En-Jui Kuo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
En-Jui Kuo has a total of 51 co-authors. Here are the top co-authors by number of shared publications:
- Chi-Sheng Chen
Graduate Institute of Biomedical Electronics and Bioinformatics, National Taiwan University, No. 1, Sec. 4, Roosevelt Road, Taipei 10617
4 shared publications - Chon-Fai Kam
Università degli Studi di Palermo
4 shared publications - Min-Hsiu Hsieh
Foxconn Research Taipei Taiwan
3 shared publications - Jian-Feng Cai
Hong Kong University of Science and Technology
2 shared publications - Ming-Chien Hsu
Hon Hai Quantum Computing Research Center
2 shared publications Pei-Che Hsu
Department of Electrical and Computer Engineering, National Yang Ming Chiao Tung University, Hsinchu, Taiwan
2 shared publications
Latest Publications
- Open Access
- 1 October 2026
- Published by IOP Publishing in New Journal of Physics
- Vol. 28 (10) , 104513
Self-testing of logical subspaces of quantum error-correcting codes
We develop explicit device-independent self-testing constructions for logical subspaces of quantum error-correcting codes. By constructing multipartite Bell inequalities tailored to stabilizer code structures, we show that maximal quantum violations uniquely certify that the underlying shared state resides within the logical subspace of a given code, up to local isometries. These constructions extend earlier stabilizer-subspace self-testing results beyond the five-qubit code to several representative stabilizer codes, including the six-qubit code, the Steane code, and Shor’s nine-qubit code. The tilted sum-of-squares variants further impose algebraic constraints on the relative weights of the logical sectors. Together, these results provide explicit examples of device-independent self-testing for representative stabilizer-code logical subspaces and suggest possible directions for verification and benchmarking of encoded quantum information.
- 1 October 2026
- Published by IOP Publishing in New Journal of Physics
- Vol. 28 (10) , 104513
Open AccessSelf-testing of logical subspaces of quantum error-correcting codes
We develop explicit device-independent self-testing constructions for logical subspaces of quantum error-correcting codes. By constructing multipartite Bell inequalities tailored to stabilizer code structures, we show that maximal quantum violations uniquely certify that the underlying shared state resides within the logical subspace of a given code, up to local isometries. These constructions extend earlier stabilizer-subspace self-testing results beyond the five-qubit code to several representative stabilizer codes, including the six-qubit code, the Steane code, and Shor’s nine-qubit code. The tilted sum-of-squares variants further impose algebraic constraints on the relative weights of the logical sectors. Together, these results provide explicit examples of device-independent self-testing for representative stabilizer-code logical subspaces and suggest possible directions for verification and benchmarking of encoded quantum information.
- Open Access
- 29 July 2026
- Published by IOP Publishing in Quantum Science and Technology
- Vol. 11 (3) , 035051
Quantum Adaptive Self-Attention for quantum Transformer models
A recurring weakness in quantum machine learning (QML) is that reported ‘quantum advantages’ are seldom tested against a capacity-matched classical control, leaving it unclear whether a gain comes from the quantum substrate or from the architectural change that accompanies it. Our primary contribution is methodological: a protocol for attributing such gains honestly—a capacity-matched classical bottleneck of identical parameter budget, transparent reporting of where quantum does not help, and validation on real quantum hardware—which we develop and apply through a concrete case study. That case study is Quantum Adaptive Self-Attention (QASA), a hybrid Transformer that replaces the value projection of a single encoder layer with a 36-parameter parameterized quantum circuit (PQC), keeping all other layers classical. Across nine synthetic benchmarks and the real-world ETTh1 dataset, QASA improves on a full-capacity classical Transformer for chaotic and trend-dominated signals. To ask whether this is a genuinely quantum effect, we introduce a control rarely applied in QML—a capacity-matched classical bottleneck with the same parameter budget—and find that it matches the PQC on the error metrics. The gain is therefore attributable to the low-rank value-projection bottleneck (an architectural parsimony principle), not to quantumness; adding further quantum layers only degrades performance and trainability. We accordingly position the quantum layer not as a source of accuracy advantage but as a competitive instantiation of this principle: its low-rank compression onto the signal’s intrinsic dimensionality is matched by a classical bottleneck, so the gain is architectural rather than quantum. The quantum layer’s distinguishing features are physical—a high circuit entanglement (Meyer–Wallach Q = 0.981 with only 27 CNOTs, which we report as a circuit-level property) and, most concretely, noisy intermediate-scale quantum deployability, which we verify by executing the trained model on a real IBM Quantum processor (one-step prediction within 7.5 % of noiseless simulation on the quantum-favored task and 25 % , with overlapping error bars, on a classical-favored control; no error mitigation). Relative to other quantum sequence models (quantum long short-term memory (QLSTM), QnnFormer), QASA is moreover the most resource-efficient of the three: it reaches competitive accuracy with the fewest quantum parameters (36 vs 90–128) and the strongest entanglement-per-gate ( Q = 0.981 with 27 CNOTs vs QLSTM’s 56), and retains trainable gradients that deeper circuits lose. We argue that capacity-matched baselines and honest reporting of where quantum does not help are prerequisites for credible quantum-machine-learning claims.
