arXiv subjects

Shaobo Li

Publications and source records attributed to Shaobo Li.

At least 19 recordsLinked to original sources

arXiv2026

Cross-View Sequential Visual Localization with Spatio-Temporal Context Modeling for Autonomous Driving

Continuous and reliable localization is essential for autonomous driving. Cross-view visual localization matches ground images with satellite maps, providing complementary localization cues for pipelines that depend on Global Navigation Satellite System (GNSS) signals and high-definition (HD) maps. Most existing cross-view visual localization methods process each frame independently, leaving temporal information underused and limiting accuracy under dynamic occlusion, illumination variation, and repetitive textures. This study proposes a temporal-context-enhanced framework for cross-view sequence visual localization. The proposed recurrent cross-frame module aggregates historical context from the previous state to enhance the coarse ground feature of each current frame. These enhanced features facilitate satellite candidate-region classification, while hierarchical fine-grained features enable precise local offset estimation. On the CVIS dataset, the proposed method reduces mean localization error from 3.80 m to 1.57 m and increases R@1 m from 8.14% to 40.22%. Direct transfer to KITTI-CVL achieves a mean error of 2.61 m, with target-domain fine-tuning further reducing the mean error to 2.27 m. Zero-shot field experiments on a real-world vehicle achieve a mean error of 2.84 m and R@5 m of 96.86%. These results demonstrate that temporal context enhancement significantly improves cross-view localization accuracy and supports robust deployment on public benchmarks and real-world roads.

cs.CV↗

arXiv2026

Benchmarking LLM Serving Systems for Agentic AI Workloads with XPerf

We present XPerf, a benchmarking framework that load-tests LLM serving systems with diverse agentic AI workloads. It provides detailed profiling of the serving system and hardware, enabling users to identify performance bottlenecks introduced by agentic workloads. Benchmarking LLM serving systems under agentic workloads is challenging - agentic applications rely on nondeterministic LLM outputs to guide their control flow; therefore, workload patterns vary unpredictably from run to run. XPerf minimizes this workload variation with a fine-grained trace replay approach: it enables users to easily collect traces from real agentic applications, synthesize new workloads with various patterns if needed, and reproducibly replay them on different LLM serving systems. XPerf includes eight agentic applications across diverse use cases (e.g., coding, deep research, and Q&A) by default. Our empirical study using these workloads shows that XPerf accurately replays agentic workloads, provides detailed performance breakdowns, scales to larger serving systems, and assists in serving system debugging. We will open-source XPerf on GitHub.

cs.DC↗

arXiv2026

MO-SAE:Multi-Objective Stacked Autoencoders Optimization for Edge Anomaly Detection

Stacked AutoEncoders (SAE) have been widely adopted in edge anomaly detection scenarios. However, the resource-intensive nature of SAE can pose significant challenges for edge devices, which are typically resource-constrained and must adapt rapidly to dynamic and changing conditions. Optimizing SAE to meet the heterogeneous demands of real-world deployment scenarios, including high performance under constrained storage, low power consumption, fast inference, and efficient model updates, remains a substantial challenge. To address this, we propose an integrated optimization framework that jointly considers these critical factors to achieve balanced and adaptive system-level optimization. Specifically, we formulate SAE optimization for edge anomaly detection as a multi-objective optimization problem and propose MO-SAE (Multi-Objective Stacked AutoEncoders). The multiple objectives are addressed by integrating model clipping, multi-branch exit design, and a matrix approximation technique. In addition, a multi-objective heuristic algorithm is employed to effectively balance the competing objectives in SAE optimization. Our results demonstrate that the proposed MO-SAE delivers substantial improvements over the original approach. On the x86 architecture, it reduces storage space and power consumption by at least 50%, improves runtime efficiency by no less than 28%, and achieves an 11.8% compression rate, all while maintaining application performance. Furthermore, MO-SAE runs efficiently on edge devices with ARM architecture. Experimental results show a 15% improvement in inference speed, facilitating efficient deployment in cloud-edge collaborative anomaly detection systems.

cs.NE↗

arXiv2026

RAGPerf: An End-to-End Benchmarking Framework for Retrieval-Augmented Generation Systems

