arXiv subjects

Tian Huang

Publications and source records attributed to Tian Huang.

At least 19 recordsLinked to original sources

arXiv2026

A Possible Triple Formation Scenario of Binary Black Hole Merge With One In Pair-instability Supernova Mass Gap

Observations of binary black hole (BBH) mergers detected by LIGO -- such as GW170729, GW190620, GW190706, GW230107, GW230820, and GW230928 -- feature high effective spins and primary black holes that fall squarely into the pair-instability supernova (PISN) mass gap ($\sim 45-130 \, M_{\odot}$). These events pose a significant challenge to standard stellar and binary evolution theories. To address this, we propose an isolated hierarchical triple stellar evolution channel. In this framework, tidal synchronization in tight inner binaries drives chemically homogeneous evolution (CHE), entirely bypassing giant expansion. A subsequent triple common envelope (TCE) evolution, triggered by the tertiary companion, rapidly drives the inner BBH to coalescence. Our model can provide a detailed evolutionary pathway that elegantly reproduces the properties of these GWs, such as GW190706. Assuming a low-metallicity environment ($Z = 0.001$), our framework predicts a volumetric merger rate of approximately $0.011 \, \mathrm{Gpc}^{-3}\mathrm{yr}^{-1}$ at $z \approx 0.68$, accounting for $22\%$ of the empirical rate for this mass regime in the GWTC-4 catalog. This study demonstrates that primordial triple interactions are a highly efficient avenue for populating the PISN mass gap.

astro-ph.HE↗

arXiv2026

Attitude-Aided Linear Calibration of Triaxial Accelerometers

Triaxial MEMS accelerometers are widely used for inertial sensing, navigation, and sensor fusion, but existing calibration methods often rely on costly reference setups or nonlinear iterative optimization, limiting their efficiency and applicability to low-cost or self-calibrating systems. We present attitude-aided linear accelerometer calibration (ALAC), a method that operates on any platform providing orientation information, such as turntables, robotic arms, or inertial measurement units. ALAC constructs a combined error matrix (CEM) to represent sensor errors in a unified calibration model and enables linear least-squares estimation. The bias and gravity vector are jointly estimated, implicitly accounting for platform misalignment, and matrix decomposition of the CEM recovers scale, non-orthogonality, and alignment rotation parameters. Under static gravity, calibration is formulated as a constrained homogeneous least-squares (CHLS) problem and solved in closed form using standard linear algebra. Only five arbitrarily oriented measurements are required, and a recursive extension supports online or in-field calibration. Experiments on a stationary robot-mounted accelerometer and a quasi-static public IMU trajectory show that ALAC, in both offline and online modes, outperforms reference-based and online baselines in accuracy and robustness to sensor noise. On the same dataset, it matches iterative self-calibration under filtered conditions and surpasses all evaluated baselines on raw measurements. These results demonstrate a robust and practical calibration scheme for MEMS-based inertial platforms, especially low-cost IMUs and online calibration scenarios.

cs.RO↗

arXiv2026

CoSPlay: Cooperative Self-Play at Test-Time with Self-Generated Code and Unit Test

Recently, Reinforcement Learning with Verifiable Rewards (RLVR) and Test-Time Scaling (TTS) have advanced LLM code generation through executable verification. Yet Ground-Truth Unit Tests (GT UTs) remain a bottleneck: SOTA RLVR methods require them for costly training, while existing TTS methods lose competitiveness without them. This motivates GT-free TTS, where existing methods directly use self-generated UTs to refine and select code candidates. Yet such UTs are often noisy or spuriously coupled with wrong code, and UT quality in turn cannot be validated without reliable code. The key challenge is therefore to jointly improve both. To this end, we present CoSPlay, a GT-free, training-free framework that jointly improves codes and UTs through cooperative self-play. It first explores diverse solution ideas and identifies their potential failure modes to produce discriminative UT ideas. It then uses bidirectional pass-count signals from the Code-UT execution matrix to iteratively prune or fix weak codes and refresh or replace unreliable UTs, letting the two pools co-evolve. Finally, when multiple codes remain tied at the highest pass count, it picks the final code from the largest output-consensus cluster, since correct codes agree on the same inputs while wrong codes diverge. Experiments on four challenging benchmarks show that CoSPlay on Qwen2.5-7B-Instruct improves average BoN from 22.1% to 33.2% and UT accuracy from 14.6% to 78.3%, matching or surpassing the RLVR model CURE-7B. When applied to CURE-7B, it further improves BoN by 5.7%. CoSPlay also generalizes across diverse backbones and outperforms GT-free TTS baselines under comparable token budgets, with continued gains as the budget scales up. These results suggest a scalable inference strategy for competitive code generation without any GT data.

