arXiv subjects

Bo Li

Publications and source records attributed to Bo Li.

At least 397 records · Page 22Linked to original sources

arXiv2025

Privacy-Preserving Federated Embedding Learning for Localized Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) has recently emerged as a promising solution for enhancing the accuracy and credibility of Large Language Models (LLMs), particularly in Question & Answer tasks. This is achieved by incorporating proprietary and private data from integrated databases. However, private RAG systems face significant challenges due to the scarcity of private domain data and critical data privacy issues. These obstacles impede the deployment of private RAG systems, as developing privacy-preserving RAG systems requires a delicate balance between data security and data availability. To address these challenges, we regard federated learning (FL) as a highly promising technology for privacy-preserving RAG services. We propose a novel framework called Federated Retrieval-Augmented Generation (FedE4RAG). This framework facilitates collaborative training of client-side RAG retrieval models. The parameters of these models are aggregated and distributed on a central-server, ensuring data privacy without direct sharing of raw data. In FedE4RAG, knowledge distillation is employed for communication between the server and client models. This technique improves the generalization of local RAG retrievers during the federated learning process. Additionally, we apply homomorphic encryption within federated learning to safeguard model parameters and mitigate concerns related to data leakage. Extensive experiments conducted on the real-world dataset have validated the effectiveness of FedE4RAG. The results demonstrate that our proposed framework can markedly enhance the performance of private RAG systems while maintaining robust data privacy protection.

cs.CL↗

arXiv2025

Anyprefer: An Agentic Framework for Preference Data Synthesis

High-quality preference data is essential for aligning foundation models with human values through preference learning. However, manual annotation of such data is often time-consuming and costly. Recent methods often adopt a self-rewarding approach, where the target model generates and annotates its own preference data, but this can lead to inaccuracies since the reward model shares weights with the target model, thereby amplifying inherent biases. To address these issues, we propose Anyprefer, a framework designed to synthesize high-quality preference data for aligning the target model. Anyprefer frames the data synthesis process as a cooperative two-player Markov Game, where the target model and the judge model collaborate together. Here, a series of external tools are introduced to assist the judge model in accurately rewarding the target model's responses, mitigating biases in the rewarding process. In addition, a feedback mechanism is introduced to optimize prompts for both models, enhancing collaboration and improving data quality. The synthesized data is compiled into a new preference dataset, Anyprefer-V1, consisting of 58K high-quality preference pairs. Extensive experiments show that Anyprefer significantly improves model alignment performance across four main applications, covering 21 datasets, achieving average improvements of 18.55% in five natural language generation datasets, 3.66% in nine vision-language understanding datasets, 30.05% in three medical image analysis datasets, and 16.00% in four visuo-motor control tasks.

cs.LG↗

arXiv2025

A Survey of Task-Oriented Knowledge Graph Reasoning: Status, Applications, and Prospects

Knowledge graphs (KGs) have emerged as a powerful paradigm for structuring and leveraging diverse real-world knowledge, which serve as a fundamental technology for enabling cognitive intelligence systems with advanced understanding and reasoning capabilities. Knowledge graph reasoning (KGR) aims to infer new knowledge based on existing facts in KGs, playing a crucial role in applications such as public security intelligence, intelligent healthcare, and financial risk assessment. From a task-centric perspective, existing KGR approaches can be broadly classified into static single-step KGR, static multi-step KGR, dynamic KGR, multi-modal KGR, few-shot KGR, and inductive KGR. While existing surveys have covered these six types of KGR tasks, a comprehensive review that systematically summarizes all KGR tasks particularly including downstream applications and more challenging reasoning paradigms remains lacking. In contrast to previous works, this survey provides a more comprehensive perspective on the research of KGR by categorizing approaches based on primary reasoning tasks, downstream application tasks, and potential challenging reasoning tasks. Besides, we explore advanced techniques, such as large language models (LLMs), and their impact on KGR. This work aims to highlight key research trends and outline promising future directions in the field of KGR.

