arXiv subjects

Yi Zhang

Publications and source records attributed to Yi Zhang.

At least 451 records · Page 25Linked to original sources

arXiv2025

A water Cherenkov detector prototype for future high-energy tau-neutrino experiment

The detection of high-energy tau neutrinos remains a critical challenge in neutrino astronomy, limited by inadequate angular resolution and sensitivity in current detectors like IceCube and KM3NeT. We present a modular water Cherenkov detector prototype optimized for tau-neutrino-induced extensive air showers (EAS) in the 1-100 PeV range, leveraging canyon terrain for natural cosmic-ray shielding. Laboratory validation demonstrates this prototype design has high detection efficiency (>99%) and timing resolution (<2 ns) on MIP particles, enabling precise tau-neutrino-induced EAS reconstruction for future study. The results establish a foundation of a low-cost, scalable neutrino observatory, advancing flavor ratio measurements and cosmic-ray origin problems.

astro-ph.HE↗

arXiv2025

On the Collapse Errors Induced by the Deterministic Sampler for Diffusion Models

Despite the widespread adoption of deterministic samplers in diffusion models (DMs), their potential limitations remain largely unexplored. In this paper, we identify collapse errors, a previously unrecognized phenomenon in ODE-based diffusion sampling, where the sampled data is overly concentrated in local data space. To quantify this effect, we introduce a novel metric and demonstrate that collapse errors occur across a variety of settings. When investigating its underlying causes, we observe a see-saw effect, where score learning in low noise regimes adversely impacts the one in high noise regimes. This misfitting in high noise regimes, coupled with the dynamics of deterministic samplers, ultimately causes collapse errors. Guided by these insights, we apply existing techniques from sampling, training, and architecture to empirically support our explanation of collapse errors. This work provides intensive empirical evidence of collapse errors in ODE-based diffusion sampling, emphasizing the need for further research into the interplay between score learning and deterministic sampling, an overlooked yet fundamental aspect of diffusion models.

cs.LG↗

arXiv2025

Contribution of Globular Clusters to Diffuse Gamma-ray Emission from Galactic Plane

The diffuse Galactic $γ$-ray emission (DGE) provides a valuable probe for investigating the cosmic ray propagation and interactions within our Galactic environment. Recent observations have demonstrated systematic excesses of DGE compared with the conventional cosmic-ray propagation model predictions. While $γ$-ray emissions have been detected in a subset of globular clusters, their undetected populations may significantly contribute to the DGE. Motivated by this possibility, we present a comprehensive assessment of potential contributions from unresolved globular clusters to the DGE. In our analysis, a nonparametric method is employed to estimate the luminosity function and spatial distribution function of globular clusters using the Fermi-LAT fourth source catalog (4FGL) combined with a reference globular cluster catalog. Based on these distributions, we calculate the cumulative contribution of unresolved globular cluster populations to the DGE observed by Fermi-LAT and the Large High Altitude Air Shower Observatory (LHAASO). Our results reveal that globular clusters account for only $\sim$2\% of the DGE at the TeV range, and smaller than $1\%$ in the GeV regime, which is effectively negligible.

astro-ph.HE↗

arXiv2025

A Novel Mutation Based Method for Detecting FPGA Logic Synthesis Tool Bugs

FPGA (Field-Programmable Gate Array) logic synthesis tools are key components in the EDA (Electronic Design Automation) toolchain. They convert hardware designs written in description languages such as Verilog into gate-level representations for FPGAs. However, defects in these tools may lead to unexpected behaviors and pose security risks. Therefore, it is crucial to harden these tools through testing. Although several methods have been proposed to automatically test FPGA logic synthesis tools, the challenge remains of insufficient semantic and logical complexity in test programs. In this paper, we propose VERMEI, a new method for testing FPGA logic synthesis tools. VERMEI consists of three modules: preprocessing, equivalent mutation, and bug identification. The preprocessing module identifies zombie logic (inactive code with no impact on the circuit output) in seed programs through simulation and coverage analysis. The equivalent mutation module generates equivalent variants of seed programs by pruning or inserting logic fragments in zombie areas. It uses Bayesian sampling to extract logic fragments from historical Verilog designs, making the generated variants have complex control flows and structures. The bug identification module, based on differential testing, compares the synthesized outputs of seed and variant programs to identify bugs. Experiments on Yosys, Vivado, and Quartus demonstrate that VERMEI outperforms the state-of-the-art methods. Within five months, VERMEI reported 15 bugs to vendors, 9 of which were confirmed as new.

