arXiv subjects

Bing Liu

Publications and source records attributed to Bing Liu.

At least 73 records · Page 4Linked to original sources

arXiv2025

Semi-supervised Image Dehazing via Expectation-Maximization and Bidirectional Brownian Bridge Diffusion Models

Existing dehazing methods deal with real-world haze images with difficulty, especially scenes with thick haze. One of the main reasons is the lack of real-world paired data and robust priors. To avoid the costly collection of paired hazy and clear images, we propose an efficient semi-supervised image dehazing method via Expectation-Maximization and Bidirectional Brownian Bridge Diffusion Models (EM-B3DM) with a two-stage learning scheme. In the first stage, we employ the EM algorithm to decouple the joint distribution of paired hazy and clear images into two conditional distributions, which are then modeled using a unified Brownian Bridge diffusion model to directly capture the structural and content-related correlations between hazy and clear images. In the second stage, we leverage the pre-trained model and large-scale unpaired hazy and clear images to further improve the performance of image dehazing. Additionally, we introduce a detail-enhanced Residual Difference Convolution block (RDC) to capture gradient-level information, significantly enhancing the model's representation capability. Extensive experiments demonstrate that our EM-B3DM achieves superior or at least comparable performance to state-of-the-art methods on both synthetic and real-world datasets.

cs.CV↗

arXiv2025

MultiNRC: A Challenging and Native Multilingual Reasoning Evaluation Benchmark for LLMs

Although recent Large Language Models (LLMs) have shown rapid improvement on reasoning benchmarks in English, the evaluation of such LLMs' multilingual reasoning capability across diverse languages and cultural contexts remains limited. Existing multilingual reasoning benchmarks are typically constructed by translating existing English reasoning benchmarks, biasing these benchmarks towards reasoning problems with context in English language/cultures. In this work, we introduce the Multilingual Native Reasoning Challenge (MultiNRC), a benchmark designed to assess LLMs on more than 1,000 native, linguistic and culturally grounded reasoning questions written by native speakers in French, Spanish, and Chinese. MultiNRC covers four core reasoning categories: language-specific linguistic reasoning, wordplay & riddles, cultural/tradition reasoning, and math reasoning with cultural relevance. For cultural/tradition reasoning and math reasoning with cultural relevance, we also provide English equivalent translations of the multilingual questions by manual translation from native speakers fluent in English. This set of English equivalents can provide a direct comparison of LLM reasoning capacity in other languages vs. English on the same reasoning questions. We systematically evaluate current 14 leading LLMs covering most LLM families on MultiNRC and its English equivalent set. The results show that (1) current LLMs are still not good at native multilingual reasoning, with none scoring above 50% on MultiNRC; (2) LLMs exhibit distinct strengths and weaknesses in handling linguistic, cultural, and logical reasoning tasks; (3) Most models perform substantially better in math reasoning in English compared to in original languages (+10%), indicating persistent challenges with culturally grounded knowledge.

cs.CL↗

arXiv2025

Exploring Task-Solving Paradigm for Generalized Cross-Domain Face Anti-Spoofing via Reinforcement Fine-Tuning

Recently the emergence of novel presentation attacks has drawn increasing attention to face anti-spoofing. However, existing methods tend to memorize data patterns from the training set, resulting in poor generalization to unknown attack types across different scenarios and limited interpretability. To address these challenges, this paper presents a reinforcement fine-tuning-based face anti-spoofing method that stimulates the capabilities of multimodal large language models to think and learn how to solve the anti-spoofing task itself, rather than relying on the memorization of authenticity patterns. We design verifiable class consistent reward and reasoning consistent reward, and employ a GRPO-based optimization strategy to guide the model in exploring reasoning policies from multiple perspectives to maximize expected rewards. As a result, through iterative trial-and-error learning while retaining only high-reward trajectories, the model distills highly generalizable decision-making rules from the extensive solution space to effectively address cross-domain face anti-spoofing tasks. Extensive experimental results demonstrate that our method achieves state-of-the-art cross-domain generalization performance. It generalizes well to diverse unknown attack types in unseen target domains while providing interpretable reasoning for its authenticity decisions without requiring labor-intensive textual annotations for training.