cs.LG↗

arXiv2026

LLM-Based Data Generation and Clinical Skills Evaluation for Low-Resource French OSCEs

Objective Structured Clinical Examinations (OSCEs) are the standard method for assessing medical students' clinical and communication skills through structured patient interviews. In France, however, the organization of training sessions is limited by human and logistical constraints, restricting students' access to repeated practice and structured feedback. Recent advances in Natural Language Processing (NLP) and Large Language Models (LLMs) now offer the opportunity to automatically evaluate such medical interviews, thereby alleviating the need for human examiners during training. Yet, real French OSCE annotated transcripts remain extremely scarce, limiting reproducible research and reliable benchmarking. To address these challenges, we investigate the use of LLMs for both generating and evaluating French OSCE dialogues in a low-resource context. We introduce a controlled pipeline that produces synthetic doctor-patient interview transcripts guided by scenario-specific evaluation criteria, combining ideal and perturbed performances to simulate varying student skill levels. The resulting dialogues are automatically silver-labeled through an LLM-assisted framework supporting adjustable evaluation strictness. Benchmarking multiple open-source and proprietary LLMs shows that mid-size models ($\le$32B parameters) achieve accuracies comparable to GPT-4o ($\sim$90\%) on synthetic data, highlighting the feasibility of locally deployable, privacy-preserving evaluation systems for medical education.

cs.CL↗

arXiv2025

First Results from HERA Phase II

We report the first upper limits on the power spectrum of 21-cm fluctuations during the Epoch of Reionization and Cosmic Dawn from Phase II of the Hydrogen Epoch of Reionization Array (HERA) experiment. HERA Phase II constitutes several significant improvements in the signal chain compared to Phase I, most notably resulting in expanded frequency bandwidth, from 50-250 MHz. In these first upper limits, we investigate a small two-week subset of the available Phase II observations, with a focus on identifying new systematic characteristics of the instrument, and establishing an analysis pipeline to account for them. We report 2$\sigma$ upper limits in eight spectral bands, spanning $5.6 \leq z \leq 24.4$ that are consistent with thermal noise at the $2\sigma$ level for $k \gtrsim 0.6-0.9 h{\rm Mpc}^{-1}$ (band dependent). Our tightest limit during Cosmic Dawn ($z>12$) is $1.13\times 10^6 {\rm mK}^2$ at ($k=0.55 h{\rm Mpc}^{-1}, z=16.78$), and during the EoR ($5.5<z<12$) it is $1.78\times 10^3 {\rm mK}^2$ at ($k=0.70 h{\rm Mpc}^{-1}, z=7.05$). We find that mutual coupling has become our dominant systematic, leaking foreground power that strongly contaminates the low-$k$ modes, resulting in the loss of modes from $k=0.35-0.55$ compared to Phase I data.

astro-ph.CO↗

arXiv2025

Is Quantum Optimization Ready? An Effort Towards Neural Network Compression using Adiabatic Quantum Computing

Quantum optimization is the most mature quantum computing technology to date, providing a promising approach towards efficiently solving complex combinatorial problems. Methods such as adiabatic quantum computing (AQC) have been employed in recent years on important optimization problems across various domains. In deep learning, deep neural networks (DNN) have reached immense sizes to support new predictive capabilities. Optimization of large-scale models is critical for sustainable deployment, but becomes increasingly challenging with ever-growing model sizes and complexity. While quantum optimization is suitable for solving complex problems, its application to DNN optimization is not straightforward, requiring thorough reformulation for compatibility with commercially available quantum devices. In this work, we explore the potential of adopting AQC for fine-grained pruning-quantization of convolutional neural networks. We rework established heuristics to formulate model compression as a quadratic unconstrained binary optimization (QUBO) problem, and assess the solution space offered by commercial quantum annealing devices. Through our exploratory efforts of reformulation, we demonstrate that AQC can achieve effective compression of practical DNN models. Experiments demonstrate that adiabatic quantum computing (AQC) not only outperforms classical algorithms like genetic algorithms and reinforcement learning in terms of time efficiency but also excels at identifying global optima.

