arXiv subjects

Zhiming Zhang

Publications and source records attributed to Zhiming Zhang.

At least 19 recordsLinked to original sources

arXiv2026

GeoAgentBench: A Dynamic Execution Benchmark for Tool-Augmented Agents in Spatial Analysis

The integration of Large Language Models (LLMs) into Geographic Information Systems (GIS) marks a paradigm shift toward autonomous spatial analysis. However, evaluating these LLM-based agents remains challenging due to the complex, multi-step nature of geospatial workflows. Existing benchmarks primarily rely on static text or code matching, neglecting dynamic runtime feedback and the multimodal nature of spatial outputs. To address this gap, we introduce GeoAgentBench (GABench), a dynamic and interactive evaluation benchmark tailored for tool-augmented GIS agents. GABench provides a realistic execution sandbox integrating 117 atomic GIS tools, encompassing 53 typical spatial analysis tasks across 6 core GIS domains. Recognizing that precise parameter configuration is the primary determinant of execution success in dynamic GIS environments, we designed the Parameter Execution Accuracy (PEA) metric, which utilizes a "Last-Attempt Alignment" strategy to quantify the fidelity of implicit parameter inference. Complementing this, a Vision-Language Model (VLM) based verification is proposed to assess data-spatial accuracy and cartographic style adherence. Furthermore, to address the frequent task failures caused by parameter misalignments and runtime anomalies, we developed a novel agent architecture, Plan-and-React, that mimics expert cognitive workflows by decoupling global orchestration from step-wise reactive execution. Extensive experiments with seven representative LLMs demonstrate that the Plan-and-React paradigm significantly outperforms traditional frameworks, achieving the optimal balance between logical rigor and execution robustness, particularly in multi-step reasoning and error recovery. Our findings highlight current capability boundaries and establish a robust standard for assessing and advancing the next generation of autonomous GeoAI.

cs.AI↗

arXiv2025

Automated Snippet-Alignment Data Augmentation for Code Translation

Code translation aims to translate the code from its source language to the target language and is used in various software development scenarios. Recent developments in Large Language Models (LLMs) have showcased their capabilities in code translation, and parallel corpora play a crucial role in training models for code translation. Parallel corpora can be categorized into program-alignment (PA) and snippet-alignment (SA) data. Although PA data has complete context and is suitable for semantic alignment learning, it may not provide adequate fine-grained training signals due to its extended length, while the brevity of SA data enables more fine-grained alignment learning. Due to limited parallel corpora, researchers explore several augmentation methods for code translation. Previous studies mainly focus on augmenting PA data. In this paper, we propose a data augmentation method that leverages LLMs to generate SA data automatically. To fully leverage both PA data and SA data, we explore a simple yet effective two-stage training strategy, which consistently enhances model performance compared to fine-tuning solely on PA data. Experiments on TransCoder-test demonstrate that our augmented SA data combined with the two-stage training approach yields consistent improvements over the baseline, achieving a maximum gain of 3.78% on pass@k.

cs.SE↗

arXiv2025

InstructPLM-mu: 1-Hour Fine-Tuning of ESM2 Beats ESM3 in Protein Mutation Predictions

Multimodal protein language models deliver strong performance on mutation-effect prediction, but training such models from scratch demands substantial computational resources. In this paper, we propose a fine-tuning framework called InstructPLM-mu and try to answer a question: \textit{Can multimodal fine-tuning of a pretrained, sequence-only protein language model match the performance of models trained end-to-end? } Surprisingly, our experiments show that fine-tuning ESM2 with structural inputs can reach performance comparable to ESM3. To understand how this is achieved, we systematically compare three different feature-fusion designs and fine-tuning recipes. Our results reveal that both the fusion method and the tuning strategy strongly affect final accuracy, indicating that the fine-tuning process is not trivial. We hope this work offers practical guidance for injecting structure into pretrained protein language models and motivates further research on better fusion mechanisms and fine-tuning protocols.

q-bio.QM↗

arXiv2025

Success is in the Details: Evaluate and Enhance Details Sensitivity of Code LLMs through Counterfactuals

