QT is introduced, a Quantum-inspired Transformer for vision tasks with three components: angle-inspired encoding that maps image tokens to learned trigonometric Hilbert-space features analogous to quantum rotation-based state encoding; self-attention over these periodic features, inducing a classical cosine kernel approximated to quantum fidelity kernels; and gated multiplicative emulation, a trainable classical surrogate for interaction terms found in variational circuits.
Abstract
Quantum machine learning offers a compelling representational perspective: angle-encoded states inhabit Hilbert spaces in which periodic similarities and interactions can be expressed naturally. Realizing this perspective for visual recognition remains difficult, however, because present quantum neural networks are constrained by limited qubit counts, costly circuit simulation and measurement, noise, and unstable optimization on noisy intermediate-scale quantum devices. We investigate whether useful structural ideas from quantum models can instead be realized as scalable classical Transformer operations. We introduce QiT, a Quantum-inspired Transformer for vision tasks with three components: (i) angle-inspired encoding that maps image tokens to learned trigonometric Hilbert-space features analogous to quantum rotation-based state encoding; (ii) self-attention over these periodic features, inducing a classical cosine kernel approximated to quantum fidelity kernels; and (iii) gated multiplicative emulation, a trainable classical surrogate for interaction terms found in variational circuits. All components are differentiable tensor operations, so QiT claims neither quantum computation nor quantum speedup and retains the $\mathcal{O}(N^2D)$ attention complexity of a standard Vision Transformer. Across image-classification benchmarks, QiT is competitive with a matched classical Transformer while avoiding the severe runtime cost observed for a small simulated quantum Transformer. QiT-B reaches 78.3\% ImageNet-1K top-1 accuracy with 45.7M parameters and 11.5 GFLOPs. These results position QiT as a scalable baseline for isolating and evaluating quantum-motivated inductive biases in visual recognition.
These proof-of-concept results, obtained on small synthetic tasks, suggest that the physics of quantum computation can provide intrinsic interpretability signals with no direct classical counterpart, motivating study of whether this advantage persists at scale.
Together, these results delineate a practical operating regime for high-dimensional local quantum learning and show that receptive-field scaling can be managed through a coordinated choice of upload granularity, entangling structure, information retention, and execution depth.
Wen-Bin Yu, Yan-Feng Fan, You-Le Wang et al.· Machine Learning: Science an...· 0 citations
It is shown that a transition-probability-only learning interface can possess exact continuous blind directions in certain quantum-state families, and multistate relational observables are established as measurable, trainable, and physically consequential signals for quantum representation learning beyond pairwise fide...
This work introduces discretization-aware fine-tuning (DAFT), a method that adapts a pre-trained chemical foundation model to produce representations that remain informative after quantization, and evaluates both quantum and classical models under a controlled setting in which they receive identical discretized bit-str...
Results indicate that high performance in the proposed object detection model does not require maximal entanglement and efficient learning can emerge through topology controlled information flow, targeted restriction of entanglement, and information renormalization within the Hilbert space.
Mohammad Bahrami, M. Rafiee, Mohsen Norouzi· 0 citations
Quantum MeanFlow (QMF), the quantum analogue of the MeanFlow formulation, is established as a viable method for single-step quantum generative sampling, saving on quantum circuit evaluations per generated sample.
Ashish Joshi, Eshaan Mistry, T. Koyama· 0 citations
Known for his clear and elegant writing style, Bertsekas shaped fields from control and optimization to large-scale computation and artificial intelligence.