quant-ph↗

arXiv2025

A demonstration of the effect of fringe-rate filtering in the Hydrogen Epoch of Reionization Array delay power spectrum pipeline

Radio interferometers targeting the 21cm brightness temperature fluctuations at high redshift are subject to systematic effects that operate over a range of different timescales. These can be isolated by designing appropriate Fourier filters that operate in fringe-rate (FR) space, the Fourier pair of local sidereal time (LST). Applications of FR filtering include separating effects that are correlated with the rotating sky vs. those relative to the ground, down-weighting emission in the primary beam sidelobes, and suppressing noise. FR filtering causes the noise contributions to the visibility data to become correlated in time however, making interpretation of subsequent averaging and error estimation steps more subtle. In this paper, we describe fringe rate filters that are implemented using discrete prolate spheroidal sequences, and designed for two different purposes -- beam sidelobe/horizon suppression (the `mainlobe' filter), and ground-locked systematics removal (the `notch' filter). We apply these to simulated data, and study how their properties affect visibilities and power spectra generated from the simulations. Included is an introduction to fringe-rate filtering and a demonstration of fringe-rate filters applied to simple situations to aid understanding.

astro-ph.CO↗

arXiv2025

Prompt2Task: Automating UI Tasks on Smartphones from Textual Prompts

UI task automation enables efficient task execution by simulating human interactions with graphical user interfaces (GUIs), without modifying the existing application code. However, its broader adoption is constrained by the need for expertise in both scripting languages and workflow design. To address this challenge, we present Prompt2Task, a system designed to comprehend various task-related textual prompts (e.g., goals, procedures), thereby generating and performing the corresponding automation tasks. Prompt2Task incorporates a suite of intelligent agents that mimic human cognitive functions, specializing in interpreting user intent, managing external information for task generation, and executing operations on smartphones. The agents can learn from user feedback and continuously improve their performance based on the accumulated knowledge. Experimental results indicated a performance jump from a 22.28\% success rate in the baseline to 95.24\% with Prompt2Task, requiring an average of 0.69 user interventions for each new task. Prompt2Task presents promising applications in fields such as tutorial creation, smart assistance, and customer service.

cs.HC↗

arXiv2025

Direct Preference-Based Evolutionary Multi-Objective Optimization with Dueling Bandit

Optimization problems find widespread use in both single-objective and multi-objective scenarios. In practical applications, users aspire for solutions that converge to the region of interest (ROI) along the Pareto front (PF). While the conventional approach involves approximating a fitness function or an objective function to reflect user preferences, this paper explores an alternative avenue. Specifically, we aim to discover a method that sidesteps the need for calculating the fitness function, relying solely on human feedback. Our proposed approach entails conducting direct preference learning facilitated by an active dueling bandit algorithm. The experimental phase is structured into three sessions. Firstly, we assess the performance of our active dueling bandit algorithm. Secondly, we implement our proposed method within the context of Multi-objective Evolutionary Algorithms (MOEAs). Finally, we deploy our method in a practical problem, specifically in protein structure prediction (PSP). This research presents a novel interactive preference-based MOEA framework that not only addresses the limitations of traditional techniques but also unveils new possibilities for optimization problems.

cs.AI↗

arXiv2025

Receiver design for the REACH global 21-cm signal experiment

We detail the the REACH radiometric system designed to enable measurements of the 21-cm neutral hydrogen line. Included is the radiometer architecture and end-to-end system simulations as well as a discussion of the challenges intrinsic to highly-calibratable system development. Following this, we share laboratory results based on the calculation of noise wave parameters utilising an over-constrained least squares approach demonstrating a calibration RMSE of 80 mK for five hours of integration on a custom-made source with comparable impedance to that of the antenna used in the field. This paper therefore documents the state of the calibrator and data analysis in December 2022 in Cambridge before shipping to South Africa.