- 29 July 2026
- Published by IOP Publishing in Quantum Science and Technology
- Vol. 11 (3) , 035051
Open AccessQuantum Adaptive Self-Attention for quantum Transformer models
A recurring weakness in quantum machine learning (QML) is that reported ‘quantum advantages’ are seldom tested against a capacity-matched classical control, leaving it unclear whether a gain comes from the quantum substrate or from the architectural change that accompanies it. Our primary contribution is methodological: a protocol for attributing such gains honestly—a capacity-matched classical bottleneck of identical parameter budget, transparent reporting of where quantum does not help, and validation on real quantum hardware—which we develop and apply through a concrete case study. That case study is Quantum Adaptive Self-Attention (QASA), a hybrid Transformer that replaces the value projection of a single encoder layer with a 36-parameter parameterized quantum circuit (PQC), keeping all other layers classical. Across nine synthetic benchmarks and the real-world ETTh1 dataset, QASA improves on a full-capacity classical Transformer for chaotic and trend-dominated signals. To ask whether this is a genuinely quantum effect, we introduce a control rarely applied in QML—a capacity-matched classical bottleneck with the same parameter budget—and find that it matches the PQC on the error metrics. The gain is therefore attributable to the low-rank value-projection bottleneck (an architectural parsimony principle), not to quantumness; adding further quantum layers only degrades performance and trainability. We accordingly position the quantum layer not as a source of accuracy advantage but as a competitive instantiation of this principle: its low-rank compression onto the signal’s intrinsic dimensionality is matched by a classical bottleneck, so the gain is architectural rather than quantum. The quantum layer’s distinguishing features are physical—a high circuit entanglement (Meyer–Wallach Q = 0.981 with only 27 CNOTs, which we report as a circuit-level property) and, most concretely, noisy intermediate-scale quantum deployability, which we verify by executing the trained model on a real IBM Quantum processor (one-step prediction within 7.5 % of noiseless simulation on the quantum-favored task and 25 % , with overlapping error bars, on a classical-favored control; no error mitigation). Relative to other quantum sequence models (quantum long short-term memory (QLSTM), QnnFormer), QASA is moreover the most resource-efficient of the three: it reaches competitive accuracy with the fewest quantum parameters (36 vs 90–128) and the strongest entanglement-per-gate ( Q = 0.981 with 27 CNOTs vs QLSTM’s 56), and retains trainable gradients that deeper circuits lose. We argue that capacity-matched baselines and honest reporting of where quantum does not help are prerequisites for credible quantum-machine-learning claims.
- Open Access
- 1 July 2026
- Published by IOP Publishing in Journal of Cosmology and Astroparticle Physics
- Vol. 2026 (07)
Accretion-driven squeezing of fuzzy dark matter halo cores in the Schrödinger-Newton framework
We investigate the impact of accretion onto supermassive black holes on the density profiles of a fuzzy dark matter soliton core at the center of a dark matter halo. Treating the supermassive black hole at the galactic center as a point mass, we numerically solve the Schrödinger-Newton equation for the scalar field. We find that the time-dependent perturbation induces a pronounced squeezing of the soliton profile, simultaneously shrinking the core size and increasing the central density. These results clarify how black hole growth can reshape fuzzy-dark-matter structures and may help reconcile tensions in observed galactic core properties.