Code Sensitivity refers to the ability of Code LLMs to recognize and respond to details changes in problem descriptions. While current code benchmarks and instruction data focus on difficulty and diversity, sensitivity is overlooked. We first introduce the CTF-Code benchmark, constructed using counterfactual perturbations, minimizing input changes while maximizing output changes. The evaluation shows that many LLMs have a more than 10\% performance drop compared to the original problems. To fully utilize sensitivity, CTF-Instruct, an incremental instruction fine-tuning framework, extends on existing data and uses a selection mechanism to meet the three dimensions of difficulty, diversity, and sensitivity. Experiments show that LLMs fine-tuned with CTF-Instruct data achieve over a 2\% improvement on CTF-Code, and more than a 10\% performance boost on LiveCodeBench, validating the feasibility of enhancing LLMs' sensitivity to improve performance.

cs.CL↗

arXiv2025

Feature splitting parallel algorithm for Dantzig selectors

The Dantzig selector is a widely used and effective method for variable selection in ultra-high-dimensional data. Feature splitting is an efficient processing technique that involves dividing these ultra-high-dimensional variable datasets into manageable subsets that can be stored and processed more easily on a single machine. This paper proposes a variable splitting parallel algorithm for solving both convex and nonconvex Dantzig selectors based on the proximal point algorithm. The primary advantage of our parallel algorithm, compared to existing parallel approaches, is the significantly reduced number of iteration variables, which greatly enhances computational efficiency and accelerates the convergence speed of the algorithm. Furthermore, we show that our solution remains unchanged regardless of how the data is partitioned, a property referred to as partitioninsensitive. In theory, we use a concise proof framework to demonstrate that the algorithm exhibits linear convergence. Numerical experiments indicate that our algorithm performs competitively in both parallel and nonparallel environments. The R package for implementing the proposed algorithm can be obtained at https://github.com/xfwu1016/PPADS.

stat.CO↗

arXiv2025

First experimental proof of PET imaging based on multi-anode MCP-PMTs with Cherenkov radiator-integrated window

Improving the coincidence time resolution (CTR) of time-of-flight positron emission tomography (TOF-PET) systems to achieve a higher signal-to-noise ratio (SNR) gain or even direct positron emission imaging (dPEI) is of paramount importance for many advanced new clinical applications of PET imaging. This places higher demands on the timing performance of all aspects of PET systems. One effective approach is to use microchannel plate photomultiplier tubes (MCP-PMTs) for prompt Cherenkov photon detection. In this study, we developed a dual-module Cherenkov PET imaging experimental platform, utilising our proprietary 8 * 8-anode Cherenkov radiator-integrated window MCP-PMTs in combination with custom-designed multi-channel electronics, and designed a specific calibration and correction method for the platform. Using this platform, a CTR of 103 ps FWHM was achieved. We overcame the limitations of single-anode detectors in previous experiments, significantly enhanced imaging efficiency and achieved module-level Cherenkov PET imaging for the first time. Imaging experiments involving radioactive sources and phantoms of various shapes and types were conducted, which preliminarily validated the feasibility and advancement of this imaging method. In addition, the effects of normalisation correction and the interaction probability between the gamma rays and the MCP on the images and experimental results were analysed and verified.

physics.ins-det↗

arXiv2024

Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token Recycling

Massive parameters of LLMs have made inference latency a fundamental bottleneck. Speculative decoding represents a lossless approach to accelerate inference through a guess-and-verify paradigm. Some methods rely on additional architectures to guess draft tokens, which need extra training before use. Alternatively, retrieval-based training-free techniques build libraries from pre-existing corpora or by n-gram generation. However, they face challenges like large storage requirements, time-consuming retrieval, and limited adaptability. Observing that candidate tokens generated during the decoding process are likely to reoccur in future sequences, we propose Token Recycling. It stores candidate tokens in an adjacency matrix and employs a breadth-first-search (BFS)-like algorithm to construct a draft tree, which is then validated through tree attention. New candidate tokens from the decoding process are then used to update the matrix. Token Recycling requires \textless2MB of additional storage and achieves approximately 2x speedup across all sizes of LLMs. It significantly outperforms existing train-free methods by 30\% and even a widely recognized training method by 25\%.

