arXiv subjects

Xiao Xiao

Publications and source records attributed to Xiao Xiao.

At least 37 records · Page 2Linked to original sources

arXiv2026

Evaluating Developmental Cognition Capabilities of LLMs

Conversational AI is increasingly personalized around users' preferences, histories, goals, and knowledge, but much less around how users interpret and take up model outputs to construct and understand their reality. We draw on Robert Kegan's constructive-developmental theory as a complementary lens on this dimension. Existing methods for assessing developmental stage in the Keganian tradition rely either on expert interviews that do not scale or on sentence-completion instruments that are proprietary, lengthy, or invasive. To make this perspective tractable for LLM evaluation, we introduce the Developmental Sentence Completion Test (DSCT), a 20-item instrument designed to elicit developmental signal in self-administered text. Throughout, we treat the resulting labels as characterizations of stage-like structure in elicited responses, not as validated person-level developmental stage. We then ask how much of that signal can be recovered by LLMs across three elicited response regimes: simulated personas, real human respondents, and default model-generated answers. On simulated personas, top frontier models recover simulator-intended labels with high accuracy. On real human DSCT responses, human-LLM agreement is fair, with much stronger within-neighborhood than exact agreement. Finally, when LLMs answer DSCT prompts without persona-conditioning, their responses exhibit stable stage-like differences across model families, with larger and newer models tending to generate higher-rated text. These results suggest that stage-conditioned signal is cleaner in synthetic responses than in human-written DSCT text, and that the core constraint for stage-aware conversational AI is not classifier accuracy alone, but the availability of developmental signal from elicited text.

cs.AI↗

arXiv2026

Trace estimates and improved pointwise bounds for joint eigenfunctions

For $L^2$-normalized joint eigenfunctions in a quantum integrable system, [GT20] gave polynomial improvements over the standard Hömander bounds for typical points. In this paper, we improve their result by establishing a sharp bound of $h^{\frac{-n+k+1}2}$ for the points satisfying a rank $k$ non-degeneracy condition.

math.AP↗

arXiv2026

Topology-Aware Block Coordinate Descent for Qubit Frequency Allocation of Superconducting Quantum Processors

Pre-execution calibration is a major bottleneck for operating superconducting quantum processors, and qubit frequency allocation is especially challenging due to crosstalk-coupled objectives. We establish that the widely-used Snake optimizer is mathematically equivalent to Block Coordinate Descent (BCD), providing a rigorous theoretical foundation for this strategy for qubit frequency allocation. Building on this formalization, we present a topology-aware block ordering obtained by casting order selection as a Sequence-Dependent Traveling Salesman Problem (SD-TSP) and solving it efficiently with a nearest-neighbor heuristic. The SD-TSP cost reflects how a given block choice expands the reduced-circuit footprint required to evaluate the block-local objective, enabling orders that minimize per-epoch evaluation time. Under local crosstalk/bounded-degree assumptions, the method achieves linear complexity in qubit count per epoch, while maintaining comparable optimization performance. We formalize the calibration objective, clarify when reduced experiments are equivalent or approximate to the full objective, and analyze convergence of the resulting inexact BCD with noisy measurements. Simulations based on a physics-motivated error simulator show that the proposed BCD-NNA ordering attains the same optimization accuracy at markedly lower runtime than graph-based heuristics (BFS, DFS) and random orders, while also achieving optimization quality comparable to a genetic-algorithm baseline. This method is robust to noisy objective-function evaluations and tolerant to moderate non-local crosstalk mismatch. These results provide a scalable, implementation-ready workflow for frequency calibration in near-term superconducting processors and, more broadly, for locality-structured calibration tasks in future scalable architectures.