- 1 July 2026
- Published by IOP Publishing in Journal of Cosmology and Astroparticle Physics
- Vol. 2026 (07)
Open AccessAccretion-driven squeezing of fuzzy dark matter halo cores in the Schrödinger-Newton framework
We investigate the impact of accretion onto supermassive black holes on the density profiles of a fuzzy dark matter soliton core at the center of a dark matter halo. Treating the supermassive black hole at the galactic center as a point mass, we numerically solve the Schrödinger-Newton equation for the scalar field. We find that the time-dependent perturbation induces a pronounced squeezing of the soliton profile, simultaneously shrinking the core size and increasing the central density. These results clarify how black hole growth can reshape fuzzy-dark-matter structures and may help reconcile tensions in observed galactic core properties.
- Open Access
- 17 April 2026
- Published by Springer Nature in npj Quantum Information
- Vol. 12 (1)
Beyond boson sampling: higher spin sampling as a practical path to quantum supremacy
Since the dawn of quantum computation science, a range of quantum algorithms have been proposed, yet few have experimentally demonstrated a definitive quantum advantage. Shor’s algorithm, while renowned, has not been realized at a scale to outperform classical methods. In contrast, Fock-state boson sampling has been theoretically established, under standard complexity-theoretic assumptions, as a promising route toward quantum computational advantage. However, most existing experimental realizations of boson sampling to date have been based on Gaussian boson sampling, in which the input states consist of squeezed states of light. In this work, we introduce a higher-spin ( S ) sampling framework and show that it provides a practical path toward quantum computational advantage. We derive a quasi-linear scaling relation between the number of sites m and the number of spins n , namely m ~ n 1+ ϵ , where ϵ = 3/(2 S ) decreases with increasing spin quantum number. This suggests that, within a spin system, Fock-state boson sampling can be implemented in a quasi-linear mode regime ( m = Ω ( n 1+ ϵ )), significantly reducing experimental resource requirements.
- 17 April 2026
- Published by Springer Nature in npj Quantum Information
- Vol. 12 (1)
Open AccessBeyond boson sampling: higher spin sampling as a practical path to quantum supremacy
Since the dawn of quantum computation science, a range of quantum algorithms have been proposed, yet few have experimentally demonstrated a definitive quantum advantage. Shor’s algorithm, while renowned, has not been realized at a scale to outperform classical methods. In contrast, Fock-state boson sampling has been theoretically established, under standard complexity-theoretic assumptions, as a promising route toward quantum computational advantage. However, most existing experimental realizations of boson sampling to date have been based on Gaussian boson sampling, in which the input states consist of squeezed states of light. In this work, we introduce a higher-spin ( S ) sampling framework and show that it provides a practical path toward quantum computational advantage. We derive a quasi-linear scaling relation between the number of sites m and the number of spins n , namely m ~ n 1+ ϵ , where ϵ = 3/(2 S ) decreases with increasing spin quantum number. This suggests that, within a spin system, Fock-state boson sampling can be implemented in a quasi-linear mode regime ( m = Ω ( n 1+ ϵ )), significantly reducing experimental resource requirements.
- Open Access
- 13 April 2026
- Published by Springer Nature in Quantum Information Processing
- Vol. 25 (5) , 141
Quantum algorithms for Gowers norm estimation, polynomial testing, and arithmetic progression counting over finite abelian groups
We propose a family of quantum algorithms for estimating Gowers uniformity norms $$ U^k $$ over finite abelian groups, extending earlier quantum methods for the $$ U^2 $$ -norm to arbitrary prime fields and higher-order uniformity norms. Our algorithms prepare quantum states encoding higher-order finite differences and apply Fourier sampling together with amplitude estimation to obtain estimates of Gowers norms. As a central application, we study algebraic property testing problems of distinguishing whether a bounded function $$ f: \mathbb {F}_p^n \rightarrow \mathbb {C} $$ is a low-degree phase polynomial or is far from any such structure. We show that whenever an inverse theorem for the $$ U^{d+1} $$ -norm is available, our quantum framework yields a corresponding structure-testing algorithm whose query and measurement complexity depends explicitly on the quantitative bounds of that inverse theorem. In particular, using the recent