arXiv subjects

Xinyu Shi

Publications and source records attributed to Xinyu Shi.

33 records · Page 2Linked to original sources

arXiv2025

Calibrating DRAMPower Model for HPC: A Runtime Perspective from Real-Time Measurements

Main memory's rising energy consumption has emerged as a critical challenge in modern computing architectures, particularly in large-scale systems, driven by frequent access patterns, growing data volumes, and insufficient power management strategies. Accurate modeling of DRAM power consumption is essential to address this challenge and optimize energy efficiency. However, existing modeling tools often rely on vendor-provided datasheet values that are obtained under worst-case or idealized conditions. As a result, they fail to capture important system-level factors, such as temperature variations, chip aging, and workload-induced variability, which leads to significant discrepancies between estimated and actual power consumption observed in real deployments. In this work, we propose a runtime calibration methodology for the DRAMPower model using energy measurements collected from real-system experiments. By applying custom memory benchmarks on an HPC cluster and leveraging fine-grained power monitoring infrastructure, we refine key current parameters (IDD values) in the model. Our calibration reduces the average energy estimation error to less than 5%, substantially improving modeling accuracy and making DRAMPower a more reliable tool for power-aware system design and optimization on the target server platform.

cs.AR↗

arXiv2025

BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent

Deep-Research agents, which integrate large language models (LLMs) with search tools, have shown success in improving the effectiveness of handling complex queries that require iterative search planning and reasoning over search results. Evaluations on current benchmarks like BrowseComp relies on black-box live web search APIs, have notable limitations in (1) fairness: dynamic and opaque web APIs hinder fair comparisons and reproducibility of deep research methods; (2) transparency: lack of control over the document corpus makes it difficult to isolate retriever contributions. In other words, the current evaluations may compare a complete deep research system at a given time, but they do not foster well-controlled experiments to provide insights into the capability of underlying deep research LLMs. To address these challenges, we introduce BrowseComp-Plus, a benchmark derived from BrowseComp, employing a fixed, carefully curated corpus. Each query in BrowseComp-Plus includes human-verified supporting documents and mined challenging negatives, enabling controlled experimentation. The benchmark is shown to be effective in distinguishing the performance of deep research systems. For instance, the open-source model Search-R1, when paired with the BM25 retriever, achieves 3.86% accuracy, whereas the GPT-5 achieves 55.9%. Integrating the GPT-5 with the Qwen3-Embedding-8B retriever further enhances its accuracy to 70.1% with fewer search calls. This benchmark allows comprehensive evaluation and disentangled analysis of deep research agents and retrieval methods, fostering insights into retrieval effectiveness, citation accuracy, and context engineering in Deep-Research system.

cs.CL↗

arXiv2025

Unleashing LLM Reasoning Capability via Scalable Question Synthesis from Scratch

Improving the mathematical reasoning capabilities of Large Language Models (LLMs) is critical for advancing artificial intelligence. However, access to extensive, diverse, and high-quality reasoning datasets remains a significant challenge, particularly for the open-source community. In this paper, we propose ScaleQuest, a novel, scalable, and cost-effective data synthesis method that enables the generation of large-scale mathematical reasoning datasets using lightweight 7B-scale models. ScaleQuest introduces a two-stage question-tuning process comprising Question Fine-Tuning (QFT) and Question Preference Optimization (QPO) to unlock the question generation capabilities of problem-solving models. By generating diverse questions from scratch -- without relying on powerful proprietary models or seed data -- we produce a dataset of 1 million problem-solution pairs. Our experiments demonstrate that models trained on our data outperform existing open-source datasets in both in-domain and out-of-domain evaluations. Furthermore, our approach shows continued performance improvement as the volume of training data increases, highlighting its potential for ongoing data scaling. The extensive improvements observed in code reasoning tasks demonstrate the generalization capabilities of our proposed method. Our work provides the open-source community with a practical solution to enhance the mathematical reasoning abilities of LLMs.

cs.CL↗

arXiv2025

NMR study of supersolid phases in the triangular-lattice antiferromagnet Na2BaCo(PO4)2