cs.AI↗

arXiv2025

Minder: Faulty Machine Detection for Large-scale Distributed Model Training

Large-scale distributed model training requires simultaneous training on up to thousands of machines. Faulty machine detection is critical when an unexpected fault occurs in a machine. From our experience, a training task can encounter two faults per day on average, possibly leading to a halt for hours. To address the drawbacks of the time-consuming and labor-intensive manual scrutiny, we propose Minder, an automatic faulty machine detector for distributed training tasks. The key idea of Minder is to automatically and efficiently detect faulty distinctive monitoring metric patterns, which could last for a period before the entire training task comes to a halt. Minder has been deployed in our production environment for over one year, monitoring daily distributed training tasks where each involves up to thousands of machines. In our real-world fault detection scenarios, Minder can accurately and efficiently react to faults within 3.6 seconds on average, with a precision of 0.904 and F1-score of 0.893.

cs.DC↗

arXiv2025

RLeXplore: Accelerating Research in Intrinsically-Motivated Reinforcement Learning

Extrinsic rewards can effectively guide reinforcement learning (RL) agents in specific tasks. However, extrinsic rewards frequently fall short in complex environments due to the significant human effort needed for their design and annotation. This limitation underscores the necessity for intrinsic rewards, which offer auxiliary and dense signals and can enable agents to learn in an unsupervised manner. Although various intrinsic reward formulations have been proposed, their implementation and optimization details are insufficiently explored and lack standardization, thereby hindering research progress. To address this gap, we introduce RLeXplore, a unified, highly modularized, and plug-and-play framework offering reliable implementations of eight state-of-the-art intrinsic reward methods. Furthermore, we conduct an in-depth study that identifies critical implementation details and establishes well-justified standard practices in intrinsically-motivated RL. Our documentation, examples, and source code are available at https://github.com/RLE-Foundation/RLeXplore.

cs.LG↗

arXiv2025

Improving Consistency in Diffusion Models for Image Super-Resolution

Recent methods exploit the powerful text-to-image (T2I) diffusion models for real-world image super-resolution (Real-ISR) and achieve impressive results compared to previous models. However, we observe two kinds of inconsistencies in diffusion-based methods which hinder existing models from fully exploiting diffusion priors. The first is the semantic inconsistency arising from diffusion guidance. T2I generation focuses on semantic-level consistency with text prompts, while Real-ISR emphasizes pixel-level reconstruction from low-quality (LQ) images, necessitating more detailed semantic guidance from LQ inputs. The second is the training-inference inconsistency stemming from the DDPM, which improperly assumes high-quality (HQ) latent corrupted by Gaussian noise as denoising inputs for each timestep. To address these issues, we introduce ConsisSR to handle both semantic and training-inference consistencies. On the one hand, to address the semantic inconsistency, we proposed a Hybrid Prompt Adapter (HPA). Instead of text prompts with coarse-grained classification information, we leverage the more powerful CLIP image embeddings to explore additional color and texture guidance. On the other hand, we introduce Time-Aware Latent Augmentation (TALA) to bridge the training-inference inconsistency. Based on the probability function p(t), we accordingly enhance the SDSR training strategy. With LQ latent with Gaussian noise as inputs, our TALA not only focuses on diffusion noise but also refine the LQ latent towards the HQ counterpart. Our method demonstrates state-of-the-art performance among existing diffusion models. The code will be made publicly available.

cs.CV↗

arXiv2025

Think Hierarchically, Act Dynamically: Hierarchical Multi-modal Fusion and Reasoning for Vision-and-Language Navigation

Vision-and-Language Navigation (VLN) aims to enable embodied agents to follow natural language instructions and reach target locations in real-world environments. While prior methods often rely on either global scene representations or object-level features, these approaches are insufficient for capturing the complex interactions across modalities required for accurate navigation. In this paper, we propose a Multi-level Fusion and Reasoning Architecture (MFRA) to enhance the agent's ability to reason over visual observations, language instructions and navigation history. Specifically, MFRA introduces a hierarchical fusion mechanism that aggregates multi-level features-ranging from low-level visual cues to high-level semantic concepts-across multiple modalities. We further design a reasoning module that leverages fused representations to infer navigation actions through instruction-guided attention and dynamic context integration. By selectively capturing and combining relevant visual, linguistic, and temporal signals, MFRA improves decision-making accuracy in complex navigation scenarios. Extensive experiments on benchmark VLN datasets including REVERIE, R2R, and SOON demonstrate that MFRA achieves superior performance compared to state-of-the-art methods, validating the effectiveness of multi-level modal fusion for embodied navigation.