We present the design and implementation of a RAG-based AI system benchmarking (RAGPerf) framework for characterizing the system behaviors of RAG pipelines. To facilitate detailed profiling and fine-grained performance analysis, RAGPerf decouples the RAG workflow into several modular components - embedding, indexing, retrieval, reranking, and generation. RAGPerf offers the flexibility for users to configure the core parameters of each component and examine their impact on the end-to-end query performance and quality. RAGPerf has a workload generator to model real-world scenarios by supporting diverse datasets (e.g., text, pdf, code, and audio), different retrieval and update ratios, and query distributions. RAGPerf also supports different embedding models, major vector databases such as LanceDB, Milvus, Qdrant, Chroma, and Elasticsearch, as well as different LLMs for content generation. It automates the collection of performance metrics (i.e., end-to-end query throughput, host/GPU memory footprint, and CPU/GPU utilization) and accuracy metrics (i.e., context recall, query accuracy, and factual consistency). We demonstrate the capabilities of RAGPerf through a comprehensive set of experiments and open source its codebase at GitHub. Our evaluation shows that RAGPerf incurs negligible performance overhead.

cs.PF↗

arXiv2025

Quantile Predictions for Equity Premium using Penalized Quantile Regression with Consistent Variable Selection across Multiple Quantiles

This paper considers equity premium prediction, for which mean regression can be problematic due to heteroscedasticity and heavy-tails of the error. We show advantages of quantile predictions using a novel penalized quantile regression that offers a model for a full spectrum analysis on the equity premium distribution. To enhance model interpretability and address the well-known issue of crossing quantile predictions in quantile regression, we propose a model that enforces the selection of a common set of variables across all quantiles. Such a selection consistency is achieved by simultaneously estimating all quantiles with a group penalty that ensures sparsity pattern is the same for all quantiles. Consistency results are provided that allow the number of predictors to increase with the sample size. A Huberized quantile loss function and an augmented data approach are implemented for computational efficiency. Simulation studies show the effectiveness of the proposed approach. Empirical results show that the proposed method outperforms several benchmark methods. Moreover, we find some important predictors reverse their relationship to the excess return from lower to upper quantiles, potentially offering interesting insights to the domain experts. Our proposed method can be applied to other fields.

stat.ME↗

arXiv2025

CDW-CoT: Clustered Distance-Weighted Chain-of-Thoughts Reasoning

Large Language Models (LLMs) have recently achieved impressive results in complex reasoning tasks through Chain of Thought (CoT) prompting. However, most existing CoT methods rely on using the same prompts, whether manually designed or automatically generated, to handle the entire dataset. This one-size-fits-all approach may fail to meet the specific needs arising from the diversities within a single dataset. To solve this problem, we propose the Clustered Distance-Weighted Chain of Thought (CDW-CoT) method, which dynamically constructs prompts tailored to the characteristics of each data instance by integrating clustering and prompt optimization techniques. Our method employs clustering algorithms to categorize the dataset into distinct groups, from which a candidate pool of prompts is selected to reflect the inherent diversity within the dataset. For each cluster, CDW-CoT trains the optimal prompt probability distribution tailored to their specific characteristics. Finally, it dynamically constructs a unique prompt probability distribution for each test instance, based on its proximity to cluster centers, from which prompts are selected for reasoning. CDW-CoT consistently outperforms traditional CoT methods across six datasets, including commonsense, symbolic, and mathematical reasoning tasks. Specifically, when compared to manual CoT, CDW-CoT achieves an average accuracy improvement of 25.34% on LLaMA2 (13B) and 15.72% on LLaMA3 (8B).

cs.LG↗

arXiv2025

SkyByte: Architecting an Efficient Memory-Semantic CXL-based SSD with OS and Hardware Co-design

The CXL-based solid-state drive (CXL-SSD) provides a promising approach towards scaling the main memory capacity at low cost. However, the CXL-SSD faces performance challenges due to the long flash access latency and unpredictable events such as garbage collection in the SSD device, stalling the host processor and wasting compute cycles. Although the CXL interface enables the byte-granular data access to the SSD, accessing flash chips is still at page granularity due to physical limitations. The mismatch of access granularity causes significant unnecessary I/O traffic to flash chips, worsening the suboptimal end-to-end data access performance. In this paper, we present SkyByte, an efficient CXL-based SSD that employs a holistic approach to address the aforementioned challenges by co-designing the host operating system (OS) and SSD controller. To alleviate the long memory stall when accessing the CXL-SSD, SkyByte revisits the OS context switch mechanism and enables opportunistic context switches upon the detection of long access delays. To accommodate byte-granular data accesses, SkyByte architects the internal DRAM of the SSD controller into a cacheline-level write log and a page-level data cache, and enables data coalescing upon log cleaning to reduce the I/O traffic to flash chips. SkyByte also employs optimization techniques that include adaptive page migration for exploring the performance benefits of fast host memory by promoting hot pages in CXL-SSD to the host. We implement SkyByte with a CXL-SSD simulator and evaluate its efficiency with various data-intensive applications. Our experiments show that SkyByte outperforms current CXL-based SSD by 6.11X, and reduces the I/O traffic to flash chips by 23.08X on average. SkyByte also reaches 75% of the performance of the ideal case that assumes unlimited DRAM capacity in the host, which offers an attractive cost-effective solution.