astro-ph.IM↗

arXiv2025

matvis: A matrix-based visibility simulator for fast forward modelling of many-element 21 cm arrays

Detection of the faint 21 cm line emission from the Cosmic Dawn and Epoch of Reionisation will require not only exquisite control over instrumental calibration and systematics to achieve the necessary dynamic range of observations but also validation of analysis techniques to demonstrate their statistical properties and signal loss characteristics. A key ingredient in achieving this is the ability to perform high-fidelity simulations of the kinds of data that are produced by the large, many-element, radio interferometric arrays that have been purpose-built for these studies. The large scale of these arrays presents a computational challenge, as one must simulate a detailed sky and instrumental model across many hundreds of frequency channels, thousands of time samples, and tens of thousands of baselines for arrays with hundreds of antennas. In this paper, we present a fast matrix-based method for simulating radio interferometric measurements (visibilities) at the necessary scale. We achieve this through judicious use of primary beam interpolation, fast approximations for coordinate transforms, and a vectorised outer product to expand per-antenna quantities to per-baseline visibilities, coupled with standard parallelisation techniques. We validate the results of this method, implemented in the publicly-available matvis code, against a high-precision reference simulator, and explore its computational scaling on a variety of problems.

astro-ph.IM↗

arXiv2024

Hydrogen Epoch of Reionization Array (HERA) Phase II Deployment and Commissioning

This paper presents the design and deployment of the Hydrogen Epoch of Reionization Array (HERA) phase II system. HERA is designed as a staged experiment targeting 21 cm emission measurements of the Epoch of Reionization. First results from the phase I array are published as of early 2022, and deployment of the phase II system is nearing completion. We describe the design of the phase II system and discuss progress on commissioning and future upgrades. As HERA is a designated Square Kilometer Array (SKA) pathfinder instrument, we also show a number of "case studies" that investigate systematics seen while commissioning the phase II system, which may be of use in the design and operation of future arrays. Common pathologies are likely to manifest in similar ways across instruments, and many of these sources of contamination can be mitigated once the source is identified.

astro-ph.IM↗

arXiv2023

Spectral lens enables a minimalist framework for hyperspectral imaging

Conventional lens-based imaging techniques have long been limited to capturing only the intensity distribution of objects, resulting in the loss of other crucial dimensions such as spectral data. Here, we report a spectral lens that captures both spatial and spectral information, and further demonstrate a minimalist framework wherein hyperspectral imaging can be readily achieved by replacing lenses in standard cameras with our spectral lens. As a paradigm, we capitalize on planar liquid crystal optics to implement the proposed framework. Our experiments with various targets show that the resulting hyperspectral camera exhibits excellent performance in both spectral and spatial domains. With merits such as ultra-compactness and strong compatibility, our framework paves a practical pathway for advancing hyperspectral imaging apparatus toward miniaturization, with great potential for portable applications.

physics.optics↗

arXiv2023

DeepFire2: A Convolutional Spiking Neural Network Accelerator on FPGAs

Brain-inspired spiking neural networks (SNNs) replace the multiply-accumulate operations of traditional neural networks by integrate-and-fire neurons, with the goal of achieving greater energy efficiency. Specialized hardware implementations of those neurons clearly have advantages over general-purpose devices in terms of power and performance, but exhibit poor scalability when it comes to accelerating large neural networks. DeepFire2 introduces a hardware architecture which can map large network layers efficiently across multiple super logic regions in a multi-die FPGA. That gives more control over resource allocation and parallelism, benefiting both throughput and energy consumption. Avoiding the use of lookup tables to implement the AND operations of an SNN, prevents the layer size to be limited by logic resources. A deep pipeline does not only lead to an increased clock speed of up to 600 MHz. We double the throughput and power efficiency compared to our previous version of DeepFire, which equates to an almost 10-fold improvement over other previous implementations. Importantly, we are able to deploy a large ImageNet model, while maintaining a throughput of over 1500 frames per second.