cs.SE↗

arXiv2025

$V_{cb}$ puzzle in semi-leptonic $B\to D^*$ decays revisited

Inspired by the newly reported $B\to D^*(\to Dπ)\ell\barν_\ell$ differential decay rates by the Belle and Belle II Collaborations, we revisit the $V_{cb}$ puzzle in semi-leptonic $B\to D^*$ decays, considering the latest lattice QCD~(LQCD) simulations and light-cone sum rule~(LCSR) results. We examine the commonly used Caprini-Lellouch-Neubert~(CLN), Boyd-Grinstein-Lebed~(BGL), and heavy quark effective theory~(HQET) parameterizations. We demonstrate that these three parameterizations yield consistent results and reconfirm the $V_{cb}$ puzzle. Then, we use a state-of-the-art Bayesian method to estimate the impact of higher-order terms beyond the present HQET expansion on the uncertainty of $V_{cb}$. We show that higher-order effects cannot eliminate the deviation between the exclusive and inclusive determinations of $V_{cb}$. Finally, utilizing the best-fit results obtained in the HQET parameterization via fitting LQCD and LCSR data only as inputs, we predict the relevant observables, i.e., $R_{D^*}$, $F_L^{D^*}$, and $P_τ^{D^*}$, sensitive to new physics in the $B\to D^*\ell\barν_\ell$ decays. We conclude that lepton-flavour universality violations still exist in the $b\to cτν$.

hep-ph↗

arXiv2025

Spin-triplet pair density wave superconductors

Recent experiments have shown that the nonzero center of mass momentum pair density wave (PDW) is a widespread phenomenon observed over different superconducting materials. However, concrete theoretical model realizations of the PDW order have remained elusive. Here, we study a one-dimensional model with nearest-neighbor pairing attraction, i.e. a spinful Kitaev chain, under generic spin-orbit couplings such that the spin-rotation symmetry is fully broken. The most general superconducting order parameter is described by a spatial dependent $\mathbf{d}_i$-vector. We show that a spin-triplet pair density wave (t-PDW) emerges in the ground state and occupies a large part of the phase diagram. The $\mathbf{d_i}$-vector of the t-PDW rotates with a pitch $Q_{\rm pdw}$ along the chain and spans an ellipsoid. The pure t-PDW is fully gapped and realizes a class-DIII topological superconductor, characterized by two Majorana zero modes localized at each end of the chain and protected by time-reversal symmetry. Our findings reveal unprecedented insights into the exotic pure PDW superconductor and provide a possible explanation for the one-dimensional PDW detected along domain walls in monolayer iron-based superconductor Fe(Te,Se) and potentially realizable using other quantum structures in unconventional superconductors.

cond-mat.supr-con↗

arXiv2025

MM-Food-100K: A 100,000-Sample Multimodal Food Intelligence Dataset with Verifiable Provenance

We present MM-Food-100K, a public 100,000-sample multimodal food intelligence dataset with verifiable provenance. It is a curated approximately 10% open subset of an original 1.2 million, quality-accepted corpus of food images annotated for a wide range of information (such as dish name, region of creation). The corpus was collected over six weeks from over 87,000 contributors using the Codatta contribution model, which combines community sourcing with configurable AI-assisted quality checks; each submission is linked to a wallet address in a secure off-chain ledger for traceability, with a full on-chain protocol on the roadmap. We describe the schema, pipeline, and QA, and validate utility by fine-tuning large vision-language models (ChatGPT 5, ChatGPT OSS, Qwen-Max) on image-based nutrition prediction. Fine-tuning yields consistent gains over out-of-box baselines across standard metrics; we report results primarily on the MM-Food-100K subset. We release MM-Food-100K for publicly free access and retain approximately 90% for potential commercial access with revenue sharing to contributors.

cs.AI↗

arXiv2025

Optimizing LLM-Based Multi-Agent System with Textual Feedback: A Case Study on Software Development