cs.CL↗

arXiv2024

Causal Customer Churn Analysis with Low-rank Tensor Block Hazard Model

This study introduces an innovative method for analyzing the impact of various interventions on customer churn, using the potential outcomes framework. We present a new causal model, the tensorized latent factor block hazard model, which incorporates tensor completion methods for a principled causal analysis of customer churn. A crucial element of our approach is the formulation of a 1-bit tensor completion for the parameter tensor. This captures hidden customer characteristics and temporal elements from churn records, effectively addressing the binary nature of churn data and its time-monotonic trends. Our model also uniquely categorizes interventions by their similar impacts, enhancing the precision and practicality of implementing customer retention strategies. For computational efficiency, we apply a projected gradient descent algorithm combined with spectral clustering. We lay down the theoretical groundwork for our model, including its non-asymptotic properties. The efficacy and superiority of our model are further validated through comprehensive experiments on both simulated and real-world applications.

stat.ML↗

arXiv2024

Semi-Instruct: Bridging Natural-Instruct and Self-Instruct for Code Large Language Models

Instruction tuning plays a pivotal role in Code Large Language Models (Code LLMs) for the task of program synthesis. Presently, two dominant paradigms for collecting tuning data are natural-instruct (human-written) and self-instruct (automatically generated). Natural-instruct includes diverse and correct codes but lacks instruction-code pairs, and exists improper code formats like nested single-line codes. In contrast, self-instruct automatically generates proper paired data. However, it suffers from low diversity due to generating duplicates and cannot ensure the correctness of codes. To bridge the both paradigms, we propose \textbf{Semi-Instruct}. It first converts diverse but improper codes from natural-instruct into proper instruction-code pairs through a method similar to self-instruct. To verify the correctness of generated codes, we design a novel way to construct test cases by generating cases' inputs and executing correct codes from natural-instruct to get outputs. Finally, diverse and correct instruction-code pairs are retained for instruction tuning. Experiments show that semi-instruct is significantly better than natural-instruct and self-instruct. Furthermore, the performance steadily improves as data scale increases.

cs.CL↗

arXiv2024

Python is Not Always the Best Choice: Embracing Multilingual Program of Thoughts

Program of Thoughts (PoT) is an approach characterized by its executable intermediate steps, which ensure the accuracy of the logical calculations in the reasoning process. Currently, PoT primarily uses Python. However, relying solely on a single language may result in suboptimal solutions and overlook the potential benefits of other programming languages. In this paper, we conduct comprehensive experiments on the programming languages used in PoT and find that no single language consistently delivers optimal performance across all tasks and models. The effectiveness of each language varies depending on the specific scenarios. Inspired by this, we propose a task and model agnostic approach called MultiPoT, which harnesses strength and diversity from various languages. Experimental results reveal that it significantly outperforms Python Self-Consistency. Furthermore, it achieves comparable or superior performance compared to the best monolingual PoT in almost all tasks across all models. In particular, MultiPoT achieves more than 4.6% improvement on average on ChatGPT (gpt-3.5-turbo-0701).

cs.CL↗

arXiv2022

Real-RawVSR: Real-World Raw Video Super-Resolution with a Benchmark Dataset

In recent years, real image super-resolution (SR) has achieved promising results due to the development of SR datasets and corresponding real SR methods. In contrast, the field of real video SR is lagging behind, especially for real raw videos. Considering the superiority of raw image SR over sRGB image SR, we construct a real-world raw video SR (Real-RawVSR) dataset and propose a corresponding SR method. We utilize two DSLR cameras and a beam-splitter to simultaneously capture low-resolution (LR) and high-resolution (HR) raw videos with 2x, 3x, and 4x magnifications. There are 450 video pairs in our dataset, with scenes varying from indoor to outdoor, and motions including camera and object movements. To our knowledge, this is the first real-world raw VSR dataset. Since the raw video is characterized by the Bayer pattern, we propose a two-branch network, which deals with both the packed RGGB sequence and the original Bayer pattern sequence, and the two branches are complementary to each other. After going through the proposed co-alignment, interaction, fusion, and reconstruction modules, we generate the corresponding HR sRGB sequence. Experimental results demonstrate that the proposed method outperforms benchmark real and synthetic video SR methods with either raw or sRGB inputs. Our code and dataset are available at https://github.com/zmzhang1998/Real-RawVSR.