quant-ph↗

arXiv2026

In-situ benchmarking of fault-tolerant quantum circuits. I. Clifford circuits

Benchmarking physical devices and verifying logical algorithms are important tasks for scalable fault-tolerant quantum computing. Numerous protocols exist for benchmarking devices before running actual algorithms. In this work, we show that both physical and logical errors of fault-tolerant circuits can even be characterized in-situ using syndrome data. To achieve this, we map general fault-tolerant Clifford circuits to subsystem codes using the spacetime code formalism and develop a scheme for estimating Pauli noise in Clifford circuits using syndrome data. We give necessary and sufficient conditions for the learnability of physical and logical noise from given syndrome data, and show that we can accurately predict logical fidelities from the same data. Importantly, our approach requires only a polynomial sample size, even when the logical error rate is exponentially suppressed by the code distance, and thus gives an exponential advantage against methods that use only logical data such as direct fidelity estimation. We demonstrate the practical applicability of our methods in various scenarios using synthetic data as well as the experimental data from a recent demonstration of fault-tolerant circuits by Bluvstein et al. [Nature 626, 7997 (2024)]. Our methods provide an efficient, in-situ way of characterizing a fault-tolerant quantum computer to help gate calibration, improve decoding accuracy, and verify logical circuits.

quant-ph↗

arXiv2025

Bayesian buckling load optimisation for structures with geometric uncertainties

Optimised lightweight structures, such as shallow domes and slender towers, are prone to sudden buckling failure because geometric uncertainties/imperfections can lead to a drastic reduction in their buckling loads. We introduce a framework for the robust optimisation of buckling loads, considering geometric nonlinearities and random geometric imperfections. The mean and standard deviation of buckling loads are estimated by Monte Carlo sampling of random imperfections and performing a nonlinear finite element computation for each sample. The extended system method is employed to compute the buckling load directly, avoiding costly path-following procedures. Furthermore, the quasi-Monte Carlo sampling using the Sobol sequence is implemented to generate more uniformly distributed samples, which significantly reduces the number of finite element computations. The objective function consisting of the weighted sum of the mean and standard deviation of the buckling load is optimised using Bayesian optimisation. The accuracy and efficiency of the proposed framework are demonstrated through robust sizing optimisation of several geometrically nonlinear truss examples.

math.NA↗

arXiv2025

Transmon qutrit-based simulation of spin-1 AKLT systems

Qutrit-based quantum circuits could help reduce the overall circuit depths, and hence the effect of noise, when the system of interest has a local dimension of three. Accessing second excited states in superconducting transmons provides a straightforward hardware realization of qutrits useful for such ternary encoding. In this work, we successfully calibrate microwave pulse gates to a low error rate to operate transmon qutrits. We use these qutrits to simulate one-dimensional spin-1 AKLT states (Affleck, Kennedy, Lieb, and Tasaki), which exhibit a multitude of interesting phenomena, such as topologically protected ground states, string order, and the existence of a robust Berry phase. We demonstrate the efficacy of qutrit-based simulation by preparing high-fidelity ground states of the AKLT Hamiltonian with open boundaries for various chain lengths. We then use ground state preparations of the perturbed AKLT Hamiltonian with periodic boundaries to calculate the Berry phase and illustrate non-trivial ground state topology. To establish the advantage of qutrits over qubits in the presence of noise, we present scalable methods for preparing the AKLT state and computing its Berry phase using tensor network simulations. Our work provides a pathway toward more general spin-1 physics simulations using transmon qutrits, with applications in chemistry, magnetism, and topological phases of matter.

quant-ph↗

arXiv2025

Unveil A Peculiar Light Curve Pattern of Magnetar Burst with GECAM observations of SGR J1935+2154

Magnetar X-ray Burst (MXB) is usually composed of a single pulse or multiple pulses with rapid rise and brief duration mostly observed in hard X-ray (soft gamma-ray) band. Previous work studied the temporal behavior of some magnetar bursts and employed the Fast Rise Exponential Decay (FRED) model to fit pulses of MXB. However, whether there is other kind of pulse shape has not been explored. In this study, we systematically examined light curve of MXBs from SGR J1935+2154 detected by GECAM between 2021 and 2022. We find that there are different light curve morphologies. Especially, we discover a peculiar and new pattern, Exponential Rise and Cut-Off Decay (ERCOD), which is significantly different from FRED and could be well described by a mathematical function we proposed. We find that MXBs with ERCOD shape are generally longer in duration, brighter in the peak flux, and harder in spectrum. We note that the ERCOD shape is not unique to SGR J1935+2154 but also present in other magnetars. This new light curve pattern may imply a special burst and radiation mechanism of magnetar.