We have seen remarkable progress in large language models (LLMs) empowered multi-agent systems solving complex tasks necessitating cooperation among experts with diverse skills. However, optimizing LLM-based multi-agent systems remains challenging. In this work, we perform an empirical case study on group optimization of role-based multi-agent systems utilizing natural language feedback for challenging software development tasks under various evaluation dimensions. We propose a two-step agent prompts optimization pipeline: identifying underperforming agents with their failure explanations utilizing textual feedback and then optimizing system prompts of identified agents utilizing failure explanations. We then study the impact of various optimization settings on system performance with two comparison groups: online against offline optimization and individual against group optimization. For group optimization, we study two prompting strategies: one-pass and multi-pass prompting optimizations. Overall, we demonstrate the effectiveness of our optimization method for role-based multi-agent systems tackling software development tasks evaluated on diverse evaluation dimensions, and we investigate the impact of diverse optimization settings on group behaviors of the multi-agent systems to provide practical insights for future development.

cs.AI↗

arXiv2025

All-optical temporal integration mediated by subwavelength heat antennas

Optical computing systems deliver unrivalled processing speeds for scalar operations. Yet, integrated implementations have been constrained to low-dimensional tensor operations that fall short of the vector dimensions required for modern artificial intelligence. We demonstrate an all-optical neuromorphic computing system based on time division multiplexing, capable of processing input vectors exceeding 250,000 elements within a unified framework. The platform harnesses optically driven thermo-optic modulation in standing wave optical fields, with titanium nano-antennas functioning as wavelength-selective absorbers. Counterintuitively, the thermal time dynamics of the system enable simultaneous time integration of ultra-fast (50GHz) signals and the application of programmable, non-linear activation functions, entirely within the optical domain. This unified framework constitutes a leap towards large-scale photonic computing that satisfies the dimensional requirements of AI workloads.

physics.optics↗

arXiv2025

GaussianCross: Cross-modal Self-supervised 3D Representation Learning via Gaussian Splatting

The significance of informative and robust point representations has been widely acknowledged for 3D scene understanding. Despite existing self-supervised pre-training counterparts demonstrating promising performance, the model collapse and structural information deficiency remain prevalent due to insufficient point discrimination difficulty, yielding unreliable expressions and suboptimal performance. In this paper, we present GaussianCross, a novel cross-modal self-supervised 3D representation learning architecture integrating feed-forward 3D Gaussian Splatting (3DGS) techniques to address current challenges. GaussianCross seamlessly converts scale-inconsistent 3D point clouds into a unified cuboid-normalized Gaussian representation without missing details, enabling stable and generalizable pre-training. Subsequently, a tri-attribute adaptive distillation splatting module is incorporated to construct a 3D feature field, facilitating synergetic feature capturing of appearance, geometry, and semantic cues to maintain cross-modal consistency. To validate GaussianCross, we perform extensive evaluations on various benchmarks, including ScanNet, ScanNet200, and S3DIS. In particular, GaussianCross shows a prominent parameter and data efficiency, achieving superior performance through linear probing (<0.1% parameters) and limited data training (1% of scenes) compared to state-of-the-art methods. Furthermore, GaussianCross demonstrates strong generalization capabilities, improving the full fine-tuning accuracy by 9.3% mIoU and 6.1% AP$_{50}$ on ScanNet200 semantic and instance segmentation tasks, respectively, supporting the effectiveness of our approach. The code, weights, and visualizations are publicly available at \href{https://rayyoh.github.io/GaussianCross/}{https://rayyoh.github.io/GaussianCross/}.

cs.CV↗

arXiv2025

MemInsight: Autonomous Memory Augmentation for LLM Agents

Large language model (LLM) agents have evolved to intelligently process information, make decisions, and interact with users or tools. A key capability is the integration of long-term memory capabilities, enabling these agents to draw upon historical interactions and knowledge. However, the growing memory size and need for semantic structuring pose significant challenges. In this work, we propose an autonomous memory augmentation approach, MemInsight, to enhance semantic data representation and retrieval mechanisms. By leveraging autonomous augmentation to historical interactions, LLM agents are shown to deliver more accurate and contextualized responses. We empirically validate the efficacy of our proposed approach in three task scenarios; conversational recommendation, question answering and event summarization. On the LLM-REDIAL dataset, MemInsight boosts persuasiveness of recommendations by up to 14%. Moreover, it outperforms a RAG baseline by 34% in recall for LoCoMo retrieval. Our empirical results show the potential of MemInsight to enhance the contextual performance of LLM agents across multiple tasks.

