arXiv subjects

Jianbo Li

Publications and source records attributed to Jianbo Li.

At least 19 recordsLinked to original sources

arXiv2026

OptiSet: Unified Optimizing Set Selection and Ranking for Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) improves generation quality by incorporating evidence retrieved from large external corpora. However, most existing methods rely on statically selecting top-k passages based on individual relevance, which fails to exploit combinatorial gains among passages and often introduces substantial redundancy. To address this limitation, we propose OptiSet, a set-centric framework that unifies set selection and set-level ranking for RAG. OptiSet adopts an "Expand-then-Refine" paradigm: it first expands a query into multiple perspectives to enable a diverse candidate pool and then refines the candidate pool via re-selection to form a compact evidence set. We then devise a self-synthesis strategy without strong LLM supervision to derive preference labels from the set conditional utility changes of the generator, thereby identifying complementary and redundant evidence. Finally, we introduce a set-list wise training strategy that jointly optimizes set selection and set-level ranking, enabling the model to favor compact, high-gain evidence sets. Extensive experiments demonstrate that OptiSet improves performance on complex combinatorial problems and makes generation more efficient. The source code is publicly available.

cs.AI↗

arXiv2026

ArcAligner: Adaptive Recursive Aligner for Compressed Context Embeddings in RAG

Retrieval-Augmented Generation (RAG) helps LLMs stay accurate, but feeding long documents into a prompt makes the model slow and expensive. This has motivated context compression, ranging from token pruning and summarization to embedding-based compression. While researchers have tried ''compressing'' these documents into smaller summaries or mathematical embeddings, there is a catch: the more you compress the data, the more the LLM struggles to understand it. To address this challenge, we propose ArcAligner (Adaptive recursive context *Aligner*), a lightweight module integrated into the language model layers to help the model better utilize highly compressed context representations for downstream generation. It uses an adaptive ''gating'' system that only adds extra processing power when the information is complex, keeping the system fast. Across knowledge-intensive QA benchmarks, ArcAligner consistently beats compression baselines at comparable compression rates, especially on multi-hop and long-tail settings. The source code is publicly available.

cs.CL↗

arXiv2025

CoCoA: Collaborative Chain-of-Agents for Parametric-Retrieved Knowledge Synergy

Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs), especially for knowledge-intensive tasks. Despite its advantages, current RAG methods often struggle to fully exploit knowledge during generation. In particular, the synergy between the model's internal parametric knowledge and external retrieved knowledge remains limited. Retrieved contents may sometimes mislead generation, while certain generated content can guide the model toward more accurate outputs. In this work, we propose Collaborative Chain-of-Agents, a framework designed to enhance explicitly synergy over both parametric and retrieved knowledge. Specifically, we first introduce CoCoA-zero, a multi-agent RAG framework that first performs conditional knowledge induction and then reasons answers. Building on this, we develop CoCoA, a long-chain training strategy that synthesizes extended multi-agent reasoning trajectories from CoCoA-zero to fine-tune the LLM. This strategy enhances the model's capability to explicitly integrate and jointly leverage parametric and retrieved knowledge. Experimental results demonstrate the superiority of CoCoA in open-domain QA and multi-hop QA.

cs.CL↗

arXiv2025

Modulated differentiable STFT and balanced spectrum metric for freight train wheelset bearing cross-machine transfer monitoring under speed fluctuations

The service conditions of wheelset bearings has a direct impact on the safe operation of railway heavy haul freight trains as the key components. However, speed fluctuation of the trains and few fault samples are the two main problems that restrict the accuracy of bearing fault diagnosis. Therefore, a cross-machine transfer diagnosis (pyDSN) network coupled with interpretable modulated differentiable short-time Fourier transform (STFT) and physics-informed balanced spectrum quality metric is proposed to learn domain-invariant and discriminative features under time-varying speeds. Firstly, due to insufficiency in extracting extract frequency components of time-varying speed signals using fixed windows, a modulated differentiable STFT (MDSTFT) that is interpretable with STFT-informed theoretical support, is proposed to extract the robust time-frequency spectrum (TFS). During training process, multiple windows with different lengths dynamically change. Also, in addition to the classification metric and domain discrepancy metric, we creatively introduce a third kind of metric, referred to as the physics-informed metric, to enhance transferable TFS. A physics-informed balanced spectrum quality (BSQ) regularization loss is devised to guide an optimization direction for MDSTFT and model. With it, not only can model acquire high-quality TFS, but also a physics-restricted domain adaptation network can be also acquired, making it learn real-world physics knowledge, ultimately diminish the domain discrepancy across different datasets. The experiment is conducted in the scenario of migrating from the laboratory datasets to the freight train dataset, indicating that the hybrid-driven pyDSN outperforms existing methods and has practical value.