astro-ph.HE↗

arXiv2025

Large Processor Chip Model

Computer System Architecture serves as a crucial bridge between software applications and the underlying hardware, encompassing components like compilers, CPUs, coprocessors, and RTL designs. Its development, from early mainframes to modern domain-specific architectures, has been driven by rising computational demands and advancements in semiconductor technology. However, traditional paradigms in computer system architecture design are confronting significant challenges, including a reliance on manual expertise, fragmented optimization across software and hardware layers, and high costs associated with exploring expansive design spaces. While automated methods leveraging optimization algorithms and machine learning have improved efficiency, they remain constrained by a single-stage focus, limited data availability, and a lack of comprehensive human domain knowledge. The emergence of large language models offers transformative opportunities for the design of computer system architecture. By leveraging the capabilities of LLMs in areas such as code generation, data analysis, and performance modeling, the traditional manual design process can be transitioned to a machine-based automated design approach. To harness this potential, we present the Large Processor Chip Model (LPCM), an LLM-driven framework aimed at achieving end-to-end automated computer architecture design. The LPCM is structured into three levels: Human-Centric; Agent-Orchestrated; and Model-Governed. This paper utilizes 3D Gaussian Splatting as a representative workload and employs the concept of software-hardware collaborative design to examine the implementation of the LPCM at Level 1, demonstrating the effectiveness of the proposed approach. Furthermore, this paper provides an in-depth discussion on the pathway to implementing Level 2 and Level 3 of the LPCM, along with an analysis of the existing challenges.

cs.AR↗

arXiv2025

Confidence in Large Language Model Evaluation: A Bayesian Approach to Limited-Sample Challenges

Large language models (LLMs) exhibit probabilistic output characteristics, yet conventional evaluation frameworks rely on deterministic scalar metrics. This study introduces a Bayesian approach for LLM capability assessment that integrates prior knowledge through probabilistic inference, addressing limitations under limited-sample regimes. By treating model capabilities as latent variables and leveraging a curated query set to induce discriminative responses, we formalize model ranking as a Bayesian hypothesis testing problem over mutually exclusive capability intervals. Experimental evaluations with GPT-series models demonstrate that the proposed method achieves superior discrimination compared to conventional evaluation methods. Results indicate that even with reduced sample sizes, the approach maintains statistical robustness while providing actionable insights, such as probabilistic statements about a model's likelihood of surpassing specific baselines. This work advances LLM evaluation methodologies by bridging Bayesian inference with practical constraints in real-world deployment scenarios.

cs.CL↗

arXiv2025

ITERTL: An Iterative Framework for Fine-tuning LLMs for RTL Code Generation

Recently, large language models (LLMs) have demonstrated excellent performance, inspiring researchers to explore their use in automating register transfer level (RTL) code generation and improving hardware design efficiency. However, the existing approaches to fine-tune LLMs for RTL generation typically are conducted on fixed datasets, which do not fully stimulate the capability of LLMs and require large amounts of reference data, which are costly to acquire. To mitigate these issues, we innovatively introduce an iterative training paradigm named ITERTL. During each iteration, samples are drawn from the model trained in the previous cycle. Then these new samples are employed for training in current loop. Furthermore, we introduce a plug-and-play data filtering strategy, thereby encouraging the model to generate high-quality, self-contained code. Our model outperforms GPT4 and state-of-the-art (SOTA) open-source models, achieving remarkable 53.8% pass@1 rate on VerilogEval-human benchmark. Under similar conditions of data quantity and quality, our approach significantly outperforms the baseline. Extensive experiments validate the effectiveness of the proposed method.

cs.CL↗

arXiv2025

RTLRepoCoder: Repository-Level RTL Code Completion through the Combination of Fine-Tuning and Retrieval Augmentation

As an essential part of modern hardware design, manually writing Register Transfer Level (RTL) code such as Verilog is often labor-intensive. Following the tremendous success of large language models (LLMs), researchers have begun to explore utilizing LLMs for generating RTL code. However, current studies primarily focus on generating simple single modules, which can not meet the demands in real world. In fact, due to challenges in managing long-context RTL code and complex cross-file dependencies, existing solutions cannot handle large-scale Verilog repositories in practical hardware development. As the first endeavor to exclusively adapt LLMs for large-scale RTL development, we propose RTLRepoCoder, a groundbreaking solution that incorporates specific fine-tuning and Retrieval-Augmented Generation (RAG) for repository-level Verilog code completion. Open-source Verilog repositories from the real world, along with an extended context size, are used for domain-specific fine-tuning. The optimized RAG system improves the information density of the input context by retrieving relevant code snippets. Tailored optimizations for RAG are carried out, including the embedding model, the cross-file context splitting strategy, and the chunk size. Our solution achieves state-of-the-art performance on public benchmark, significantly surpassing GPT-4 and advanced domain-specific LLMs on Edit Similarity and Exact Match rate. Comprehensive experiments demonstrate the remarkable effectiveness of our approach and offer insights for future work.