cs.CL↗

arXiv2025

A Unified Perception-Language-Action Framework for Adaptive Autonomous Driving

Autonomous driving systems face significant challenges in achieving human-like adaptability, robustness, and interpretability in complex, open-world environments. These challenges stem from fragmented architectures, limited generalization to novel scenarios, and insufficient semantic extraction from perception. To address these limitations, we propose a unified Perception-Language-Action (PLA) framework that integrates multi-sensor fusion (cameras, LiDAR, radar) with a large language model (LLM)-augmented Vision-Language-Action (VLA) architecture, specifically a GPT-4.1-powered reasoning core. This framework unifies low-level sensory processing with high-level contextual reasoning, tightly coupling perception with natural language-based semantic understanding and decision-making to enable context-aware, explainable, and safety-bounded autonomous driving. Evaluations on an urban intersection scenario with a construction zone demonstrate superior performance in trajectory tracking, speed prediction, and adaptive planning. The results highlight the potential of language-augmented cognitive frameworks for advancing the safety, interpretability, and scalability of autonomous driving systems.

cs.RO↗

arXiv2025

Efficient Real-Time Aircraft ETA Prediction via Feature Tokenization Transformer

Estimated time of arrival (ETA) for airborne aircraft in real-time is crucial for arrival management in aviation, particularly for runway sequencing. Given the rapidly changing airspace context, the ETA prediction efficiency is as important as its accuracy in a real-time arrival aircraft management system. In this study, we utilize a feature tokenization-based Transformer model to efficiently predict aircraft ETA. Feature tokenization projects raw inputs to latent spaces, while the multi-head self-attention mechanism in the Transformer captures important aspects of the projections, alleviating the need for complex feature engineering. Moreover, the Transformer's parallel computation capability allows it to handle ETA requests at a high frequency, i.e., 1HZ, which is essential for a real-time arrival management system. The model inputs include raw data, such as aircraft latitude, longitude, ground speed, theta degree for the airport, day and hour from track data, the weather context, and aircraft wake turbulence category. With a data sampling rate of 1HZ, the ETA prediction is updated every second. We apply the proposed aircraft ETA prediction approach to Singapore Changi Airport (ICAO Code: WSSS) using one-month Automatic Dependent Surveillance-Broadcast (ADS-B) data from October 1 to October 31, 2022. In the experimental evaluation, the ETA modeling covers all aircraft within a range of 10NM to 300NM from WSSS. The results show that our proposed method method outperforms the commonly used boosting tree based model, improving accuracy by 7\% compared to XGBoost, while requiring only 39\% of its computing time. Experimental results also indicate that, with 40 aircraft in the airspace at a given timestamp, the ETA inference time is only 51.7 microseconds, making it promising for real-time arrival management systems.

cs.LG↗

arXiv2025

A Wide-Input 0.25 um BCD LDO with Dual-Stage Amplifier and Active Ripple Cancellation for High PSRR and Fast Transient Response

Demand for on-chip low-dropout regulators (LDOs) with both high power-supply rejection ratio (PSRR) and fast transient response is growing as system-on-chip (SoC) integration increases. However, conventional LDO architectures face difficulty achieving these performance metrics simultaneously over wide input voltage ranges. This paper presents a wide-input linear regulator implemented in 0.25 um BCD technology that attains high PSRR and swift load-transient performance while maintaining low quiescent current. The proposed LDO employs a dual-stage error amplifier architecture and active ripple cancellation along both the power path and the error amplifier's supply to significantly enhance PSRR across frequency. An adaptive fast feedback branch together with an on-chip frequency compensation network is introduced to accelerate transient response without compromising stability. A two-stage PSRR analytical model and a three-frequency-band PSRR interpretation framework are developed to guide the design. Cadence Spectre simulations of the 14 V-output LDO demonstrate a -75 dB low-frequency PSRR, and during a 50 uA - 4 mA load step the output voltage droop is kept under 0.65 V with recovery within 16 us. These results validate the effectiveness of the proposed architecture and analysis, indicating that the design meets the stringent requirements of analog/RF SoCs and portable electronics.