quasipolynomial inverse theorem for the $$ U^4 $$ -norm over $$ \mathbb {F}_p^n $$ , we obtain quasipolynomial-time quantum algorithms for detecting cubic phase polynomials. For higher-order norms such as $$ U^5 $$ and $$ U^6 $$ over $$ \mathbb {F}_2^n $$ , the best known inverse theorems provide only tower-type quantitative bounds; accordingly, our detection algorithms remain correct but inherit complexity corresponding to tower-type quantitative bounds. We also present a quantum method for estimating the number of 3-term arithmetic progressions in Boolean functions via the $$ U^2 $$ -norm. Although not query-optimal compared to Grover-style counting, this approach is sensitive to additive structure and naturally aligned with tools from higher-order Fourier analysis. Finally, we observe that Gowers norms are invariant under certain classes of shift-type noise, implying that our algorithms retain robustness under natural quantum noise models. This suggests that Gowers norm-based quantum procedures may serve as stable primitives for quantum property testing, learning theory, and the analysis of pseudorandomness in the NISQ regime.- 13 April 2026
- Published by Springer Nature in Quantum Information Processing
- Vol. 25 (5) , 141
Open AccessQuantum algorithms for Gowers norm estimation, polynomial testing, and arithmetic progression counting over finite abelian groups
We propose a family of quantum algorithms for estimating Gowers uniformity norms $$ U^k $$ over finite abelian groups, extending earlier quantum methods for the $$ U^2 $$ -norm to arbitrary prime fields and higher-order uniformity norms. Our algorithms prepare quantum states encoding higher-order finite differences and apply Fourier sampling together with amplitude estimation to obtain estimates of Gowers norms. As a central application, we study algebraic property testing problems of distinguishing whether a bounded function $$ f: \mathbb {F}_p^n \rightarrow \mathbb {C} $$ is a low-degree phase polynomial or is far from any such structure. We show that whenever an inverse theorem for the $$ U^{d+1} $$ -norm is available, our quantum framework yields a corresponding structure-testing algorithm whose query and measurement complexity depends explicitly on the quantitative bounds of that inverse theorem. In particular, using the recent quasipolynomial inverse theorem for the $$ U^4 $$ -norm over $$ \mathbb {F}_p^n $$ , we obtain quasipolynomial-time quantum algorithms for detecting cubic phase polynomials. For higher-order norms such as $$ U^5 $$ and $$ U^6 $$ over $$ \mathbb {F}_2^n $$ , the best known inverse theorems provide only tower-type quantitative bounds; accordingly, our detection algorithms remain correct but inherit complexity corresponding to tower-type quantitative bounds. We also present a quantum method for estimating the number of 3-term arithmetic progressions in Boolean functions via the $$ U^2 $$ -norm. Although not query-optimal compared to Grover-style counting, this approach is sensitive to additive structure and naturally aligned with tools from higher-order Fourier analysis. Finally, we observe that Gowers norms are invariant under certain classes of shift-type noise, implying that our algorithms retain robustness under natural quantum noise models. This suggests that Gowers norm-based quantum procedures may serve as stable primitives for quantum property testing, learning theory, and the analysis of pseudorandomness in the NISQ regime. - Open Access
Meta-Learning for GPU-Accelerated Quantum Many-Body Problems
We explore the industrial and scientific applicability of the VQE-LSTM framework by integrating meta-learning with GPU accelerated quantum simulation using NVIDIA's CUDA-Q (CUDAQ) platform. This work demonstrates how an LSTM-FC meta-initialization module can extend the practical reach of the Variational Quantum Eigensolver (VQE) in both chemistry and physics domains. In the chemical regime, the framework predicts ground-state energies of molecular Hamiltonians derived from PySCF, achieving near FCI accuracy while maintaining favorable O(N^2) scaling with molecular size. In the physical counterpart, we applied the same model to quantized Simple Harmonic Motion systems (SHM), successfully reproducing its ground and excited states through VQE and Variational Quantum Deflation (VQD) methods. Benchmark results on NVIDIA GPUs reveal significant speedups over CPU-based implementations, validating CUDAQ's capability to handle large-scale variational workloads efficiently. Overall, this study establishes VQE-LSTM as a viable and scalable approach for GPU accelerated quantum simulation, bridging quantum chemistry and condensed-matter physics through a unified, meta-learned initialization strategy.
