arXiv subjects

Ran Tao

Publications and source records attributed to Ran Tao.

At least 55 records · Page 3Linked to original sources

arXiv2026

Agent Bain vs. Agent McKinsey: A New Text-to-SQL Benchmark for the Business Domain

Text-to-SQL benchmarks have traditionally only tested simple data access as a translation task of natural language to SQL queries. But in reality, users tend to ask diverse questions that require more complex responses including data-driven predictions or recommendations. Using the business domain as a motivating example, we introduce CORGI, a new benchmark that expands text-to-SQL to reflect practical database queries encountered by end users. CORGI is composed of synthetic databases inspired by enterprises such as DoorDash, Airbnb, and Lululemon. It provides questions across four increasingly complicated categories of business queries: descriptive, explanatory, predictive, and recommendational. This challenge calls for causal reasoning, temporal forecasting, and strategic recommendation, reflecting multi-level and multi-step agentic intelligence. We find that LLM performance degrades on higher-level questions as question complexity increases. CORGI also introduces and encourages the text-to-SQL community to consider new automatic methods for evaluating open-ended, qualitative responses in data access tasks. Our experiments show that LLMs exhibit an average 33.12% lower success execution rate (SER) on CORGI compared to existing benchmarks such as BIRD, highlighting the substantially higher complexity of real-world business needs. We release the CORGI dataset, an evaluation framework, and a submission website to support future research.

cs.CL↗

arXiv2026

Non-volatile Programmable Photonic Integrated Circuits using Mechanically Latched MEMS: A System-Level Scheme Enabling Power-Connection-Free Operation Without Performance Compromise

Programmable photonic integrated circuits (PPICs) offer a versatile platform for implementing diverse optical functions on a generic hardware mesh. However, the scalability of PPICs faces critical power consumption barriers. Therefore, we propose a novel non-volatile PPIC architecture utilizing MEMS with mechanical latching, enabling stable passive operation without any power connection once configured. To ensure practical applicability, we present a system-level solution including both this hardware innovation and an accompanying automatic error-resilient configuration algorithm. The algorithm compensates for the lack of continuous tunability inherent in the non-volatile hardware design, thereby enabling such new operational paradigm without compromising performance, and also ensuring robustness against fabrication errors. Functional simulations were performed to validate the proposed scheme by configuring five distinct functionalities of varying complexity, including a Mach-Zehnder interferometer (MZI), a MZI lattice filter, a ring resonator (ORR), a double ORR ring-loaded MZI, and a triple ORR coupled resonator waveguide filter. The results demonstrate that our non-volatile scheme achieves performance equivalent to conventional PPICs. Robustness analysis was also conducted, and the results demonstrated that our scheme exhibits strong robustness against various fabrication errors. Furthermore, we explored the trade-off between the hardware design complexity of such non-volatile scheme and its performance. This study establishes a viable pathway to a new generation of power-connection-free PPICs, providing a practical and scalable solution for future photonic systems.

physics.optics↗

arXiv2025

Universal Reasoning Model

Universal transformers (UTs) have been widely used for complex reasoning tasks such as ARC-AGI and Sudoku, yet the specific sources of their performance gains remain underexplored. In this work, we systematically analyze UTs variants and show that improvements on ARC-AGI primarily arise from the recurrent inductive bias and strong nonlinear components of Transformer, rather than from elaborate architectural designs. Motivated by this finding, we propose the Universal Reasoning Model (URM), which enhances the UT with short convolution and truncated backpropagation. Our approach substantially improves reasoning performance, achieving state-of-the-art 53.8% pass@1 on ARC-AGI 1 and 16.0% pass@1 on ARC-AGI 2. Our code is avaliable at https://github.com/UbiquantAI/URM.

cs.AI↗

arXiv2025

Fluctuation exponents of the half-space KPZ at stationarity

We study the half-space KPZ equation with a Neumann boundary condition, starting from stationary Brownian initial data. We derive a variance identity that links the fluctuations of the height function to the transversal fluctuations of a half-space polymer model. Utilizing this identity, we obtain estimates for the polymer endpoints, leading to optimal fluctuation exponents for the height function in both the subcritical and critical regimes, as well as an optimal upper bound for the fluctuation exponents in the extended critical regime. We also compute the average growth rate as a function of the boundary parameter.