cs.LG↗

arXiv2025

GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal Synthesis

The Retrieval-Augmented Generation (RAG) framework introduces a retrieval module to dynamically inject retrieved information into the input context of large language models (LLMs), and has demonstrated significant success in various NLP tasks. However, the current study points out that there is a preference gap between retrievers and LLMs in the RAG framework, which limit the further improvement of system performance. Some highly relevant passages may interfere with LLM reasoning because they contain complex or contradictory information; while some indirectly related or even inaccurate content may help LLM generate more accurate answers by providing suggestive information or logical clues. To solve this, we propose GainRAG, a novel approach that aligns the retriever's and LLM's preferences by defining a new metric, "gain", which measure how well an input passage contributes to correct outputs. Specifically, we propose a method to estimate these gain signals and train a middleware that aligns the preferences of the retriever and the LLM using only limited data. In addition, we introduce a pseudo-passage strategy to mitigate degradation. The experimental results on 6 datasets verify the effectiveness of GainRAG.

cs.IR↗

arXiv2024

TASER: Temporal Adaptive Sampling for Fast and Accurate Dynamic Graph Representation Learning

Recently, Temporal Graph Neural Networks (TGNNs) have demonstrated state-of-the-art performance in various high-impact applications, including fraud detection and content recommendation. Despite the success of TGNNs, they are prone to the prevalent noise found in real-world dynamic graphs like time-deprecated links and skewed interaction distribution. The noise causes two critical issues that significantly compromise the accuracy of TGNNs: (1) models are supervised by inferior interactions, and (2) noisy input induces high variance in the aggregated messages. However, current TGNN denoising techniques do not consider the diverse and dynamic noise pattern of each node. In addition, they also suffer from the excessive mini-batch generation overheads caused by traversing more neighbors. We believe the remedy for fast and accurate TGNNs lies in temporal adaptive sampling. In this work, we propose TASER, the first adaptive sampling method for TGNNs optimized for accuracy, efficiency, and scalability. TASER adapts its mini-batch selection based on training dynamics and temporal neighbor selection based on the contextual, structural, and temporal properties of past interactions. To alleviate the bottleneck in mini-batch generation, TASER implements a pure GPU-based temporal neighbor finder and a dedicated GPU feature cache. We evaluate the performance of TASER using two state-of-the-art backbone TGNNs. On five popular datasets, TASER outperforms the corresponding baselines by an average of 2.3% in Mean Reciprocal Rank (MRR) while achieving an average of 5.1x speedup in training time.

cs.LG↗

arXiv2023

Object Detection for Caries or Pit and Fissure Sealing Requirement in Children's First Permanent Molars

Dental caries is one of the most common oral diseases that, if left untreated, can lead to a variety of oral problems. It mainly occurs inside the pits and fissures on the occlusal/buccal/palatal surfaces of molars and children are a high-risk group for pit and fissure caries in permanent molars. Pit and fissure sealing is one of the most effective methods that is widely used in prevention of pit and fissure caries. However, current detection of pits and fissures or caries depends primarily on the experienced dentists, which ordinary parents do not have, and children may miss the remedial treatment without timely detection. To address this issue, we present a method to autodetect caries and pit and fissure sealing requirements using oral photos taken by smartphones. We use the YOLOv5 and YOLOX models and adopt a tiling strategy to reduce information loss during image pre-processing. The best result for YOLOXs model with tiling strategy is 72.3 mAP.5, while the best result without tiling strategy is 71.2. YOLOv5s6 model with/without tiling attains 70.9/67.9 mAP.5, respectively. We deploy the pre-trained network to mobile devices as a WeChat applet, allowing in-home detection by parents or children guardian.

eess.IV↗

arXiv2021

Backscatter Sensors Communication for 6G Low-powered NOMA-enabled IoT Networks under Imperfect SIC