cs.CV↗

arXiv2021

Robust physics discovery via supervised and unsupervised pattern recognition using the Euler characteristic

Machine learning approaches have been widely used for discovering the underlying physics of dynamical systems from measured data. Existing approaches, however, still lack robustness, especially when the measured data contain a large level of noise. The lack of robustness is mainly attributed to the insufficient representativeness of used features. As a result, the intrinsic mechanism governing the observed system cannot be accurately identified. In this study, we use an efficient topological descriptor for complex data, i.e., the Euler characteristics (ECs), as features to characterize the spatiotemporal data collected from dynamical systems and discover the underlying physics. Unsupervised manifold learning and supervised classification results show that EC can be used to efficiently distinguish systems with different while similar governing models. We also demonstrate that the machine learning approaches using EC can improve the confidence level of sparse regression methods of physics discovery.

cs.CE↗

arXiv2021

Parsimony-Enhanced Sparse Bayesian Learning for Robust Discovery of Partial Differential Equations

Robust physics discovery is of great interest for many scientific and engineering fields. Inspired by the principle that a representative model is the one simplest possible, a new model selection criteria considering both model's Parsimony and Sparsity is proposed. A Parsimony Enhanced Sparse Bayesian Learning (PeSBL) method is developed for discovering the governing Partial Differential Equations (PDEs) of nonlinear dynamical systems. Compared with the conventional Sparse Bayesian Learning (SBL) method, the PeSBL method promotes parsimony of the learned model in addition to its sparsity. In this method, the parsimony of model terms is evaluated using their locations in the prescribed candidate library, for the first time, considering the increased complexity with the power of polynomials and the order of spatial derivatives. Subsequently, the model parameters are updated through Bayesian inference with the raw data. This procedure aims to reduce the error associated with the possible loss of information in data preprocessing and numerical differentiation prior to sparse regression. Results of numerical case studies indicate that the governing PDEs of many canonical dynamical systems can be correctly identified using the proposed PeSBL method from highly noisy data (up to 50% in the current study). Next, the proposed methodology is extended for stochastic PDE learning where all parameters and modeling error are considered as random variables. Hierarchical Bayesian Inference (HBI) is integrated with the proposed framework for stochastic PDE learning from a population of observations. Finally, the proposed PeSBL is demonstrated for system response prediction with uncertainties and anomaly diagnosis. Codes of all demonstrated examples in this study are available on the website: https://github.com/ymlasu.

cs.LG↗

arXiv2021

Robust Data-Driven Discovery of Partial Differential Equations under Uncertainties

Robust physics (e.g., governing equations and laws) discovery is of great interest for many engineering fields and explainable machine learning. A critical challenge compared with general training is that the term and format of governing equations is not known as a prior. In addition, significant measurement noise and complex algorithm hyperparameter tuning usually reduces the robustness of existing methods. A robust data-driven method is proposed in this study for identifying the governing Partial Differential Equations (PDEs) of a given system from noisy data. The proposed method is based on the concept of Progressive Sparse Identification of PDEs (PSI-PDE or $ψ$-PDE). Special focus is on the handling of data with huge uncertainties (e.g., 50$\%$ noise level). Neural Network modeling and fast Fourier transform (FFT) are implemented to reduce the influence of noise in sparse regression. Following this, candidate terms from the prescribed library are progressively selected and added to the learned PDEs, which automatically promotes parsimony with respect to the number of terms in PDEs as well as their complexity. Next, the significance of each learned terms is further evaluated and the coefficients of PDE terms are optimized by minimizing the L2 residuals. Results of numerical case studies indicate that the governing PDEs of many canonical dynamical systems can be correctly identified using the proposed $ψ$-PDE method with highly noisy data. One great benefit of proposed algorithm is that it avoids complex algorithm modification and hyperparameter tuning in most existing methods. Limitations of the proposed method and major findings are presented.