math.PR↗

arXiv2025

Selective trapping of bacteria in porous media by cell length

Bacteria commonly inhabit porous environments such as host tissues, soil, and marine sediments, where complex geometries constrain and redirect their motion. Although bacterial motility has been studied in porous media, the roles of cell length and pore shape in navigating these environments remain poorly understood. Here, we investigate how cell morphology and pore architecture jointly determine bacterial spreading behavior. Using genetically engineered E. coli with tunable cell length, we performed single-cell tracking in microfluidic devices that mimic ordered and disordered porous structures. We find that elongated bacteria traverse ordered pore networks more effectively than short cells, exhibiting straighter paths, greater directional persistence, and enhanced exploration efficiency. In contrast, in disordered porous media, elongated bacteria become trapped in dead-end regions for extended periods, resulting in markedly reduced navigational efficiency. Together, these results reveal how cell shape and environmental geometry interact to govern bacterial transport. Moreover, we suggest a new mechanism for separating antimicrobial-resistant (AMR) bacteria from elongated susceptible cells in designer porous media.

cond-mat.soft↗

arXiv2025

Improving Topic Relevance Model by Mix-structured Summarization and LLM-based Data Augmentation

Topic relevance between query and document is a very important part of social search, which can evaluate the degree of matching between document and user's requirement. In most social search scenarios such as Dianping, modeling search relevance always faces two challenges. One is that many documents in social search are very long and have much redundant information. The other is that the training data for search relevance model is difficult to get, especially for multi-classification relevance model. To tackle above two problems, we first take query concatenated with the query-based summary and the document summary without query as the input of topic relevance model, which can help model learn the relevance degree between query and the core topic of document. Then, we utilize the language understanding and generation abilities of large language model (LLM) to rewrite and generate query from queries and documents in existing training data, which can construct new query-document pairs as training data. Extensive offline experiments and online A/B tests show that the proposed approaches effectively improve the performance of relevance modeling.

cs.IR↗

arXiv2025

Robust High-Resolution Multi-Organ Diffusion MRI Using Synthetic-Data-Tuned Prompt Learning

Clinical adoption of multi-shot diffusion-weighted magnetic resonance imaging (multi-shot DWI) for body-wide tumor diagnostics is limited by severe motion-induced phase artifacts from respiration, peristalsis, and so on, compounded by multi-organ, multi-slice, multi-direction and multi-b-value complexities. Here, we introduce a reconstruction framework, LoSP-Prompt, that overcomes these challenges through physics-informed modeling and synthetic-data-driven prompt learning. We model inter-shot phase variations as a high-order Locally Smooth Phase (LoSP), integrated into a low-rank Hankel matrix reconstruction. Crucially, the algorithm's rank parameter is automatically set via prompt learning trained exclusively on synthetic abdominal DWI data emulating physiological motion. Validated across 10,000+ clinical images (43 subjects, 4 scanner models, 5 centers), LoSP-Prompt: (1) Achieved twice the spatial resolution of clinical single-shot DWI, enhancing liver lesion conspicuity; (2) Generalized to seven diverse anatomical regions (liver, kidney, sacroiliac, pelvis, knee, spinal cord, brain) with a single model; (3) Outperformed state-of-the-art methods in image quality, artifact suppression, and noise reduction (11 radiologists' evaluations on a 5-point scale, $p<0.05$), achieving 4-5 points (excellent) on kidney DWI, 4 points (good to excellent) on liver, sacroiliac and spinal cord DWI, and 3-4 points (good) on knee and tumor brain. The approach eliminates navigator signals and realistic data supervision, providing an interpretable, robust solution for high-resolution multi-organ multi-shot DWI. Its scanner-agnostic performance signifies transformative potential for precision oncology.

cs.CV↗

arXiv2025

What Makes Diffusion Language Models Super Data Learners?

