mlsanityData to 7 Oct 2026

Complex Transformer: A Framework for Modeling Complex-Valued Sequence

arXiv 1910.10202 ↗First posted 22 Oct 2019cs.LG cs.SD eess.AScited by 32

Not on the map. Why?

Abstract (arXiv)

While deep learning has received a surge of interest in a variety of fields in recent years, major deep learning models barely use complex numbers. However, speech, signal and audio data are naturally complex-valued after Fourier Transform, and studies have shown a potentially richer representation of complex nets. In this paper, we propose a Complex Transformer, which incorporates the transformer model as a backbone for sequence modeling; we also develop attention and encoder-decoder network operating for complex input. The model achieves state-of-the-art performance on the MusicNet dataset and an In-phase Quadrature (IQ) signal dataset.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 1; 2023: 7; 2024: 9; 2025: 7; 2026: 5.

32 papers.

Sort:

By area:

  1. 2023Building Blocks for a Complex-Valued Transformer Architecturecited by 16
  2. 2025iFairy: the First 2-bit Complex LLM with All Parameters in ±1, ± icited by 5
  3. 2024Expanding Expressivity in Transformer Models with M"obiusAttentioncited by 4
  4. 2021Deep Sound Field Reconstruction in Real Rooms: Introducing the ISOBEL Sound Field Datasetcited by 3
  5. 2022Adversarial Audio Synthesis with Complex-valued Polynomial Networkscited by 3
  6. 2024CoNO: Complex Neural Operator for Continous Dynamical Physical Systemscited by 3
  7. 2025A Survey of Deep Learning for Complex Speech Spectrogramscited by 3
  8. 2021A Two-stage Complex Network using Cycle-consistent Generative Adversarial Networks for Speech Enhancementcited by 2
  9. 2023Adapting Pre-trained Language Models for Quantum Natural Language Processingcited by 2
  10. 2023Self-supervised Adaptive Pre-training of Multilingual Speech Models for Language and Dialect Identificationcited by 2
  11. 2025BeatFormer: Efficient motion-robust remote heart rate estimation through unsupervised spectral zoomed attention filterscited by 2
  12. 2025Holographic Transformers for Complex-Valued Signal Processing: Integrating Phase Interference into Self-Attentioncited by 2
20 more
  1. 2025Fairy2i: Training Complex LLMs from Real LLMs with All Parameters in ± 1, ± icited by 2
  2. 2026Fourier Transformers for Latent Crystallographic Diffusion and Generative Modelingcited by 1
  3. 2026The Quantum Shortcut: Complex Phase-State Dynamics Reduce the Optimization Steps of Sequence Modelscited by 1
  4. 2021Signal Transformer: Complex-valued Attention and Meta-Learning for Signal Recognitioncited by 0
  5. 2023Emerging Approaches for THz Array Imaging: A Tutorial Review and Software Toolcited by 0
  6. 2023Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adaptercited by 0
  7. 2023GMTR: Graph Matching Transformerscited by 0
  8. 2023DarkShot: Lighting Dark Images with Low-Compute and High-Qualitycited by 0
  9. 2024TRLS: A Time Series Representation Learning Framework via Spectrogram for Medical Signal Processingcited by 0
  10. 2024TEN-GUARD: Tensor Decomposition for Backdoor Attack Detection in Deep Neural Networkscited by 0
  11. 2024DeepCSHAP: Utilizing Shapley Values to Explain Deep Complex-Valued Neural Networkscited by 0
  12. 2024T-Pixel2Mesh: Combining Global and Local Transformer for 3D Mesh Generation from a Single Imagecited by 0
  13. 2024Strategic Arms with Side Communication Prevail Over Low-Regret MAB Algorithmscited by 0
  14. 2024Towards General Deepfake Detection with Dynamic Curriculumcited by 0
  15. 2024Attr-Int: A Simple and Effective Entity Alignment Framework for Heterogeneous Knowledge Graphscited by 0
  16. 2025Mask6D: Masked Pose Priors For 6D Object Pose Estimationcited by 0
  17. 2025Unfolding Framework with Complex-Valued Deformable Attention for High-Quality Computer-Generated Hologram Generationcited by 0
  18. 2026Scaled Dot-Product Attention implements projection of inputs onto a common surfacecited by 0
  19. 2026Perturbing the Phase: Analyzing Adversarial Robustness of Complex-Valued Neural Networkscited by 0
  20. 2026IQ-JEPA: A Joint-Embedding Predictive Architecture with a Hermitian Vision Transformer for Sound Speed and Attenuation Estimation from Ultrasound IQ Datacited by 0