cs.CV↗

arXiv2025

AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs

In this paper, we propose AutoDAN-Turbo, a black-box jailbreak method that can automatically discover as many jailbreak strategies as possible from scratch, without any human intervention or predefined scopes (e.g., specified candidate strategies), and use them for red-teaming. As a result, AutoDAN-Turbo can significantly outperform baseline methods, achieving a 74.3% higher average attack success rate on public benchmarks. Notably, AutoDAN-Turbo achieves an 88.5 attack success rate on GPT-4-1106-turbo. In addition, AutoDAN-Turbo is a unified framework that can incorporate existing human-designed jailbreak strategies in a plug-and-play manner. By integrating human-designed strategies, AutoDAN-Turbo can even achieve a higher attack success rate of 93.4 on GPT-4-1106-turbo.

cs.CR↗

arXiv2025

Large Language Model Empowered Privacy-Protected Framework for PHI Annotation in Clinical Notes

The de-identification of private information in medical data is a crucial process to mitigate the risk of confidentiality breaches, particularly when patient personal details are not adequately removed before the release of medical records. Although rule-based and learning-based methods have been proposed, they often struggle with limited generalizability and require substantial amounts of annotated data for effective performance. Recent advancements in large language models (LLMs) have shown significant promise in addressing these issues due to their superior language comprehension capabilities. However, LLMs present challenges, including potential privacy risks when using commercial LLM APIs and high computational costs for deploying open-source LLMs locally. In this work, we introduce LPPA, an LLM-empowered Privacy-Protected PHI Annotation framework for clinical notes, targeting the English language. By fine-tuning LLMs locally with synthetic notes, LPPA ensures strong privacy protection and high PHI annotation accuracy. Extensive experiments demonstrate LPPA's effectiveness in accurately de-identifying private information, offering a scalable and efficient solution for enhancing patient privacy protection.

cs.CR↗

arXiv2025

X-type stacking in cross-chain antiferromagnets

Physical phenomena in condensed matter normally arise from the collective effect of all atoms, while selectively addressing a lone atomic sublattice by external stimulus is elusive. The later functionality may, however, benefit various applications, as the response may differ when the external stimulus affects only a specific sublattice rather than the entire solid. Here, we introduce cross-chain antiferromagnets, where the stacking of two magnetic sublattices forms a pattern of intersecting atomic chains, allowing for the sublattice selectivity. We dub this antiferromagnetic (AFM) stacking X-type and demonstrate that it exhibits unique spin-dependent transport properties not present in conventional magnets. Through high-throughput analyses and computations, we unveil three prototypes of X-type AFM stacking and identify 15 candidate candidates. Using $β$-Fe$_{2}$PO$_{5}$ as a representative X-type antiferromagnet, we predict sublattice-selective spin-polarized transport driven by the X-type stacking, where one magnetic sublattice conducts, while the other does not. Consequently, a spin torque can be exerted solely on a single sublattice, leading to unconventional ultrafast dynamics of the Nèel vector capable of deterministic switching of the AFM domains. Our work uncovers a previously overlooked type of magnetic moment stacking and reveals sublattice-selective physical properties promising for high-performance spintronic applications.

cond-mat.mtrl-sci↗

arXiv2025

Giant Magnetocaloric Effect in Spin Supersolid Candidate Na$_2$BaCo(PO$_4$)$_2$

Supersolid, an exotic quantum state of matter that consists of particles forming an incompressible solid structure while simultaneously showing superfluidity of zero viscosity [1], is one of the long-standing pursuits in fundamental research [2, 3]. Although the initial report of $^4$He supersolid turned out to be an artifact [4], this intriguing quantum matter has inspired enthusiastic investigations into ultracold quantum gases [5-8]. Nevertheless, the realization of supersolidity in condensed matter remains elusive. Here we find evidence for a quantum magnetic analogue of supersolid -- the spin supersolid -- in the recently synthesized triangular-lattice antiferromagnet Na$_2$BaCo(PO$_4$)$_2$ [9]. Notably, a giant magnetocaloric effect related to the spin supersolidity is observed in the demagnetization cooling process, manifesting itself as two prominent valley-like regimes, with the lowest temperature attaining below 100 mK. Not only is there an experimentally determined series of critical fields but the demagnetization cooling profile also shows excellent agreement with the theoretical simulations with an easy-axis Heisenberg model. Neutron diffractions also successfully locate the proposed spin supersolid phases by revealing the coexistence of three-sublattice spin solid order and interlayer incommensurability indicative of the spin superfluidity. Thus, our results indicate a strong entropic effect of the spin supersolid phase in a frustrated quantum magnet and open up a viable and promising avenue for applications in sub-Kelvin refrigeration, especially in the context of persistent concerns about helium shortages [10, 11].