cs.CV↗

arXiv2025

Privacy-Preserving Resilient Vector Consensus

This paper studies privacy-preserving resilient vector consensus in multi-agent systems against faulty agents, where normal agents can achieve consensus within the convex hull of their initial states while protecting state vectors from being disclosed. Specifically, we consider a modification of an existing algorithm known as Approximate Distributed Robust Convergence Using Centerpoints (ADRC), i.e., Privacy-Preserving ADRC (PP-ADRC). Under PP-ADRC, each normal agent introduces multivariate Gaussian noise to its state during each iteration. We first provide sufficient conditions to ensure that all normal agents' states can achieve mean square convergence under PP-ADRC. Then, we analyze convergence accuracy from two perspectives, i.e., the Mahalanobis distance of the final value from its expectation and the Hausdorff distance-based alteration of the convex hull caused by noise when only partial dimensions are added with noise. Then, we employ concentrated geo-privacy to characterize privacy preservation and conduct a thorough comparison with differential privacy. Finally, numerical simulations demonstrate the theoretical results.

eess.SY↗

arXiv2025

ImprovDML: Improved Trade-off in Private Byzantine-Resilient Distributed Machine Learning

Jointly addressing Byzantine attacks and privacy leakage in distributed machine learning (DML) has become an important issue. A common strategy involves integrating Byzantine-resilient aggregation rules with differential privacy mechanisms. However, the incorporation of these techniques often results in a significant degradation in model accuracy. To address this issue, we propose a decentralized DML framework, named ImprovDML, that achieves high model accuracy while simultaneously ensuring privacy preservation and resilience to Byzantine attacks. The framework leverages a kind of resilient vector consensus algorithms that can compute a point within the normal (non-Byzantine) agents' convex hull for resilient aggregation at each iteration. Then, multivariate Gaussian noises are introduced to the gradients for privacy preservation. We provide convergence guarantees and derive asymptotic learning error bounds under non-convex settings, which are tighter than those reported in existing works. For the privacy analysis, we adopt the notion of concentrated geo-privacy, which quantifies privacy preservation based on the Euclidean distance between inputs. We demonstrate that it enables an improved trade-off between privacy preservation and model accuracy compared to differential privacy. Finally, numerical simulations validate our theoretical results.

cs.LG↗

arXiv2025

Modality-Guided Dynamic Graph Fusion and Temporal Diffusion for Self-Supervised RGB-T Tracking

To reduce the reliance on large-scale annotations, self-supervised RGB-T tracking approaches have garnered significant attention. However, the omission of the object region by erroneous pseudo-label or the introduction of background noise affects the efficiency of modality fusion, while pseudo-label noise triggered by similar object noise can further affect the tracking performance. In this paper, we propose GDSTrack, a novel approach that introduces dynamic graph fusion and temporal diffusion to address the above challenges in self-supervised RGB-T tracking. GDSTrack dynamically fuses the modalities of neighboring frames, treats them as distractor noise, and leverages the denoising capability of a generative model. Specifically, by constructing an adjacency matrix via an Adjacency Matrix Generator (AMG), the proposed Modality-guided Dynamic Graph Fusion (MDGF) module uses a dynamic adjacency matrix to guide graph attention, focusing on and fusing the object's coherent regions. Temporal Graph-Informed Diffusion (TGID) models MDGF features from neighboring frames as interference, and thus improving robustness against similar-object noise. Extensive experiments conducted on four public RGB-T tracking datasets demonstrate that GDSTrack outperforms the existing state-of-the-art methods. The source code is available at https://github.com/LiShenglana/GDSTrack.

cs.CV↗

arXiv2025

Learning Unknown Spoof Prompts for Generalized Face Anti-Spoofing Using Only Real Face Images

Face anti-spoofing is a critical technology for ensuring the security of face recognition systems. However, its ability to generalize across diverse scenarios remains a significant challenge. In this paper, we attribute the limited generalization ability to two key factors: covariate shift, which arises from external data collection variations, and semantic shift, which results from substantial differences in emerging attack types. To address both challenges, we propose a novel approach for learning unknown spoof prompts, relying solely on real face images from a single source domain. Our method generates textual prompts for real faces and potential unknown spoof attacks by leveraging the general knowledge embedded in vision-language models, thereby enhancing the model's ability to generalize to unseen target domains. Specifically, we introduce a diverse spoof prompt optimization framework to learn effective prompts. This framework constrains unknown spoof prompts within a relaxed prior knowledge space while maximizing their distance from real face images. Moreover, it enforces semantic independence among different spoof prompts to capture a broad range of spoof patterns. Experimental results on nine datasets demonstrate that the learned prompts effectively transfer the knowledge of vision-language models, enabling state-of-the-art generalization ability against diverse unknown attack types across unseen target domains without using any spoof face images.