Open AccessMeta-Learning for GPU-Accelerated Quantum Many-Body Problems
We explore the industrial and scientific applicability of the VQE-LSTM framework by integrating meta-learning with GPU accelerated quantum simulation using NVIDIA's CUDA-Q (CUDAQ) platform. This work demonstrates how an LSTM-FC meta-initialization module can extend the practical reach of the Variational Quantum Eigensolver (VQE) in both chemistry and physics domains. In the chemical regime, the framework predicts ground-state energies of molecular Hamiltonians derived from PySCF, achieving near FCI accuracy while maintaining favorable O(N^2) scaling with molecular size. In the physical counterpart, we applied the same model to quantized Simple Harmonic Motion systems (SHM), successfully reproducing its ground and excited states through VQE and Variational Quantum Deflation (VQD) methods. Benchmark results on NVIDIA GPUs reveal significant speedups over CPU-based implementations, validating CUDAQ's capability to handle large-scale variational workloads efficiently. Overall, this study establishes VQE-LSTM as a viable and scalable approach for GPU accelerated quantum simulation, bridging quantum chemistry and condensed-matter physics through a unified, meta-learned initialization strategy.
- Open Access
FreqLens: Interpretable Frequency Attribution for Time Series Forecasting
Time series forecasting models often lack interpretability, limiting their adoption in domains requiring explainable predictions. We propose \textsc{FreqLens}, an interpretable forecasting framework that discovers and attributes predictions to learnable frequency components. \textsc{FreqLens} introduces two key innovations: (1) \emph{learnable frequency discovery} -- frequency bases are parameterized via sigmoid mapping and learned from data with diversity regularization, enabling automatic discovery of dominant periodic patterns without domain knowledge; and (2) \emph{axiomatic frequency attribution} -- a theoretically grounded framework that provably satisfies Completeness, Faithfulness, Null-Frequency, and Symmetry axioms, with per-frequency attributions equivalent to Shapley values. On Traffic and Weather datasets, \textsc{FreqLens} achieves competitive or superior performance while discovering physically meaningful frequencies: all 5 independent runs discover the 24-hour daily cycle ($24.6 \pm 0.1$h, 2.5\% error) and 12-hour half-daily cycle ($11.8 \pm 0.1$h, 1.6\% error) on Traffic, and weekly cycles ($10\times$ longer than the input window) on Weather. These results demonstrate genuine frequency-level knowledge discovery with formal theoretical guarantees on attribution quality.
Open AccessFreqLens: Interpretable Frequency Attribution for Time Series Forecasting
Time series forecasting models often lack interpretability, limiting their adoption in domains requiring explainable predictions. We propose \textsc{FreqLens}, an interpretable forecasting framework that discovers and attributes predictions to learnable frequency components. \textsc{FreqLens} introduces two key innovations: (1) \emph{learnable frequency discovery} -- frequency bases are parameterized via sigmoid mapping and learned from data with diversity regularization, enabling automatic discovery of dominant periodic patterns without domain knowledge; and (2) \emph{axiomatic frequency attribution} -- a theoretically grounded framework that provably satisfies Completeness, Faithfulness, Null-Frequency, and Symmetry axioms, with per-frequency attributions equivalent to Shapley values. On Traffic and Weather datasets, \textsc{FreqLens} achieves competitive or superior performance while discovering physically meaningful frequencies: all 5 independent runs discover the 24-hour daily cycle ($24.6 \pm 0.1$h, 2.5\% error) and 12-hour half-daily cycle ($11.8 \pm 0.1$h, 1.6\% error) on Traffic, and weekly cycles ($10\times$ longer than the input window) on Weather. These results demonstrate genuine frequency-level knowledge discovery with formal theoretical guarantees on attribution quality.