The combination of non-orthogonal multiple access (NOMA) using power-domain with backscatter sensor communication (BSC) is expected to connect a large-scale Internet of things (IoT) devices in future sixth-generation (6G) era. In this paper, we introduce a BSC in multi-cell IoT network, where a source in each cell transmits superimposed signal to its associated IoT devices using NOMA. The backscatter sensor tag (BST) also transmit data towards IoT devices by reflecting and modulating the superimposed signal of the source. A new optimization framework is provided that simultaneously optimizes the total power of each source, power allocation coefficient of IoT devices and reflection coefficient of BST under imperfect successive interference cancellation decoding. The objective of this work is to maximize the total energy efficiency of IoT network subject to quality of services of each IoT device. The problem is first transformed using the Dinkelbach method and then decoupled into two subproblems. The Karush-Kuhn-Tucker conditions and Lagrangian dual method are employed to obtain the efficient solutions. In addition, we also present the conventional NOMA network without BSC as a benchmark framework. Simulation results unveil the advantage of our considered NOMA BSC networks over the conventional NOMA network.

eess.SP↗

arXiv2021

An open-source ABAQUS implementation of the scaled boundary finite element method to study interfacial problems using polyhedral meshes

The scaled boundary finite element method (SBFEM) is capable of generating polyhedral elements with an arbitrary number of surfaces. This salient feature significantly alleviates the meshing burden being a bottleneck in the analysis pipeline in the standard finite element method (FEM). In this paper, we implement polyhedral elements based on the SBFEM into the commercial finite element software ABAQUS. To this end, user elements are provided through the user subroutine UEL. Detailed explanations regarding the data structures and implementational aspects of the procedures are given. The focus of the current implementation is on interfacial problems and therefore, element-based surfaces are created on polyhedral user elements to establish interactions. This is achieved by an overlay of standard finite elements with negligible stiffness, provided in the ABAQUS element library, with polyhedral user elements. By means of several numerical examples, the advantages of polyhedral elements regarding the treatment of non-matching interfaces and automatic mesh generation are clearly demonstrated. Thus, the performance of ABAQUS for problems involving interfaces is augmented based on the availability of polyhedral meshes. Due to the implementation of polyhedral user elements, ABAQUS can directly handle complex geometries given in the form of digital images or stereolithography (STL) files. In order to facilitate the use of the proposed approach, the code of the UEL is published open-source and can be downloaded from https://github.com/ShukaiYa/SBFEM-UEL.

cs.MS↗

arXiv2021

Associated Spatio-Temporal Capsule Network for Gait Recognition

It is a challenging task to identify a person based on her/his gait patterns. State-of-the-art approaches rely on the analysis of temporal or spatial characteristics of gait, and gait recognition is usually performed on single modality data (such as images, skeleton joint coordinates, or force signals). Evidence has shown that using multi-modality data is more conducive to gait research. Therefore, we here establish an automated learning system, with an associated spatio-temporal capsule network (ASTCapsNet) trained on multi-sensor datasets, to analyze multimodal information for gait recognition. Specifically, we first design a low-level feature extractor and a high-level feature extractor for spatio-temporal feature extraction of gait with a novel recurrent memory unit and a relationship layer. Subsequently, a Bayesian model is employed for the decision-making of class labels. Extensive experiments on several public datasets (normal and abnormal gait) validate the effectiveness of the proposed ASTCapsNet, compared against several state-of-the-art methods.

cs.CV↗

arXiv2021

Multimodal Gait Recognition for Neurodegenerative Diseases

In recent years, single modality based gait recognition has been extensively explored in the analysis of medical images or other sensory data, and it is recognised that each of the established approaches has different strengths and weaknesses. As an important motor symptom, gait disturbance is usually used for diagnosis and evaluation of diseases; moreover, the use of multi-modality analysis of the patient's walking pattern compensates for the one-sidedness of single modality gait recognition methods that only learn gait changes in a single measurement dimension. The fusion of multiple measurement resources has demonstrated promising performance in the identification of gait patterns associated with individual diseases. In this paper, as a useful tool, we propose a novel hybrid model to learn the gait differences between three neurodegenerative diseases, between patients with different severity levels of Parkinson's disease and between healthy individuals and patients, by fusing and aggregating data from multiple sensors. A spatial feature extractor (SFE) is applied to generating representative features of images or signals. In order to capture temporal information from the two modality data, a new correlative memory neural network (CorrMNN) architecture is designed for extracting temporal features. Afterwards, we embed a multi-switch discriminator to associate the observations with individual state estimations. Compared with several state-of-the-art techniques, our proposed framework shows more accurate classification results.