cs.SE↗

arXiv2025

Signatures of Non-Abelian Kitaev quantum spin liquids in noise magnetormetry

Identification of isolated Majorana zero modes (MZMs) is a key step towards the realization of fault-tolerant topological quantum computation. Here we show how the $T_1$-based noise magnetormetry of a nitrogen-vacancy (NV) center qubit can reveal the unique signatures of Majorana fermions attached to vacancies in a non-Abelian Kitaev quantum spin liquid (KQSL). The $1/T_1$ of the NV center is found to be increased significantly when the working frequency of the NV center matches the energy difference between a MZM and a low-energy hybridized mode involving dangling Majorana fermions adjacent to vacancies. In experiments, this energy difference can be tuned by an external Zeeman field. Because of the large excitation gap of flipping a local $Z_2$ gauge field, the $1/T_1$ spectrum is robust against other fluctuations in KQSLs. Our study presents a promising pathway for identifying the non-Abelian phase in Kitaev materials.

cond-mat.str-el↗

arXiv2024

Augmenting Biomedical Named Entity Recognition with General-domain Resources

Training a neural network-based biomedical named entity recognition (BioNER) model usually requires extensive and costly human annotations. While several studies have employed multi-task learning with multiple BioNER datasets to reduce human effort, this approach does not consistently yield performance improvements and may introduce label ambiguity in different biomedical corpora. We aim to tackle those challenges through transfer learning from easily accessible resources with fewer concept overlaps with biomedical datasets. We proposed GERBERA, a simple-yet-effective method that utilized general-domain NER datasets for training. We performed multi-task learning to train a pre-trained biomedical language model with both the target BioNER dataset and the general-domain dataset. Subsequently, we fine-tuned the models specifically for the BioNER dataset. We systematically evaluated GERBERA on five datasets of eight entity types, collectively consisting of 81,410 instances. Despite using fewer biomedical resources, our models demonstrated superior performance compared to baseline models trained with additional BioNER datasets. Specifically, our models consistently outperformed the baseline models in six out of eight entity types, achieving an average improvement of 0.9% over the best baseline performance across eight entities. Our method was especially effective in amplifying performance on BioNER datasets characterized by limited data, with a 4.7% improvement in F1 scores on the JNLPBA-RNA dataset. This study introduces a new training method that leverages cost-effective general-domain NER datasets to augment BioNER models. This approach significantly improves BioNER model performance, making it a valuable asset for scenarios with scarce or costly biomedical datasets.

cs.CL↗

arXiv2024

if-ZKP: Intel FPGA-Based Acceleration of Zero Knowledge Proofs

Zero-Knowledge Proofs (ZKPs) have emerged as an important cryptographic technique allowing one party (prover) to prove the correctness of a statement to some other party (verifier) and nothing else. ZKPs give rise to user's privacy in many applications such as blockchains, digital voting, and machine learning. Traditionally, ZKPs suffered from poor scalability but recently, a sub-class of ZKPs known as Zero-knowledge Succinct Non-interactive ARgument of Knowledges (zk-SNARKs) have addressed this challenge. They are getting significant attention and are being implemented by many public libraries. In this paper, we present a novel scalable architecture that is suitable for accelerating the zk-SNARK prover compute on FPGAs. We focus on the multi-scalar multiplication (MSM) that accounts for the majority of computation time spent in zk-SNARK systems. The MSM calculations extensive rely on modular arithmetic so highly optimized Intel IP Libraries for modular arithmetic are used. The proposed architecture exploits the parallelism inherent to MSM and is implemented using the Intel OneAPI framework for FPGAs. Our implementation runs 110x-150x faster compared to reference software library, uses a generic curve form in Jacobian coordinates and is the first to report FPGA hardware acceleration results for BLS12-381 and BN128 family of elliptic curves.