We report ultra-low-temperature $^{23}$Na NMR measurements on the Ising triangular lattice antiferromagnet Na$_2$BaCo(PO$_4$)$_2$, which precisely resolve the phase diagram under magnetic field applied along the crystalline $c$ axis. With increasing field, the NMR spectra resolve three ordered phases with distinct spin configurations: the Y, up-up-down (UUD), and V phases. The spin-lattice relaxation rate $1/T_1$ data demonstrate gapless excitations in the Y and V phases, strongly supporting their supersolid nature. However, the phase transitions from the UUD phase to the two supersolid phases exhibit dramatically different behaviors upon cooling. Prior to entering the Y phase, $1/T_1$ identifies a gapless regime within the UUD phase, suggesting a Berezinskii-Kosterlitz-Thouless phase above a second-order phase transition. In contrast, the coexistence of the UUD and V phases observed in our experiments provides direct evidence of a first-order phase transition between these phases.

cond-mat.str-el↗

arXiv2025

Towards High-performance Spiking Transformers from ANN to SNN Conversion

Spiking neural networks (SNNs) show great potential due to their energy efficiency, fast processing capabilities, and robustness. There are two main approaches to constructing SNNs. Direct training methods require much memory, while conversion methods offer a simpler and more efficient option. However, current conversion methods mainly focus on converting convolutional neural networks (CNNs) to SNNs. Converting Transformers to SNN is challenging because of the presence of non-linear modules. In this paper, we propose an Expectation Compensation Module to preserve the accuracy of the conversion. The core idea is to use information from the previous T time-steps to calculate the expected output at time-step T. We also propose a Multi-Threshold Neuron and the corresponding Parallel Parameter normalization to address the challenge of large time steps needed for high accuracy, aiming to reduce network latency and power consumption. Our experimental results demonstrate that our approach achieves state-of-the-art performance. For example, we achieve a top-1 accuracy of 88.60\% with only a 1\% loss in accuracy using 4 time steps while consuming only 35\% of the original power of the Transformer. To our knowledge, this is the first successful Artificial Neural Network (ANN) to SNN conversion for Spiking Transformers that achieves high accuracy, low latency, and low power consumption on complex datasets. The source codes of the proposed method are available at https://github.com/h-z-h-cell/Transformer-to-SNN-ECMT.

cs.CV↗

arXiv2025

Brickify: Enabling Expressive Design Intent Specification through Direct Manipulation on Design Tokens

Expressing design intent using natural language prompts requires designers to verbalize the ambiguous visual details concisely, which can be challenging or even impossible. To address this, we introduce Brickify, a visual-centric interaction paradigm -- expressing design intent through direct manipulation on design tokens. Brickify extracts visual elements (e.g., subject, style, and color) from reference images and converts them into interactive and reusable design tokens that can be directly manipulated (e.g., resize, group, link, etc.) to form the visual lexicon. The lexicon reflects users' intent for both what visual elements are desired and how to construct them into a whole. We developed Brickify to demonstrate how AI models can interpret and execute the visual lexicon through an end-to-end pipeline. In a user study, experienced designers found Brickify more efficient and intuitive than text-based prompts, allowing them to describe visual details, explore alternatives, and refine complex designs with greater ease and control.

cs.HC↗

arXiv2024

Deep Neural Network-Based Prediction of B-Cell Epitopes for SARS-CoV and SARS-CoV-2: Enhancing Vaccine Design through Machine Learning

The accurate prediction of B-cell epitopes is critical for guiding vaccine development against infectious diseases, including SARS and COVID-19. This study explores the use of a deep neural network (DNN) model to predict B-cell epitopes for SARS-CoVandSARS-CoV-2,leveraging a dataset that incorporates essential protein and peptide features. Traditional sequence-based methods often struggle with large, complex datasets, but deep learning offers promising improvements in predictive accuracy. Our model employs regularization techniques, such as dropout and early stopping, to enhance generalization, while also analyzing key features, including isoelectric point and aromaticity, that influence epitope recognition. Results indicate an overall accuracy of 82% in predicting COVID-19 negative and positive cases, with room for improvement in detecting positive samples. This research demonstrates the applicability of deep learning in epitope mapping, suggesting that such approaches can enhance the speed and precision of vaccine design for emerging pathogens. Future work could incorporate structural data and diverse viral strains to further refine prediction capabilities.

cs.LG↗

arXiv2024

Reinterpreting PID Controller From the Perspective of State Feedback and Lumped Disturbance Compensation