Recent studies have shown that diffusion language models achieve remarkable data efficiency under limited-data constraints, yet the underlying mechanisms remain unclear. In this work, we perform extensive ablation experiments to disentangle the sources of this efficiency. Our results show that random masking of input tokens plays the dominant role. We further show that similar gains can be obtained through in MLP dropout and weight decay, indicating that stochastic regularization broadly enhances data efficiency in multi-epoch training. Our code is available at https://github.com/zitian-gao/data-efficiency.

cs.CL↗

arXiv2025

A Simulation Evaluation Suite for Robust Adaptive Quadcopter Control

Robust adaptive control methods are essential for maintaining quadcopter performance under external disturbances and model uncertainties. However, fragmented evaluations across tasks, simulators, and implementations hinder systematic comparison of these methods. This paper introduces an easy-to-deploy, modular simulation testbed for quadcopter control, built on RotorPy, that enables evaluation under a wide range of disturbances such as wind, payload shifts, rotor faults, and control latency. The framework includes a library of representative adaptive and non-adaptive controllers and provides task-relevant metrics to assess tracking accuracy and robustness. The unified modular environment enables reproducible evaluation across control methods and eliminates redundant reimplementation of components such as disturbance models, trajectory generators, and analysis tools. We illustrate the testbed's versatility through examples spanning multiple disturbance scenarios and trajectory types, including automated stress testing, to demonstrate its utility for systematic analysis. Code is available at https://github.com/Dz298/AdaptiveQuadBench.

cs.RO↗

arXiv2025

On Minimization/Maximization of the Generalized Multi-Order Complex Quadratic Form With Constant-Modulus Constraints

In this paper, we study the generalized problem that minimizes or maximizes a multi-order complex quadratic form with constant-modulus constraints on all elements of its optimization variable. Such a mathematical problem is commonly encountered in various applications of signal processing. We term it as the constant-modulus multi-order complex quadratic programming (CMCQP) in this paper. In general, the CMCQP is non-convex and difficult to solve. Its objective function typically relates to metrics such as signal-to-noise ratio, Cramér-Rao bound, integrated sidelobe level, etc., and constraints normally correspond to requirements on similarity to desired aspects, peak-to-average-power ratio, or constant-modulus property in practical scenarios. In order to find efficient solutions to the CMCQP, we first reformulate it into an unconstrained optimization problem with respect to phase values of the studied variable only. Then, we devise a steepest descent/ascent method with fast determinations on its optimal step sizes. Specifically, we convert the step-size searching problem into a polynomial form that leads to closed-form solutions of high accuracy, wherein the third-order Taylor expansion of the search function is conducted. Our major contributions also lie in investigating the effect of the order and specific form of matrices embedded in the CMCQP, for which two representative cases are identified. Examples of related applications associated with the two cases are also provided for completeness. The proposed methods are summarized into algorithms, whose convergence speeds are verified to be fast by comprehensive simulations and comparisons to existing methods. The accuracy of our proposed fast step-size determination is also evaluated.

eess.SP↗

arXiv2025

SpectralX: Parameter-efficient Domain Generalization for Spectral Remote Sensing Foundation Models

Recent advances in Remote Sensing Foundation Models (RSFMs) have led to significant breakthroughs in the field. While many RSFMs have been pretrained with massive optical imagery, more multispectral/hyperspectral data remain lack of the corresponding foundation models. To leverage the advantages of spectral imagery in earth observation, we explore whether existing RSFMs can be effectively adapted to process diverse spectral modalities without requiring extensive spectral pretraining. In response to this challenge, we proposed SpectralX, an innovative parameter-efficient fine-tuning framework that adapt existing RSFMs as backbone while introducing a two-stage training approach to handle various spectral inputs, thereby significantly improving domain generalization performance. In the first stage, we employ a masked-reconstruction task and design a specialized Hyper Tokenizer (HyperT) to extract attribute tokens from both spatial and spectral dimensions. Simultaneously, we develop an Attribute-oriented Mixture of Adapter (AoMoA) that dynamically aggregates multi-attribute expert knowledge while performing layer-wise fine-tuning. With semantic segmentation as downstream task in the second stage, we insert an Attribute-refined Adapter (Are-adapter) into the first stage framework. By iteratively querying low-level semantic features with high-level representations, the model learns to focus on task-beneficial attributes, enabling customized adjustment of RSFMs. Following this two-phase adaptation process, SpectralX is capable of interpreting spectral imagery from new regions or seasons. The codes will be available from the website: https://github.com/YuxiangZhang-BIT.

cs.CV↗

arXiv2025

Cross-domain Hyperspectral Image Classification based on Bi-directional Domain Adaptation