cs.CV↗

arXiv2020

Collaborative City Digital Twin For Covid-19 Pandemic: A Federated Learning Solution

In this work, we propose a collaborative city digital twin based on FL, a novel paradigm that allowing multiple city DT to share the local strategy and status in a timely manner. In particular, an FL central server manages the local updates of multiple collaborators (city DT), provides a global model which is trained in multiple iterations at different city DT systems, until the model gains the correlations between various response plan and infection trend. That means, a collaborative city DT paradigm based on FL techniques can obtain knowledge and patterns from multiple DTs, and eventually establish a `global view' for city crisis management. Meanwhile, it also helps to improve each city digital twin selves by consolidating other DT's respective data without violating privacy rules. To validate the proposed solution, we take COVID-19 pandemic as a case study. The experimental results on the real dataset with various response plan validate our proposed solution and demonstrate the superior performance.

cs.LG↗

arXiv2020

Search What You Want: Barrier Panelty NAS for Mixed Precision Quantization

Emergent hardwares can support mixed precision CNN models inference that assign different bitwidths for different layers. Learning to find an optimal mixed precision model that can preserve accuracy and satisfy the specific constraints on model size and computation is extremely challenge due to the difficult in training a mixed precision model and the huge space of all possible bit quantizations. In this paper, we propose a novel soft Barrier Penalty based NAS (BP-NAS) for mixed precision quantization, which ensures all the searched models are inside the valid domain defined by the complexity constraint, thus could return an optimal model under the given constraint by conducting search only one time. The proposed soft Barrier Penalty is differentiable and can impose very large losses to those models outside the valid domain while almost no punishment for models inside the valid domain, thus constraining the search only in the feasible domain. In addition, a differentiable Prob-1 regularizer is proposed to ensure learning with NAS is reasonable. A distribution reshaping training strategy is also used to make training more stable. BP-NAS sets new state of the arts on both classification (Cifar-10, ImageNet) and detection (COCO), surpassing all the efficient mixed precision methods designed manually and automatically. Particularly, BP-NAS achieves higher mAP (up to 2.7\% mAP improvement) together with lower bit computation cost compared with the existing best mixed precision model on COCO detection.

cs.CV↗

arXiv2019

PAGAN: Portfolio Analysis with Generative Adversarial Networks

Since decades, the data science community tries to propose prediction models of financial time series. Yet, driven by the rapid development of information technology and machine intelligence, the velocity of today's information leads to high market efficiency. Sound financial theories demonstrate that in an efficient marketplace all information available today, including expectations on future events, are represented in today prices whereas future price trend is driven by the uncertainty. This jeopardizes the efforts put in designing prediction models. To deal with the unpredictability of financial systems, today's portfolio management is largely based on the Markowitz framework which puts more emphasis in the analysis of the market uncertainty and less in the price prediction. The limitation of the Markowitz framework stands in taking very strong ideal assumptions about future returns probability distribution. To address this situation we propose PAGAN, a pioneering methodology based on deep generative models. The goal is modeling the market uncertainty that ultimately is the main factor driving future trends. The generative model learns the joint probability distribution of price trends for a set of financial assets to match the probability distribution of the real market. Once the model is trained, a portfolio is optimized by deciding the best diversification to minimize the risk and maximize the expected returns observed over the execution of several simulations. Applying the model for analyzing possible futures, is as simple as executing a Monte Carlo simulation, a technique very familiar to finance experts. The experimental results on different portfolios representing different geopolitical areas and industrial segments constructed using real-world public data sets demonstrate promising results.