cond-mat.str-el↗

arXiv2025

From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future

With the rise of large language models (LLMs), researchers are increasingly exploring their applications in var ious vertical domains, such as software engineering. LLMs have achieved remarkable success in areas including code generation and vulnerability detection. However, they also exhibit numerous limitations and shortcomings. LLM-based agents, a novel tech nology with the potential for Artificial General Intelligence (AGI), combine LLMs as the core for decision-making and action-taking, addressing some of the inherent limitations of LLMs such as lack of autonomy and self-improvement. Despite numerous studies and surveys exploring the possibility of using LLMs in software engineering, it lacks a clear distinction between LLMs and LLM based agents. It is still in its early stage for a unified standard and benchmarking to qualify an LLM solution as an LLM-based agent in its domain. In this survey, we broadly investigate the current practice and solutions for LLMs and LLM-based agents for software engineering. In particular we summarise six key topics: requirement engineering, code generation, autonomous decision-making, software design, test generation, and software maintenance. We review and differentiate the work of LLMs and LLM-based agents from these six topics, examining their differences and similarities in tasks, benchmarks, and evaluation metrics. Finally, we discuss the models and benchmarks used, providing a comprehensive analysis of their applications and effectiveness in software engineering. We anticipate this work will shed some lights on pushing the boundaries of LLM-based agents in software engineering for future research.

cs.SE↗

arXiv2025

Geometry of sets of Bargmann invariants

Certain unitary-invariants, known as Bargmann invariants or multivariate traces of quantum states, have recently gained attention due to their applications in quantum information theory. However, determining the boundaries of sets of Bargmann invariants remains a theoretical challenge. In this study, we address the problem by developing a unified, dimension-independent formulation that characterizes the sets of the 3rd and 4th Bargmann invariants.In particular, our result for the set of 4th Bargmann invariants confirms the conjecture given by Fernandes \emph{et al.} [Phys.Rev.Lett.\href{https://doi.org/10.1103/PhysRevLett.133.190201}{\textbf{133}, 190201 (2024)}]. Based on the obtained results, we conjecture that the unified, dimension-independent formulation of the boundaries for sets of 3rd-order and 4th-order Bargmann invariants may extend to the general case of the $n$th-order Bargmann invariants. These results deepen our understanding of the fundamental physical limits within quantum mechanics and pave the way for novel applications of Bargmann invariants in quantum information processing and related fields.

quant-ph↗

arXiv2025

From 128K to 4M: Efficient Training of Ultra-Long Context Large Language Models

Long-context capabilities are essential for a wide range of applications, including document and video understanding, in-context learning, and inference-time scaling, all of which require models to process and reason over long sequences of text and multimodal data. In this work, we introduce a efficient training recipe for building ultra-long context LLMs from aligned instruct model, pushing the boundaries of context lengths from 128K to 1M, 2M, and 4M tokens. Our approach leverages efficient continued pretraining strategies to extend the context window and employs effective instruction tuning to maintain the instruction-following and reasoning abilities. Our UltraLong-8B, built on Llama3.1-Instruct with our recipe, achieves state-of-the-art performance across a diverse set of long-context benchmarks. Importantly, models trained with our approach maintain competitive performance on standard benchmarks, demonstrating balanced improvements for both long and short context tasks. We further provide an in-depth analysis of key design choices, highlighting the impacts of scaling strategies and data composition. Our findings establish a robust framework for efficiently scaling context lengths while preserving general model capabilities. We release all model weights at: https://ultralong.github.io/.

cs.CL↗

arXiv2025

Spectral signatures of the Markovian to Non-Markovian transition in open quantum systems