Utilizing hyperspectral remote sensing technology enables the extraction of fine-grained land cover classes. Typically, satellite or airborne images used for training and testing are acquired from different regions or times, where the same class has significant spectral shifts in different scenes. In this paper, we propose a Bi-directional Domain Adaptation (BiDA) framework for cross-domain hyperspectral image (HSI) classification, which focuses on extracting both domain-invariant features and domain-specific information in the independent adaptive space, thereby enhancing the adaptability and separability to the target scene. In the proposed BiDA, a triple-branch transformer architecture (the source branch, target branch, and coupled branch) with semantic tokenizer is designed as the backbone. Specifically, the source branch and target branch independently learn the adaptive space of source and target domains, a Coupled Multi-head Cross-attention (CMCA) mechanism is developed in coupled branch for feature interaction and inter-domain correlation mining. Furthermore, a bi-directional distillation loss is designed to guide adaptive space learning using inter-domain correlation. Finally, we propose an Adaptive Reinforcement Strategy (ARS) to encourage the model to focus on specific generalized feature extraction within both source and target scenes in noise condition. Experimental results on cross-temporal/scene airborne and satellite datasets demonstrate that the proposed BiDA performs significantly better than some state-of-the-art domain adaptation approaches. In the cross-temporal tree species classification task, the proposed BiDA is more than 3\%$\sim$5\% higher than the most advanced method. The codes will be available from the website: https://github.com/YuxiangZhang-BIT/IEEE_TCSVT_BiDA.

cs.CV↗

arXiv2025

On lattice tilings of $\mathbb{Z}^n$ by limited magnitude error balls $\mathcal{B}(n,2,k_{1},k_{2})$ with $k_1>k_2$

Lattice tilings of $\mathbb{Z}^n$ by limited-magnitude error balls correspond to linear perfect codes under such error models and play a crucial role in flash memory applications. In this work, we establish three main results. First, we fully determine the existence of lattice tilings by $\mathcal{B}(n,2,3,0)$ in all dimensions $n$. Second, we completely resolve the case $k_1=k_2+1$. Finally, we prove that for any integers $k_1>k_2\ge0$ where $k_1+k_2+1$ is composite, no lattice tiling of $\mathbb{Z}^n$ by the error ball $\mathcal{B}(n,2,k_1,k_2)$ exists for sufficiently large $n$.

math.CO↗

arXiv2025

Impact of Noisy Supervision in Foundation Model Learning

Foundation models are usually pre-trained on large-scale datasets and then adapted to downstream tasks through tuning. However, the large-scale pre-training datasets, often inaccessible or too expensive to handle, can contain label noise that may adversely affect the generalization of the model and pose unexpected risks. This paper stands out as the first work to comprehensively understand and analyze the nature of noise in pre-training datasets and then effectively mitigate its impacts on downstream tasks. Specifically, through extensive experiments of fully-supervised and image-text contrastive pre-training on synthetic noisy ImageNet-1K, YFCC15M, and CC12M datasets, we demonstrate that, while slight noise in pre-training can benefit in-domain (ID) performance, where the training and testing data share a similar distribution, it always deteriorates out-of-domain (OOD) performance, where training and testing distributions are significantly different. These observations are agnostic to scales of pre-training datasets, pre-training noise types, model architectures, pre-training objectives, downstream tuning methods, and downstream applications. We empirically ascertain that the reason behind this is that the pre-training noise shapes the feature space differently. We then propose a tuning method (NMTune) to affine the feature space to mitigate the malignant effect of noise and improve generalization, which is applicable in both parameter-efficient and black-box tuning manners. We additionally conduct extensive experiments on popular vision and language models, including APIs, which are supervised and self-supervised pre-trained on realistic noisy data for evaluation. Our analysis and results demonstrate the importance of this novel and fundamental research direction, which we term as Noisy Model Learning.

cs.LG↗

arXiv2025

Physics-informed Deep Diffusion MRI Reconstruction with Synthetic Data: Break Training Data Bottleneck in Artificial Intelligence