q-fin.CP↗

arXiv2019

RES-PCA: A Scalable Approach to Recovering Low-rank Matrices

Robust principal component analysis (RPCA) has drawn significant attentions due to its powerful capability in recovering low-rank matrices as well as successful appplications in various real world problems. The current state-of-the-art algorithms usually need to solve singular value decomposition of large matrices, which generally has at least a quadratic or even cubic complexity. This drawback has limited the application of RPCA in solving real world problems. To combat this drawback, in this paper we propose a new type of RPCA method, RES-PCA, which is linearly efficient and scalable in both data size and dimension. For comparison purpose, AltProj, an existing scalable approach to RPCA requires the precise knowlwdge of the true rank; otherwise, it may fail to recover low-rank matrices. By contrast, our method works with or without knowing the true rank; even when both methods work, our method is faster. Extensive experiments have been performed and testified to the effectiveness of proposed method quantitatively and in visual quality, which suggests that our method is suitable to be employed as a light-weight, scalable component for RPCA in any application pipelines.

cs.LG↗

arXiv2017

MPAR: A Movement Pattern-Aware Optimal Routing for Social Delay Tolerant Networks

Social Delay Tolerant Networks (SDTNs) are a special kind of Delay Tolerant Network (DTN) that consists of a number of mobile devices with social characteristics. The current research achievements on routing algorithms tend to separately evaluate the available profit for each prospective relay node and cannot achieve the global optimal performance in an overall perspective. In this paper, we propose a Movement Pattern-Aware optimal Routing (MPAR) for SDTNs, by choosing the optimal relay node(s) set for each message, which eventually based on running a search algorithm on a hyper-cube solution space. Concretely, the movement pattern of a group of node(s) can be extracted from the movement records of nodes. Then the set of commonly visited locations for the relay node(s) set and the destination node is obtained, by which we can further evaluate the co-delivery probability of the relay node(s) set. Both local search scheme and tabu-search scheme are utilized in finding the optimal set, and the tabu-search based routing Tabu-MPAR is proved able to guide the relay node(s) set in evolving to the optimal one. We demonstrate how the MPAR algorithm significantly outperforms the previous ones through extensive simulations, based on the synthetic SDTN mobility model.

cs.IT↗

arXiv2017

A One-Hop Information Based Geographic Routing Protocol for Delay Tolerant MANETs

Delay and Disruption Tolerant Networks (DTNs) may lack continuous network connectivity. Routing in DTNs is thus a challenge since it must handle network partitioning, long delays, and dynamic topology. Meanwhile, routing protocols of the traditional Mobile Ad hoc NETworks (MANETs) cannot work well due to the failure of its assumption that most network connections are available. In this article, a geographic routing protocol is proposed for MANETs in delay tolerant situations, by using no more than one-hop information. A utility function is designed for implementing the under-controlled replication strategy. To reduce the overheads caused by message flooding, we employ a criterion so as to evaluate the degree of message redundancy. Consequently a message redundancy coping mechanism is added to our routing protocol. Extensive simulations have been conducted and the results show that when node moving speed is relatively low, our routing protocol outperforms the other schemes such as Epidemic, Spray and Wait, FirstContact in delivery ratio and average hop count, while introducing an acceptable overhead ratio into the network.

cs.NI↗

arXiv2015

Design and Application of Variable Temperature Environmental Capsule for Scanning Electron Microscopy in Gases and Liquids at Ambient Conditions

Scanning electron microscopy (SEM) of nanoscale objects in their native conditions and at different temperatures are of critical importance in revealing details of their interactions with ambient environments. Currently available environmental capsules are equipped with thin electron transparent membranes and allow imaging the samples at atmospheric pressure. However these capsules do not provide the temperature control over the sample. Here we developed and tested a thermoelectric cooling / heating setup for available environmental capsules to allow ambient pressure in situ SEM studies over the -15 °C to 100 °C temperature range in gaseous, liquid, and frozen environments. The design of the setup also allows correlation of the SEM with optical microscopy and spectroscopy. As a demonstration of the possibilities of the developed approach, we performed real-time in situ microscopy studies of water condensation on a surface of wing scales of Morpho sulkowskyi butterfly. We have found that the initial water nucleation takes place on the top of the scale ridges. These results confirmed earlier discovery of a polarity gradient of the ridges of Morpho butterflies. Our developed thermoelectric cooling / heating setup for available SEM environmental capsules promises to impact diverse needs for in-situ nano-characterization including materials science and catalysis, micro-instrumentation and device reliability, chemistry and biology.

cond-mat.mtrl-sci↗