We present a new approach for investigating the Markovian to non-Markovian transition in quantum aggregates strongly coupled to a vibrational bath through the analysis of linear absorption spectra. Utilizing hierarchical algebraic equations in the frequency domain, we elucidate how these spectra can effectively reveal transitions between Markovian and non-Markovian regimes, driven by the complex interplay of dissipation, aggregate-bath coupling, and intra-aggregate dipole-dipole interactions. Our results demonstrate that reduced dissipation induces spectral peak splitting, signaling the emergence of bath-induced non-Markovian effects. The spectral peak splitting can also be driven by enhanced dipole-dipole interactions, although the underlying mechanism differs from that of dissipation-induced splitting. Additionally, with an increase in aggregate-bath coupling strength, initially symmetric or asymmetric peaks with varying spectral amplitudes may merge under weak dipole-dipole interactions, whereas strong dipole-dipole interactions are more likely to cause peak splitting. Moreover, we find that spectral features serve as highly sensitive indicators for distinguishing the geometric structures of aggregates, while also unveiling the critical role geometry plays in shaping non-Markovian behavior. This study not only deepens our understanding of the Markovian to non-Markovian transition but also provides a robust framework for optimizing and controlling quantum systems.

quant-ph↗

arXiv2025

Dual Consistent Constraint via Disentangled Consistency and Complementarity for Multi-view Clustering

Multi-view clustering can explore common semantics from multiple views and has received increasing attention in recent years. However, current methods focus on learning consistency in representation, neglecting the contribution of each view's complementarity aspect in representation learning. This limit poses a significant challenge in multi-view representation learning. This paper proposes a novel multi-view clustering framework that introduces a disentangled variational autoencoder that separates multi-view into shared and private information, i.e., consistency and complementarity information. We first learn informative and consistent representations by maximizing mutual information across different views through contrastive learning. This process will ignore complementary information. Then, we employ consistency inference constraints to explicitly utilize complementary information when attempting to seek the consistency of shared information across all views. Specifically, we perform a within-reconstruction using the private and shared information of each view and a cross-reconstruction using the shared information of all views. The dual consistency constraints are not only effective in improving the representation quality of data but also easy to extend to other scenarios, especially in complex multi-view scenes. This could be the first attempt to employ dual consistent constraint in a unified MVC theoretical framework. During the training procedure, the consistency and complementarity features are jointly optimized. Extensive experiments show that our method outperforms baseline methods.

cs.CV↗

arXiv2025

Robustness of ferromagnetism in van der Waals magnet Fe$_3$GeTe$_2$ to hydrostatic pressure

Two-dimensional van der Waals ferromagnet Fe$_3$GeTe$_2$ (FGT) holds a great potential for applications in spintronic devices, due to its high Curie temperature, easy tunability, and excellent structural stability in air. Theoretical studies have shown that pressure, as an external parameter, significantly affects its ferromagnetic properties. In this study, we have performed comprehensive high-pressure neutron powder diffraction (NPD) experiments on FGT up to 5 GPa, to investigate the evolution of its structural and magnetic properties with hydrostatic pressure. The NPD data clearly reveal the robustness of the ferromagnetism in FGT, despite of an apparent suppression by hydrostatic pressure. As the pressure increases from 0 to 5 GPa, the Curie temperature is found to decrease monotonically from 225(5) K to 175(5) K, together with a dramatically suppressed ordered moment of Fe, which is well supported by the first-principles calculations. Although no pressure-driven structural phase transition is observed up to 5 GPa, quantitative analysis on the changes of bond lengths and bond angles indicate a significant modification of the exchange interactions, which accounts for the pressure-induced suppression of the ferromagnetism in FGT.

cond-mat.mtrl-sci↗

arXiv2025

ControlSR: Taming Diffusion Models for Consistent Real-World Image Super Resolution

We present ControlSR, a new method that can tame Diffusion Models for consistent real-world image super-resolution (Real-ISR). Previous Real-ISR models mostly focus on how to activate more generative priors of text-to-image diffusion models to make the output high-resolution (HR) images look better. However, since these methods rely too much on the generative priors, the content of the output images is often inconsistent with the input LR ones. To mitigate the above issue, in this work, we tame Diffusion Models by effectively utilizing LR information to impose stronger constraints on the control signals from ControlNet in the latent space. We show that our method can produce higher-quality control signals, which enables the super-resolution results to be more consistent with the LR image and leads to clearer visual results. In addition, we also propose an inference strategy that imposes constraints in the latent space using LR information, allowing for the simultaneous improvement of fidelity and generative ability. Experiments demonstrate that our model can achieve better performance across multiple metrics on several test sets and generate more consistent SR results with LR images than existing methods. Our code is available at https://github.com/HVision-NKU/ControlSR.

cs.CV↗