arXiv subjects

Zhongyi Yang

Publications and source records attributed to Zhongyi Yang.

4 recordsLinked to original sources

arXiv2026

Unitary designs from perturbed time evolutions of a chaotic Hamiltonian

Unitary designs provide efficient substitutes for Haar-random unitaries in quantum information processing, randomized measurements, and many-body quantum dynamics. We propose a protocol based on time evolutions of a single chaotic Hamiltonian with intermediate unitary perturbations to generate unitary designs. We derive the frame potential of the resulting ensemble in terms of those of the intermediate ensemble. The intermediate ensemble need not itself be Haar random or even approximately form a unitary design; it is sufficient that its frame-potential growth remains well suppressed relative to the maximal possible scaling. The nontrivial Pauli set and the Clifford ensemble are simple examples satisfying this criterion, whereas ensembles whose cardinality remains independent of the Hilbert-space dimension generally fail. We further show that, at the level of frame potentials, multi-Hamiltonian temporal protocols can be recursively replaced by one-Hamiltonian protocols interleaved with fixed trace-suppressed perturbations.

quant-ph↗

arXiv2026

STAR: Similarity-guided Teacher-Assisted Refinement for Super-Tiny Function Calling Models

The proliferation of Large Language Models (LLMs) in function calling is pivotal for creating advanced AI agents, yet their large scale hinders widespread adoption, necessitating transferring their capabilities into smaller ones. However, existing paradigms are often plagued by overfitting, training instability, ineffective binary rewards for multi-solution tasks, and the difficulty of synergizing techniques. We introduce STAR: Similarity-guided Teacher-Assisted Refinement, a novel holistic framework that effectively transfers LLMs' capabilities to super-tiny models. STAR consists of two core technical innovations: (1) Constrained Knowledge Distillation (CKD), a training objective that augments top-k forward KL divergence to suppress confidently incorrect predictions, ensuring training stability while preserving exploration capacity for downstream RL. STAR holistically synergizes these strategies within a cohesive training curriculum, enabling super-tiny models to achieve exceptional performance on complex function calling tasks; (2) Similarity-guided RL (Sim-RL), a RL mechanism that introduces a fine-grained, similarity-based reward. This provides a robust, continuous, and rich signal for better policy optimization by evaluating the similarity between generated outputs and the ground truth. Extensive experiments on challenging and renowned benchmarks demonstrate the effectiveness of our method. Our STAR models establish SOTA in their size classes, significantly outperforming baselines. Remarkably, our 0.6B STAR model achieves the best performance among all open models under 1B, surpassing even several well-known open models at a larger scale. STAR demonstrates a training framework that distills capabilities of LLMs into super-tiny models, paving the way for powerful, accessible, and efficient AI agents.

cs.AI↗

arXiv2025

High-Precision Fidelity Estimation with Common Randomized Measurements

Efficient fidelity estimation of multiqubit quantum states is crucial to many applications in quantum information processing. However, to estimate the infidelity $ε$ with multiplicative precision, conventional estimation protocols require (order) $1/ε^2$ different circuits in addition to $1/ε^2$ samples, which is quite resource-intensive for high-precision fidelity estimation. Here we introduce an efficient estimation protocol by virtue of common randomized measurements (CRM) integrated with shadow estimation based on the Clifford group, which only requires $1/ε$ circuits. Moreover, in many scenarios of practical interest, in the presence of depolarizing or Pauli noise for example, our protocol only requires a constant number of circuits, irrespective of the infidelity $ε$ and the qubit number. For large and intermediate quantum systems, quite often one circuit is already sufficient. In the course of study, we clarify the performance of CRM shadow estimation based on the Clifford group and 4-designs and highlight its advantages over standard and thrifty shadow estimation.

quant-ph↗

arXiv2025

From Large to Super-Tiny: End-to-End Optimization for Cost-Efficient LLMs

Large Language Models (LLMs) have significantly advanced artificial intelligence by optimizing traditional Natural Language Processing (NLP) workflows, facilitating their integration into various systems. Many such NLP systems, including ours, directly incorporate LLMs. However, this approach either results in expensive costs or yields suboptimal performance after fine-tuning. In this paper, we introduce a three-stage cost-efficient end-to-end LLM deployment pipeline, comprising prototyping, knowledge transfer, and model compression, to effectively tackle the cost-performance dilemma in LLM-based frameworks. Its high cost-efficiency is manifested not only in simplifying system complexity and producing super-tiny online models with enhanced performance and reduced costs in the results, but also in addressing development cycle constraints, the lack of extensive high-quality data, and limited computational resources during the project development process. In the first stage, we construct an optimal performance prototype system by transforming complex tasks into a function call-based LLM-driven pipeline, which serves as a teacher model to generate high-quality data. In the second stage, we combine techniques like rejection sampling fine-tuning, reinforcement learning, and knowledge distillation to transfer knowledge to 0.5B student models, delivering effective performance at minimal cost. In the final stage, we further compress models to 0.4B via quantization and pruning, achieving ultra-low latency and cost. Extensive experimental results and the framework's modular design suggest cross-domain capabilities and potential applicability in other NLP areas.

cs.CL↗