cs.NE↗

arXiv2022

Benchmarking Quantum(-inspired) Annealing Hardware on Practical Use Cases

Quantum(-inspired) annealers show promise in solving combinatorial optimisation problems in practice. There has been extensive researches demonstrating the utility of D-Wave quantum annealer and quantum-inspired annealer, i.e., Fujitsu Digital Annealer on various applications, but few works are comparing these platforms. In this paper, we benchmark quantum(-inspired) annealers with three combinatorial optimisation problems ranging from generic scientific problems to complex problems in practical use. In the case where the problem size goes beyond the capacity of a quantum(-inspired) computer, we evaluate them in the context of decomposition. Experiments suggest that both annealers are effective on problems with small size and simple settings, but lose their utility when facing problems in practical size and settings. Decomposition methods extend the scalability of annealers, but they are still far away from practical use. Based on the experiments and comparison, we discuss the advantages and limitations of quantum(-inspired) annealers, as well as the research directions that may improve the utility and scalability of the these emerging computing technologies.

quant-ph↗

arXiv2022

Robust Motion Averaging for Multi-view Registration of Point Sets Based Maximum Correntropy Criterion

As an efficient algorithm to solve the multi-view registration problem,the motion averaging (MA) algorithm has been extensively studied and many MA-based algorithms have been introduced. They aim at recovering global motions from relative motions and exploiting information redundancy to average accumulative errors. However, one property of these methods is that they use Guass-Newton method to solve a least squares problem for the increment of global motions, which may lead to low efficiency and poor robustness to outliers. In this paper, we propose a novel motion averaging framework for the multi-view registration with Laplacian kernel-based maximum correntropy criterion (LMCC). Utilizing the Lie algebra motion framework and the correntropy measure, we propose a new cost function that takes all constraints supplied by relative motions into account. Obtaining the increment used to correct the global motions, can further be formulated as an optimization problem aimed at maximizing the cost function. By virtue of the quadratic technique, the optimization problem can be solved by dividing into two subproblems, i.e., computing the weight for each relative motion according to the current residuals and solving a second-order cone program problem (SOCP) for the increment in the next iteration. We also provide a novel strategy for determining the kernel width which ensures that our method can efficiently exploit information redundancy supplied by relative motions in the presence of many outliers. Finally, we compare the proposed method with other MA-based multi-view registration methods to verify its performance. Experimental tests on synthetic and real data demonstrate that our method achieves superior performance in terms of efficiency, accuracy and robustness.

cs.CV↗

arXiv2022

Automated Detection of Antenna Malfunctions in Large-N Interferometers: A Case Study with the Hydrogen Epoch of Reionization Array

We present a framework for identifying and flagging malfunctioning antennas in large radio interferometers. We outline two distinct categories of metrics designed to detect outliers along known failure modes of large arrays: cross-correlation metrics, based on all antenna pairs, and auto-correlation metrics, based solely on individual antennas. We define and motivate the statistical framework for all metrics used, and present tailored visualizations that aid us in clearly identifying new and existing systematics. We implement these techniques using data from 105 antennas in the Hydrogen Epoch of Reionization Array (HERA) as a case study. Finally, we provide a detailed algorithm for implementing these metrics as flagging tools on real data sets.

astro-ph.IM↗

arXiv2021

RCT: Resource Constrained Training for Edge AI

Neural networks training on edge terminals is essential for edge AI computing, which needs to be adaptive to evolving environment. Quantised models can efficiently run on edge devices, but existing training methods for these compact models are designed to run on powerful servers with abundant memory and energy budget. For example, quantisation-aware training (QAT) method involves two copies of model parameters, which is usually beyond the capacity of on-chip memory in edge devices. Data movement between off-chip and on-chip memory is energy demanding as well. The resource requirements are trivial for powerful servers, but critical for edge devices. To mitigate these issues, We propose Resource Constrained Training (RCT). RCT only keeps a quantised model throughout the training, so that the memory requirements for model parameters in training is reduced. It adjusts per-layer bitwidth dynamically in order to save energy when a model can learn effectively with lower precision. We carry out experiments with representative models and tasks in image application and natural language processing. Experiments show that RCT saves more than 86\% energy for General Matrix Multiply (GEMM) and saves more than 46\% memory for model parameters, with limited accuracy loss. Comparing with QAT-based method, RCT saves about half of energy on moving model parameters.

cs.LG↗