math.NA↗

arXiv2021

Condition Assessment of Stay Cables through Enhanced Time Series Classification Using a Deep Learning Approach

This study proposes a data-driven method that detects cable damage from measured cable forces by recognizing biased patterns from the intact conditions. The proposed method solves the pattern recognition problem for cable damage detection through time series classification (TSC) in deep learning, considering that the cable's behavior can be implicitly represented by the measured cable force series. A deep learning model, long short term memory fully convolutional network (LSTM-FCN), is leveraged by assigning appropriate inputs and representative class labels for the TSC problem, First, a TSC classifier is trained and validated using the data collected under intact conditions of stay cables, setting the segmented data series as input and the cable (or cable pair) ID as class labels. Subsequently, the classifier is tested using the data collected under possible damaged conditions. Finally, the cable or cable pair corresponding to the least classification accuracy is recommended as the most probable damaged cable or cable pair. The proposed method was tested on an in-service cable-stayed bridge with damaged stay cables. Two scenarios in the proposed TSC scheme were investigated: 1) raw time series of cable forces were fed into the classifiers; and 2) cable force ratios were inputted in the classifiers considering the possible variation of force distribution between cable pairs due to cable damage. Combining the results of TSC testing in these two scenarios, the cable with rupture was correctly identified. This study proposes a data-driven methodology for cable damage detection that requires the least data preprocessing and feature engineering, which enables fast and convenient early detection in real applications.

cs.LG↗

arXiv2020

Probing the wavefunctions of correlated states in magic angle graphene

Using scanning probe microscopy and spectroscopy, we explore the spatial symmetry of the electronic wavefunctions of twisted bilayer graphene at the "magic angle" of 1.1 degrees. This small twist angle leads to a long wavelength moiré unit cell on the order of 13 nm and the appearance of two flat bands. As the twist angle is decreased, correlation effects increase until they are maximized at the magic angle. At this angle, the wavefunctions at the charge neutrality point show only C2 symmetry due to the emergence of a charge ordered state. As the system is doped, the symmetry of the wavefunctions change at each commensurate filling of the moiré unit cell pointing to the correlated nature of the spin and valley degeneracy broken states.

cond-mat.mes-hall↗

arXiv2020

Flat bands in twisted bilayer transition metal dichalcogenides

The crystal structure of a material creates a periodic potential that electrons move through giving rise to the electronic band structure of the material. When two-dimensional materials are stacked, the twist angle between the layers becomes an additional degree freedom for the resulting heterostructure. As this angle changes, the electronic band structure is modified leading to the possibility of flat bands with localized states and enhanced electronic correlations. In transition metal dichalcogenides, flat bands have been theoretically predicted to occur for long moiré wavelengths over a range of twist angles around 0 and 60 degrees giving much wider versatility than magic angle twisted bilayer graphene. Here we show the existence of a flat band in the electronic structure of 3° and 57.5° twisted bilayer WSe2 samples using scanning tunneling spectroscopy. Direct spatial mapping of wavefunctions at the flat band energy have shown that the flat bands are localized differently for 3° and 57.5°, in excellent agreement with first-principle density functional theory calculations.

cond-mat.str-el↗

arXiv2020

Local characterization and engineering of proximitized correlated states in graphene-NbSe$_2$ vertical heterostructures

Using a van der Waals vertical heterostructure consisting of monolayer graphene, monolayer hBN and NbSe$_2$, we have performed local characterization of induced correlated states in different configurations. At a temperature of 4.6 K, we have shown that both superconductivity and charge density waves can be induced in graphene from NbSe2 by proximity effects. By applying a vertical magnetic field, we imaged the Abrikosov vortex lattice and extracted the coherence length for the proximitized superconducting graphene. We further show that the induced correlated states can be completely blocked by adding a monolayer hBN between the graphene and the NbSe$_2$, which demonstrates the importance of the tunnel barrier and surface conditions between the normal metal and superconductor for the proximity effect.

cond-mat.mes-hall↗