This paper analyzes the motion of solutions to non-homogeneous linear differential equations. It further clarifies that a proportional-integral-derivative (PID) controller essentially comprises two parts: a homogeneous controller and a disturbance observer, which are responsible for stabilizing the homogeneous system and compensating for the lumped disturbances (non-homogeneous components) of the system respectively. Based on this framework, the impact of measurement noise on control performance is examined, and a parameter tuning scheme for the traditional PID controller is provided. Finally, as examples, controllers are designed for two representative control problems: a trajectory tracking controller for an underactuated vertical takeoff and landing (VTOL) aircraft in the time domain, and a lateral controller for a vehicle in the distance domain.

eess.SY↗

arXiv2024

LM-HT SNN: Enhancing the Performance of SNN to ANN Counterpart through Learnable Multi-hierarchical Threshold Model

Compared to traditional Artificial Neural Network (ANN), Spiking Neural Network (SNN) has garnered widespread academic interest for its intrinsic ability to transmit information in a more energy-efficient manner. However, despite previous efforts to optimize the learning algorithm of SNNs through various methods, SNNs still lag behind ANNs in terms of performance. The recently proposed multi-threshold model provides more possibilities for further enhancing the learning capability of SNNs. In this paper, we rigorously analyze the relationship among the multi-threshold model, vanilla spiking model and quantized ANNs from a mathematical perspective, then propose a novel LM-HT model, which is an equidistant multi-threshold model that can dynamically regulate the global input current and membrane potential leakage on the time dimension. The LM-HT model can also be transformed into a vanilla single threshold model through reparameterization, thereby achieving more flexible hardware deployment. In addition, we note that the LM-HT model can seamlessly integrate with ANN-SNN Conversion framework under special initialization. This novel hybrid learning framework can effectively improve the relatively poor performance of converted SNNs under low time latency. Extensive experimental results have demonstrated that our model can outperform previous state-of-the-art works on various types of datasets, which promote SNNs to achieve a brand-new level of performance comparable to quantized ANNs. Code is available at https://github.com/hzc1208/LMHT_SNN.

cs.NE↗

arXiv2024

Low-energy spin dynamics in a Kitaev material Na3Ni2BiO6 investigated by NMR

We performed 23Na NMR and magnetization measurements on an S = 1, quasi-2D honeycomb lattice antiferromagnet Na3Ni2BiO6. A large positive Curie-Weiss constant of 22.9 K is observed. The NMR spectra at low fields are consistent with a "zigzag" magnetic order, indicating a large easy-axis anisotropy. With field applied along the c* axis, the NMR spectra confirm the existence of a 1/3-magnetization plateau phase between 5.1 T and 7.1 T. The transition from the zigzag order to the 1/3-magnetization plateau phase is also found to be a first-order type. A monotonic decrease of the spin gap is revealed in the 1/3-magnetization plateau phase, which reaches zero at a quantum critical field Hc = 8.35 T before entering the fully polarized phase. These data suggest the existence of exchange frustration in the system along with strong ferromagnetic interactions, hosting the possibility for Kitaev physics. Besides, well below the ordered phase, the 1/T1 at high fields shows either a level off or an enhancement upon cooling below 3 K, which suggests the existence of low-energy fluctuations.

cond-mat.str-el↗

arXiv2024

SpikingResformer: Bridging ResNet and Vision Transformer in Spiking Neural Networks

The remarkable success of Vision Transformers in Artificial Neural Networks (ANNs) has led to a growing interest in incorporating the self-attention mechanism and transformer-based architecture into Spiking Neural Networks (SNNs). While existing methods propose spiking self-attention mechanisms that are compatible with SNNs, they lack reasonable scaling methods, and the overall architectures proposed by these methods suffer from a bottleneck in effectively extracting local features. To address these challenges, we propose a novel spiking self-attention mechanism named Dual Spike Self-Attention (DSSA) with a reasonable scaling method. Based on DSSA, we propose a novel spiking Vision Transformer architecture called SpikingResformer, which combines the ResNet-based multi-stage architecture with our proposed DSSA to improve both performance and energy efficiency while reducing parameters. Experimental results show that SpikingResformer achieves higher accuracy with fewer parameters and lower energy consumption than other spiking Vision Transformer counterparts. Notably, our SpikingResformer-L achieves 79.40% top-1 accuracy on ImageNet with 4 time-steps, which is the state-of-the-art result in the SNN field.