Diffusion magnetic resonance imaging (MRI) is the only imaging modality for non-invasive movement detection of in vivo water molecules, with significant clinical and research applications. Diffusion weighted imaging (DWI) MRI acquired by multi-shot techniques can achieve higher resolution, better signal-to-noise ratio, and lower geometric distortion than single-shot, but suffers from inter-shot motion-induced artifacts. These artifacts cannot be removed prospectively, leading to the absence of artifact-free training labels. Thus, the potential of deep learning in multi-shot DWI reconstruction remains largely untapped. To break the training data bottleneck, here, we propose a Physics-Informed Deep DWI reconstruction method (PIDD) to synthesize high-quality paired training data by leveraging the physical diffusion model (magnitude synthesis) and inter-shot motion-induced phase model (motion phase synthesis). The network is trained only once with 100,000 synthetic samples, achieving encouraging results on multiple realistic in vivo data reconstructions. Advantages over conventional methods include: (a) Better motion artifact suppression and reconstruction stability; (b) Outstanding generalization to multi-scenario reconstructions, including multi-resolution, multi-b-value, multi-under-sampling, multi-vendor, and multi-center; (c) Excellent clinical adaptability to patients with verifications by seven experienced doctors (p<0.001). In conclusion, PIDD presents a novel deep learning framework by exploiting the power of MRI physics, providing a cost-effective and explainable way to break the data bottleneck in deep learning medical imaging.

eess.IV↗

arXiv2025

Task-Parameter Nexus: Task-Specific Parameter Learning for Model-Based Control

This paper presents the Task-Parameter Nexus (TPN), a learning-based approach for online determination of the (near-)optimal control parameters of model-based controllers (MBCs) for tracking tasks. In TPN, a deep neural network is introduced to predict the control parameters for any given tracking task at runtime, especially when optimal parameters for new tasks are not immediately available. To train this network, we constructed a trajectory bank with various speeds and curvatures that represent different motion characteristics. Then, for each trajectory in the bank, we auto-tune the optimal control parameters offline and use them as the corresponding ground truth. With this dataset, the TPN is trained by supervised learning. We evaluated the TPN on the quadrotor platform. In simulation experiments, it is shown that the TPN can predict near-optimal control parameters for a spectrum of tracking tasks, demonstrating its robust generalization capabilities to unseen tasks.

cs.RO↗

arXiv2025

Anthropomorphic tissue-mimicking phantoms for oximetry validation in multispectral optical imaging

Significance: Optical imaging of blood oxygenation (sO$_2$) can be achieved based on the differential absorption spectra of oxy- and deoxy-haemoglobin. A key challenge in realising clinical validation of the sO$_2$ biomarkers is the absence of reliable sO$_2$ reference standards, including test objects. Aim: To enable quantitative testing of multispectral imaging methods for assessment of sO$_2$ by introducing anthropomorphic phantoms with appropriate tissue-mimicking optical properties. Approach: We used the stable copolymer-in-oil base material to create physical anthropomorphic structures and optimised dyes to mimic the optical absorption of blood across a wide spectral range. Using 3D-printed phantom moulds generated from a magnetic resonance image of a human forearm, we moulded the material into an anthropomorphic shape. Using both reflectance hyperspectral imaging (HSI) and photoacoustic tomography (PAT), we acquired images of the forearm phantoms and evaluated the performance of linear spectral unmixing (LSU). Results: Based on 10 fabricated forearm phantoms with vessel-like structures featuring five distinct sO$_2$ levels (between 0 and 100%), we showed that the measured absorption spectra of the material correlated well with HSI and PAT data with a Pearson correlation coefficient consistently above 0.8. Further, the application of LSU enabled a quantification of the mean absolute error in sO$_2$ assessment with HSI and PAT. Conclusion: Our anthropomorphic tissue-mimicking phantoms hold potential to provide a robust tool for developing, standardising, and validating optical imaging of sO$_2$.

physics.med-ph↗

arXiv2025

Tree-like graphings, wallings, and median graphings of equivalence relations

We prove several results showing that every locally finite Borel graph whose large-scale geometry is "tree-like" induces a treeable equivalence relation. In particular, our hypotheses hold if each component of the original graph either has bounded tree-width or is quasi-isometric to a tree, answering a question of Tucker-Drob. In the latter case, we moreover show that there exists a Borel quasi-isometry to a Borel forest, under the additional assumption of (componentwise) bounded degree. We also extend these results on quasi-treeings to Borel proper metric spaces. In fact, our most general result shows treeability of countable Borel equivalence relations equipped with an abstract wallspace structure on each class obeying some local finiteness conditions, which we call a proper walling. The proof is based on the Stone duality between proper wallings and median graphs, i.e., CAT(0) cube complexes. Finally, we strengthen the conclusion of treeability in these results to hyperfiniteness in the case where the original graph has one (selected) end per component, generalizing the same result for trees due to Dougherty--Jackson--Kechris.

math.LO↗