physics.app-ph↗

arXiv2025

Authenticated Sublinear Quantum Private Information Retrieval

This paper introduces a novel lower bound on communication complexity using quantum relative entropy and mutual information, refining previous classical entropy-based results. By leveraging Uhlmann's lemma and quantum Pinsker inequalities, the authors establish tighter bounds for information-theoretic security, demonstrating that quantum protocols inherently outperform classical counterparts in balancing privacy and efficiency. Also explores symmetric Quantum Private Information Retrieval (QPIR) protocols that achieve sub-linear communication complexity while ensuring robustness against specious adversaries: A post-quantum cryptography based protocol that can be authenticated for the specious server; A ring-LWE-based protocol for post-quantum security in a single-server setting, ensuring robustness against quantum attacks; A multi-server protocol optimized for hardware practicality, reducing implementation overhead while maintaining sub-linear efficiency. These protocols address critical gaps in secure database queries, offering exponential communication improvements over classical linear-complexity methods. The work also analyzes security trade-offs under quantum specious adversaries, providing theoretical guarantees for privacy and correctness.

quant-ph↗

arXiv2025

End-to-end reconstruction of ultra-high energy particle observables from radio detection of extensive air showers

The radio detection of very inclined air showers offers a promising avenue for studying ultra-high-energy cosmic rays (UHECRs) and neutrinos. Accurate reconstruction methods are essential for investigating the properties of primary particles. Recently, we developed an analytical least-squares method to reconstruct the electric field using three polarization components. The reconstruction yields no bias, with a 68\% confidence interval of [-0.02, 0.02], and a standard deviation of 0.04. Using this reconstructed electric field, we perform a realistic reconstruction of the the properties of primary particles. We employ a spherical wave model combined with an angular distribution function (ADF) for arrival direction reconstruction, achieving an angular resolution of 0.04$^\circ$. This paper also presents an energy reconstruction in which we account for the effects of geosynchrotron radiation in inclined air showers, we implement an air density correction in the energy reconstruction, resulting in a 10\% resolution in energy estimation. These findings demonstrate the reliability and effectiveness of our reconstruction methodology, paving the way for future detection experiments using sparse antenna arrays.

astro-ph.IM↗

arXiv2025

Recurrent Inference Machine for Medical Image Registration

Image registration is essential for medical image applications where alignment of voxels across multiple images is needed for qualitative or quantitative analysis. With recent advancements in deep neural networks and parallel computing, deep learning-based medical image registration methods become competitive with their flexible modelling and fast inference capabilities. However, compared to traditional optimization-based registration methods, the speed advantage may come at the cost of registration performance at inference time. Besides, deep neural networks ideally demand large training datasets while optimization-based methods are training-free. To improve registration accuracy and data efficiency, we propose a novel image registration method, termed Recurrent Inference Image Registration (RIIR) network. RIIR is formulated as a meta-learning solver to the registration problem in an iterative manner. RIIR addresses the accuracy and data efficiency issues, by learning the update rule of optimization, with implicit regularization combined with explicit gradient input. We evaluated RIIR extensively on brain MRI and quantitative cardiac MRI datasets, in terms of both registration accuracy and training data efficiency. Our experiments showed that RIIR outperformed a range of deep learning-based methods, even with only $5\%$ of the training data, demonstrating high data efficiency. Key findings from our ablation studies highlighted the important added value of the hidden states introduced in the recurrent inference framework for meta-learning. Our proposed RIIR offers a highly data-efficient framework for deep learning-based medical image registration.

eess.IV↗

arXiv2025

Giant Reversible Piezoelectricity from Symmetry-Governed Stochastic Dipole Hopping

Organic--inorganic hybrid perovskites with giant piezoelectric responses, exemplified by TMCM-CdCl$_3$, represent a promising platform for flexible and environmentally friendly electromechanical materials. However, the microscopic origin of such exceptional performance in this weakly polar system has remained elusive. Here, using deep-learning-assisted large-scale molecular dynamics simulations, we resolve this paradox by reproducing the experimentally measured piezoelectric coefficient $d_{33} \approx 220$~pC/N, and demonstrating that the giant response arises from the collective contribution of multiple intrinsic components, particularly the shear component $d_{15}$. This effect does not stem from conventional polarization rotation or phase switching, but instead originates from stochastic 120$^\circ$ in-plane rotational hopping of a small fraction of organic cations. This discrete hopping mechanism is governed by the local C$_3$-symmetric halogen-bonding network between the host framework and the guest cation. The Arrhenius-type temperature dependence of $d_{15}$ further confirms the role of thermally activated dipole hopping. This work provides a clear pathway to enhance piezoelectric performance of hybrid materials through rational engineering of host--guest interactions.

cond-mat.mtrl-sci↗