cs.CV↗

arXiv2025

BiXiao: An AI-Based Atmospheric Environment Forecasting Model Using Discontinuous Grids

Currently, the technique of numerical model-based atmospheric environment forecasting has becoming mature, yet traditional numerical prediction methods struggle to balance computational costs and forecast accuracy, facing developmental bottlenecks. Recent advancements in artificial intelligence (AI) offer new solutions for weather prediction. However, most existing AI models do not have atmospheric environmental forecasting capabilities, while those with related functionalities remain constrained by grid-dependent data requirements, thus unable to deliver operationally feasible city-scale atmospheric environment forecasts. Here we introduce 'BiXiao', a novel discontinuous-grid AI model for atmospheric environment forecasting. 'BiXiao' couples meteorological and environmental sub-models to generate predictions using site-specific observational data, completing 72-hour forecasts for six major pollutants across all key cities in the Beijing-Tianjin-Hebei region within 30 seconds. In the comparative experiments, the 'BiXiao' model outperforms mainstream numerical models in both computational efficiency and forecast accuracy. It surpasses CAMS with respect of operational 72-hour forecasting and exceeds WRF-Chem's performance in heavy pollution case predictions. The 'BiXiao' shows potential for nationwide application, providing innovative technical support and new perspectives for China's atmospheric environment forecasting operations.

physics.ao-ph↗

arXiv2025

Layer Swapping for Zero-Shot Cross-Lingual Transfer in Large Language Models

Model merging, such as model souping, is the practice of combining different models with the same architecture together without further training. In this work, we present a model merging methodology that addresses the difficulty of fine-tuning Large Language Models (LLMs) for target tasks in non-English languages, where task-specific data is often unavailable. We focus on mathematical reasoning and without in-language math data, facilitate cross-lingual transfer by composing language and math capabilities. Starting from the same pretrained model, we fine-tune separate "experts" on math instruction data in English and on generic instruction data in the target language. We then replace the top and bottom transformer layers of the math expert directly with layers from the language expert, which consequently enhances math performance in the target language. The resulting merged models outperform the individual experts and other merging methods on the math benchmark, MGSM, by 10% across four major languages where math instruction data is scarce. In addition, this layer swapping is simple, inexpensive, and intuitive, as it is based on an interpretative analysis of the most important parameter changes during the fine-tuning of each expert. The ability to successfully re-compose LLMs for cross-lingual transfer in this manner opens up future possibilities to combine model expertise, create modular solutions, and transfer reasoning capabilities across languages all post hoc.

cs.CL↗

arXiv2025

Achieving Upper Bound Accuracy of Joint Training in Continual Learning

Continual learning has been an active research area in machine learning, focusing on incrementally learning a sequence of tasks. A key challenge is catastrophic forgetting (CF), and most research efforts have been directed toward mitigating this issue. However, a significant gap remains between the accuracy achieved by state-of-the-art continual learning algorithms and the ideal or upper-bound accuracy achieved by training all tasks together jointly. This gap has hindered or even prevented the adoption of continual learning in applications, as accuracy is often of paramount importance. Recently, another challenge, termed inter-task class separation (ICS), was also identified, which spurred a theoretical study into principled approaches for solving continual learning. Further research has shown that by leveraging the theory and the power of large foundation models, it is now possible to achieve upper-bound accuracy, which has been empirically validated using both text and image classification datasets. Continual learning is now ready for real-life applications. This paper surveys the main research leading to this achievement, justifies the approach both intuitively and from neuroscience research, and discusses insights gained.

cs.LG↗

arXiv2025

Overview of EXL-50 Research Progress and Future Plan

XuanLong-50 (EXL-50) is the first medium-size spherical torus (ST) in China, with the toroidal field at major radius at 50 cm around 0.5T. CS-free and non-inductive current drive via electron cyclotron resonance heating (ECRH) was the main physics research issue for EXL-50. Discharges with plasma currents of 50 kA - 180 kA were routinely obtained in EXL-50, with the current flattop sustained for up to or beyond 2 s. The current drive effectiveness on EXL-50 was as high as 1 A/W for low-density discharges using 28GHz ECRH alone for heating power less than 200 kW. The plasma current reached Ip>80 kA for high-density (5*10e18m-2) discharges with 150 kW 28GHz ECRH. