Made Linearcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025VARGPT: Unified Understanding and Generation in a Visual Autoregressive Multimodal Large Language Model
  2. 2024Efficient Vision-Language Models by Summarizing Visual Tokens into Compact Registers
  3. 2023InfMLLM: A Unified Framework for Visual-Language Tasks
  4. 2025Towards General Continuous Memory for Vision-Language Models
  5. 2024Exploring the Frontier of Vision-Language Models: A Survey of Current Methodologies and Future Directions
  6. 2024The Revolution of Multimodal Large Language Models: A Survey
  7. 2025Visual Large Language Models for Generalized and Specialized Applications
  8. 2024EVLM: An Efficient Vision-Language Model for Visual Understanding