cs.AR↗

arXiv2025

ByteFS: System Support for (CXL-based) Memory-Semantic Solid-State Drives

Unlike non-volatile memory that resides on the processor memory bus, memory-semantic solid-state drives (SSDs) support both byte and block access granularity via PCIe or CXL interconnects. They provide scalable memory capacity using NAND flash at a much lower cost. In addition, they have different performance characteristics for their dual byte/block interface respectively, while offering essential memory semantics for upper-level software. Such a byte-accessible storage device provides new implications on the software system design. In this paper, we develop a new file system, named ByteFS, by rethinking the design primitives of file systems and SSD firmware to exploit the advantages of both byte and block-granular data accesses. ByteFS supports byte-granular data persistence to retain the persistence nature of SSDs. It extends the core data structure of file systems by enabling dual byte/block-granular data accesses. To facilitate the support for byte-granular writes, \pname{} manages the internal DRAM of SSD firmware in a log-structured manner and enables data coalescing to reduce the unnecessary I/O traffic to flash chips. ByteFS also enables coordinated data caching between the host page cache and SSD cache for best utilizing the precious memory resource. We implement ByteFS on both a real programmable SSD and an emulated memory-semantic SSD for sensitivity study. Compared to state-of-the-art file systems for non-volatile memory and conventional SSDs, ByteFS outperforms them by up to 2.7$\times$, while preserving the essential properties of a file system. ByteFS also reduces the write traffic to SSDs by up to 5.1$\times$ by alleviating unnecessary writes caused by both metadata and data updates in file systems.

cs.OS↗

arXiv2023

Long-Tailed Classification Based on Coarse-Grained Leading Forest and Multi-Center Loss

Long-tailed (LT) classification is an unavoidable and challenging problem in the real world. Most existing long-tailed classification methods focus only on solving the class-wise imbalance while ignoring the attribute-wise imbalance. The deviation of a classification model is caused by both class-wise and attribute-wise imbalance. Due to the fact that attributes are implicit in most datasets and the combination of attributes is complex, attribute-wise imbalance is more difficult to handle. For this purpose, we proposed a novel long-tailed classification framework, aiming to build a multi-granularity classification model by means of invariant feature learning. This method first unsupervisedly constructs Coarse-Grained forest (CLF) to better characterize the distribution of attributes within a class. Depending on the distribution of attributes, one can customize suitable sampling strategies to construct different imbalanced datasets. We then introduce multi-center loss (MCL) that aims to gradually eliminate confusing attributes during feature learning process. The proposed framework does not necessarily couple to a specific LT classification model structure and can be integrated with any existing LT method as an independent component. Extensive experiments show that our approach achieves state-of-the-art performance on both existing benchmarks ImageNet-GLT and MSCOCO-GLT and can improve the performance of existing LT methods. Our codes are available on GitHub: \url{https://github.com/jinyery/cognisance}

cs.CV↗

arXiv2023

Surrogate method for partial association between mixed data with application to well-being survey analysis

This paper is motivated by the analysis of a survey study of college student wellbeing before and after the outbreak of the COVID-19 pandemic. A statistical challenge in well-being survey studies lies in that outcome variables are often recorded in different scales, be it continuous, binary, or ordinal. The presence of mixed data complicates the assessment of the associations between them while adjusting for covariates. In our study, of particular interest are the associations between college students' wellbeing and other mental health measures and how other risk factors moderate these associations during the pandemic. To this end, we propose a unifying framework for studying partial association between mixed data. This is achieved by defining a unified residual using the surrogate method. The idea is to map the residual randomness to the same continuous scale, regardless of the original scales of outcome variables. It applies to virtually all commonly used models for covariate adjustments. We demonstrate the validity of using such defined residuals to assess partial association. In particular, we develop a measure that generalizes classical Kendall's tau in the sense that it can size both partial and marginal associations. More importantly, our development advances the theory of the surrogate method developed in recent years by showing that it can be used without requiring outcome variables having a latent variable structure. The use of our method in the well-being survey analysis reveals (i) significant moderation effects (i.e., the difference between partial and marginal associations) of some key risk factors; and (ii) an elevated moderation effect of physical health, loneliness, and accommodation after the onset of COVID-19.