cs.AR↗

arXiv2024

IDGen: Item Discrimination Induced Prompt Generation for LLM Evaluation

As Large Language Models (LLMs) grow increasingly adept at managing complex tasks, the evaluation set must keep pace with these advancements to ensure it remains sufficiently discriminative. Item Discrimination (ID) theory, which is widely used in educational assessment, measures the ability of individual test items to differentiate between high and low performers. Inspired by this theory, we propose an ID-induced prompt synthesis framework for evaluating LLMs to ensure the evaluation set can continually update and refine according to model abilities. Our data synthesis framework prioritizes both breadth and specificity. It can generate prompts that comprehensively evaluate the capabilities of LLMs while revealing meaningful performance differences between models, allowing for effective discrimination of their relative strengths and weaknesses across various tasks and domains. To produce high-quality data, we incorporate a self-correct mechanism into our generalization framework, and develop two models to predict prompt discrimination and difficulty score to facilitate our data synthesis framework, contributing valuable tools to evaluation data synthesis research. We apply our generated data to evaluate five SOTA models. Our data achieves an average score of 51.92, accompanied by a variance of 10.06. By contrast, previous works (i.e., SELF-INSTRUCT and WizardLM) obtain an average score exceeding 67, with a variance below 3.2. The results demonstrate that the data generated by our framework is more challenging and discriminative compared to previous works. We will release a dataset of over 3,000 carefully crafted prompts to facilitate evaluation research of LLMs.

cs.CL↗

arXiv2024

Mitigating Pooling Bias in E-commerce Search via False Negative Estimation

Efficient and accurate product relevance assessment is critical for user experiences and business success. Training a proficient relevance assessment model requires high-quality query-product pairs, often obtained through negative sampling strategies. Unfortunately, current methods introduce pooling bias by mistakenly sampling false negatives, diminishing performance and business impact. To address this, we present Bias-mitigating Hard Negative Sampling (BHNS), a novel negative sampling strategy tailored to identify and adjust for false negatives, building upon our original False Negative Estimation algorithm. Our experiments in the Instacart search setting confirm BHNS as effective for practical e-commerce use. Furthermore, comparative analyses on public dataset showcase its domain-agnostic potential for diverse applications.

cs.IR↗

arXiv2024

Android in the Zoo: Chain-of-Action-Thought for GUI Agents

Large language model (LLM) leads to a surge of autonomous GUI agents for smartphone, which completes a task triggered by natural language through predicting a sequence of actions of API. Even though the task highly relies on past actions and visual observations, existing studies typically consider little semantic information carried out by intermediate screenshots and screen operations. To address this, this work presents Chain-of-Action-Thought (dubbed CoAT), which takes the description of the previous actions, the current screen, and more importantly the action thinking of what actions should be performed and the outcomes led by the chosen action. We demonstrate that, in a zero-shot setting upon three off-the-shelf LMMs, CoAT significantly improves the action prediction compared to previous proposed context modeling. To further facilitate the research in this line, we construct a dataset Android-In-The-Zoo (AitZ), which contains 18,643 screen-action pairs together with chain-of-action-thought annotations. Experiments show that fine-tuning a 1B model (i.e. AUTO-UI-base) on our AitZ dataset achieves on-par performance with CogAgent-Chat-18B.

cs.CL↗

arXiv2024

STEMO: Early Spatio-temporal Forecasting with Multi-Objective Reinforcement Learning

Accuracy and timeliness are indeed often conflicting goals in prediction tasks. Premature predictions may yield a higher rate of false alarms, whereas delaying predictions to gather more information can render them too late to be useful. In applications such as wildfires, crimes, and traffic jams, timely forecasting are vital for safeguarding human life and property. Consequently, finding a balance between accuracy and timeliness is crucial. In this paper, we propose an early spatio-temporal forecasting model based on Multi-Objective reinforcement learning that can either implement an optimal policy given a preference or infer the preference based on a small number of samples. The model addresses two primary challenges: 1) enhancing the accuracy of early forecasting and 2) providing the optimal policy for determining the most suitable prediction time for each area. Our method demonstrates superior performance on three large-scale real-world datasets, surpassing existing methods in early spatio-temporal forecasting tasks.

cs.LG↗