- Open Access
- 20 January 2026
- Published by Springer Nature in EPJ Quantum Technology
- Vol. 13 (1)
Quantum-secured device-independent global positioning system
We propose a device-independent quantum GPS protocol that employs multipartite Bell nonlocality to self-test a $[[5,1,3]]$ five-qubit entangled state distributed to four satellites and one ground station, providing robust security against cyberattacks. Leveraging quantum rigidity, the protocol removes reliance on device assumptions, thereby bolstering GPS resilience. In the NISQ era, we compare superconducting (98.4% fidelity, 216 ns gate time) and trapped-ion (99.8% fidelity, 483 μs gate time) platforms for five-qubit code generation, and analyze photonic distribution over 20,200 km with $0.1\text{ dB}/\text{km}$ attenuation, underscoring the necessity of LEO constellations or quantum repeaters for a scalable quantum GPS protocol.- 20 January 2026
- Published by Springer Nature in EPJ Quantum Technology
- Vol. 13 (1)
Open AccessQuantum-secured device-independent global positioning system
We propose a device-independent quantum GPS protocol that employs multipartite Bell nonlocality to self-test a $[[5,1,3]]$ five-qubit entangled state distributed to four satellites and one ground station, providing robust security against cyberattacks. Leveraging quantum rigidity, the protocol removes reliance on device assumptions, thereby bolstering GPS resilience. In the NISQ era, we compare superconducting (98.4% fidelity, 216 ns gate time) and trapped-ion (99.8% fidelity, 483 μs gate time) platforms for five-qubit code generation, and analyze photonic distribution over 20,200 km with $0.1\text{ dB}/\text{km}$ attenuation, underscoring the necessity of LEO constellations or quantum repeaters for a scalable quantum GPS protocol. - Open Access
- 1 December 2025
- Published by IOP Publishing in New Journal of Physics
- Vol. 27 (12) , 124509
Quantum supremacy through Fock state q -boson sampling with transmon qubits
Transmon qubits have traditionally been regarded as limited to random circuit sampling, incapable of performing Fock state boson sampling—a problem known to be classically intractable. This work challenges that assumption by introducing q -boson Fock state sampling, a variant in which transmon qubits can operate effectively. Through direct mapping to the q -boson formalism, we demonstrate that transmons possess the capability to achieve quantum supremacy in q -boson sampling tasks. This finding expands the potential applications of transmon-based quantum processors and paves the way for new avenues in quantum computation.
- 1 December 2025
- Published by IOP Publishing in New Journal of Physics
- Vol. 27 (12) , 124509
Open AccessQuantum supremacy through Fock state q -boson sampling with transmon qubits
Transmon qubits have traditionally been regarded as limited to random circuit sampling, incapable of performing Fock state boson sampling—a problem known to be classically intractable. This work challenges that assumption by introducing q -boson Fock state sampling, a variant in which transmon qubits can operate effectively. Through direct mapping to the q -boson formalism, we demonstrate that transmons possess the capability to achieve quantum supremacy in q -boson sampling tasks. This finding expands the potential applications of transmon-based quantum processors and paves the way for new avenues in quantum computation.
- Open Access
- 4 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 189725-189734
Accelerating Parameter Initialization in Quantum Chemical Simulations via LSTM-FC-VQE
Variational Quantum Eigensolver (VQE) is a leading algorithm for quantum chemistry on near-term devices, but its performance is often limited by inefficient parameter initialization, which leads to slow convergence and high computational overhead. While meta-learning approaches such as LSTM-VQE have been proposed to predict optimization trajectories, their applicability remains restricted by rigid ansatz structures and molecule-specific parameter dimensions. To address these limitations, we propose LSTM-FC-VQE, an enhanced meta-learning framework that combines Long Short-Term Memory (LSTM) networks with a fully connected projection layer. This design enables the model to standardize variable-length parameter inputs, allowing it to handle molecular systems with heterogeneous qubit counts and ansatz architectures more effectively. We validate our approach on benchmark molecules, including H4 and H2O, and demonstrate that LSTM-FC-VQE significantly reduces the number of VQE iterations required for convergence while achieving energy accuracies comparable to full configuration interaction (FCI) results. Beyond accelerating convergence, our method generalizes to unseen molecular configurations with minimal training data, offering a scalable and data-efficient strategy for quantum chemical simulations in the NISQ era.
- 4 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 189725-189734
Open AccessAccelerating Parameter Initialization in Quantum Chemical Simulations via LSTM-FC-VQE
Variational Quantum Eigensolver (VQE) is a leading algorithm for quantum chemistry on near-term devices, but its performance is often limited by inefficient parameter initialization, which leads to slow convergence and high computational overhead. While meta-learning approaches such as LSTM-VQE have been proposed to predict optimization trajectories, their applicability remains restricted by rigid ansatz structures and molecule-specific parameter dimensions. To address these limitations, we propose LSTM-FC-VQE, an enhanced meta-learning framework that combines Long Short-Term Memory (LSTM) networks with a fully connected projection layer. This design enables the model to standardize variable-length parameter inputs, allowing it to handle molecular systems with heterogeneous qubit counts and ansatz architectures more effectively. We validate our approach on benchmark molecules, including H4 and H2O, and demonstrate that LSTM-FC-VQE significantly reduces the number of VQE iterations required for convergence while achieving energy accuracies comparable to full configuration interaction (FCI) results. Beyond accelerating convergence, our method generalizes to unseen molecular configurations with minimal training data, offering a scalable and data-efficient strategy for quantum chemical simulations in the NISQ era.