stat.ME↗

arXiv2023

Group Equivariant BEV for 3D Object Detection

Recently, 3D object detection has attracted significant attention and achieved continuous improvement in real road scenarios. The environmental information is collected from a single sensor or multi-sensor fusion to detect interested objects. However, most of the current 3D object detection approaches focus on developing advanced network architectures to improve the detection precision of the object rather than considering the dynamic driving scenes, where data collected from sensors equipped in the vehicle contain various perturbation features. As a result, existing work cannot still tackle the perturbation issue. In order to solve this problem, we propose a group equivariant bird's eye view network (GeqBevNet) based on the group equivariant theory, which introduces the concept of group equivariant into the BEV fusion object detection network. The group equivariant network is embedded into the fused BEV feature map to facilitate the BEV-level rotational equivariant feature extraction, thus leading to lower average orientation error. In order to demonstrate the effectiveness of the GeqBevNet, the network is verified on the nuScenes validation dataset in which mAOE can be decreased to 0.325. Experimental results demonstrate that GeqBevNet can extract more rotational equivariant features in the 3D object detection of the actual road scene and improve the performance of object orientation prediction.

cs.CV↗

arXiv2023

Determinate Node Selection for Semi-supervised Classification Oriented Graph Convolutional Networks

Graph Convolutional Networks (GCNs) have been proved successful in the field of semi-supervised node classification by extracting structural information from graph data. However, the random selection of labeled nodes used by GCNs may lead to unstable generalization performance of GCNs. In this paper, we propose an efficient method for the deterministic selection of labeled nodes: the Determinate Node Selection (DNS) algorithm. The DNS algorithm identifies two categories of representative nodes in the graph: typical nodes and divergent nodes. These labeled nodes are selected by exploring the structure of the graph and determining the ability of the nodes to represent the distribution of data within the graph. The DNS algorithm can be applied quite simply on a wide range of semi-supervised graph neural network models for node classification tasks. Through extensive experimentation, we have demonstrated that the incorporation of the DNS algorithm leads to a remarkable improvement in the average accuracy of the model and a significant decrease in the standard deviation, as compared to the original method.

cs.LG↗

arXiv2022

LeaFTL: A Learning-Based Flash Translation Layer for Solid-State Drives

In modern solid-state drives (SSDs), the indexing of flash pages is a critical component in their storage controllers. It not only affects the data access performance, but also determines the efficiency of the precious in-device DRAM resource. A variety of address mapping schemes and optimization techniques have been proposed. However, most of them were developed with human-driven heuristics. They cannot automatically capture diverse data access patterns at runtime in SSD controllers, which leaves a large room for improvement. In this paper, we present a learning-based flash translation layer (FTL), named LeaFTL, which learns the address mapping to tolerate dynamic data access patterns via linear regression at runtime. By grouping a large set of mapping entries into a learned segment, it significantly reduces the memory footprint of the address mapping table, which further benefits the data caching in SSD controllers. LeaFTL also employs various optimization techniques, including out-of-band metadata verification to tolerate mispredictions, optimized flash allocation, and dynamic compaction of learned index segments. We implement LeaFTL with an SSD simulator and evaluate it with various storage workloads. LeaFTL saves the memory consumption of the mapping table by 2.9x on average and improves the storage performance by 1.4x on average, in comparison with state-of-the-art FTL schemes.