cs.NE↗

arXiv2024

Piet: Facilitating Color Authoring for Motion Graphics Video

Motion graphic (MG) videos are effective and compelling for presenting complex concepts through animated visuals; and colors are important to convey desired emotions, maintain visual continuity, and signal narrative transitions. However, current video color authoring workflows are fragmented, lacking contextual previews, hindering rapid theme adjustments, and not aligning with progressive authoring flows of designers. To bridge this gap, we introduce Piet, the first tool tailored for MG video color authoring. Piet features an interactive palette to visually represent color distributions, support controllable focus levels, and enable quick theme probing via grouped color shifts. We interviewed 6 domain experts to identify the frustrations in current tools and inform the design of Piet. An in-lab user study with 13 expert designers showed that Piet effectively simplified the MG video color authoring and reduced the friction in creative color theme exploration.

cs.HC↗

arXiv2024

Exploring Interactive Color Palettes for Abstraction-Driven Exploratory Image Colorization

Color design is essential in areas such as product, graphic, and fashion design. However, current tools like Photoshop, with their concrete-driven color manipulation approach, often stumble during early ideation, favoring polished end results over initial exploration. We introduced Mondrian as a test-bed for abstraction-driven approach using interactive color palettes for image colorization. Through a formative study with six design experts, we selected three design options for visual abstractions in color design and developed Mondrian where humans work with abstractions and AI manages the concrete aspects. We carried out a user study to understand the benefits and challenges of each abstraction format and compare the Mondrian with Photoshop. A survey involving 100 participants further examined the influence of each abstraction format on color composition perceptions. Findings suggest that interactive visual abstractions encourage a non-linear exploration workflow and an open mindset during ideation, thus providing better creative affordance.

cs.HC↗

arXiv2022

Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentation

Research into Few-shot Semantic Segmentation (FSS) has attracted great attention, with the goal to segment target objects in a query image given only a few annotated support images of the target class. A key to this challenging task is to fully utilize the information in the support images by exploiting fine-grained correlations between the query and support images. However, most existing approaches either compressed the support information into a few class-wise prototypes, or used partial support information (e.g., only foreground) at the pixel level, causing non-negligible information loss. In this paper, we propose Dense pixel-wise Cross-query-and-support Attention weighted Mask Aggregation (DCAMA), where both foreground and background support information are fully exploited via multi-level pixel-wise correlations between paired query and support features. Implemented with the scaled dot-product attention in the Transformer architecture, DCAMA treats every query pixel as a token, computes its similarities with all support pixels, and predicts its segmentation label as an additive aggregation of all the support pixels' labels -- weighted by the similarities. Based on the unique formulation of DCAMA, we further propose efficient and effective one-pass inference for n-shot segmentation, where pixels of all support images are collected for the mask aggregation at once. Experiments show that our DCAMA significantly advances the state of the art on standard FSS benchmarks of PASCAL-5i, COCO-20i, and FSS-1000, e.g., with 3.1%, 9.7%, and 3.6% absolute improvements in 1-shot mIoU over previous best records. Ablative studies also verify the design DCAMA.

cs.CV↗

arXiv2022

Deformer: Towards Displacement Field Learning for Unsupervised Medical Image Registration

Recently, deep-learning-based approaches have been widely studied for deformable image registration task. However, most efforts directly map the composite image representation to spatial transformation through the convolutional neural network, ignoring its limited ability to capture spatial correspondence. On the other hand, Transformer can better characterize the spatial relationship with attention mechanism, its long-range dependency may be harmful to the registration task, where voxels with too large distances are unlikely to be corresponding pairs. In this study, we propose a novel Deformer module along with a multi-scale framework for the deformable image registration task. The Deformer module is designed to facilitate the mapping from image representation to spatial transformation by formulating the displacement vector prediction as the weighted summation of several bases. With the multi-scale framework to predict the displacement fields in a coarse-to-fine manner, superior performance can be achieved compared with traditional and learning-based approaches. Comprehensive experiments on two public datasets are conducted to demonstrate the effectiveness of the proposed Deformer module as well as the multi-scale framework.

eess.IV↗