cs.OS↗

arXiv2022

Pre-training Language Models with Deterministic Factual Knowledge

Previous works show that Pre-trained Language Models (PLMs) can capture factual knowledge. However, some analyses reveal that PLMs fail to perform it robustly, e.g., being sensitive to the changes of prompts when extracting factual knowledge. To mitigate this issue, we propose to let PLMs learn the deterministic relationship between the remaining context and the masked content. The deterministic relationship ensures that the masked factual content can be deterministically inferable based on the existing clues in the context. That would provide more stable patterns for PLMs to capture factual knowledge than randomly masking. Two pre-training tasks are further introduced to motivate PLMs to rely on the deterministic relationship when filling masks. Specifically, we use an external Knowledge Base (KB) to identify deterministic relationships and continuously pre-train PLMs with the proposed methods. The factual knowledge probing experiments indicate that the continuously pre-trained PLMs achieve better robustness in factual knowledge capturing. Further experiments on question-answering datasets show that trying to learn a deterministic relationship with the proposed methods can also help other knowledge-intensive tasks.

cs.CL↗

arXiv2022

Semi-supervised Learning with Deterministic Labeling and Large Margin Projection

The centrality and diversity of the labeled data are very influential to the performance of semi-supervised learning (SSL), but most SSL models select the labeled data randomly. This study first construct a leading forest that forms a partially ordered topological space in an unsupervised way, and select a group of most representative samples to label with one shot (differs from active learning essentially) using property of homeomorphism. Then a kernelized large margin metric is efficiently learned for the selected data to classify the remaining unlabeled sample. Optimal leading forest (OLF) has been observed to have the advantage of revealing the difference evolution along a path within a subtree. Therefore, we formulate an optimization problem based on OLF to select the samples. Also with OLF, the multiple local metrics learning is facilitated to address multi-modal and mix-modal problem in SSL, especially when the number of class is large. Attribute to this novel design, stableness and accuracy of the performance is significantly improved when compared with the state-of-the-art graph SSL methods. The extensive experimental studies have shown that the proposed method achieved encouraging accuracy and efficiency. Code has been made available at https://github.com/alanxuji/DeLaLA.

cs.AI↗

arXiv2022

The Security War in File Systems: An Empirical Study from A Vulnerability-Centric Perspective

This paper presents a systematic study on the security of modern file systems, following a vulnerability-centric perspective. Specifically, we collected 377 file system vulnerabilities committed to the CVE database in the past 20 years. We characterize them from four dimensions that include why the vulnerabilities appear, how the vulnerabilities can be exploited, what consequences can arise, and how the vulnerabilities are fixed. This way, we build a deep understanding of the attack surfaces faced by file systems, the threats imposed by the attack surfaces, and the good and bad practices in mitigating the attacks in file systems. We envision that our study will bring insights towards the future development of file systems, the enhancement of file system security, and the relevant vulnerability mitigating solutions.

cs.CR↗

arXiv2022

How Pre-trained Language Models Capture Factual Knowledge? A Causal-Inspired Analysis

Recently, there has been a trend to investigate the factual knowledge captured by Pre-trained Language Models (PLMs). Many works show the PLMs' ability to fill in the missing factual words in cloze-style prompts such as "Dante was born in [MASK]." However, it is still a mystery how PLMs generate the results correctly: relying on effective clues or shortcut patterns? We try to answer this question by a causal-inspired analysis that quantitatively measures and evaluates the word-level patterns that PLMs depend on to generate the missing words. We check the words that have three typical associations with the missing words: knowledge-dependent, positionally close, and highly co-occurred. Our analysis shows: (1) PLMs generate the missing factual words more by the positionally close and highly co-occurred words than the knowledge-dependent words; (2) the dependence on the knowledge-dependent words is more effective than the positionally close and highly co-occurred words. Accordingly, we conclude that the PLMs capture the factual knowledge ineffectively because of depending on the inadequate associations.

cs.CL↗

arXiv2021

Quantum emitter formation in carbon-doped monolayer hexagonal boron nitride

Single photon emitters (SPEs) in hexagonal boron nitride (hBN) are promising candidates for quantum light generation. Despite this, techniques to control the formation of hBN SPEs down to the monolayer limit are yet to be demonstrated. Recent experimental and theoretical investigations have suggested that the visible wavelength single photon emitters in hBN originate from carbon-related defects. Here we demonstrate a simple strategy for controlling SPE creation during the chemical vapor deposition growth of monolayer hBN via regulating surface carbon concentration. By increasing surface carbon concentration during hBN growth, we observe increases in carbon doping levels by 2.4 fold for B-C bonds and 1.6 fold for N-C bonds. For the same samples we observe an increase in SPE density from 0.13 to 0.30 emitters/um2. Our simple method enables the reliable creation of hBN SPEs in monolayer samples for the first time, opening the door to advanced 2D quantum state engineering.

cond-mat.mtrl-sci↗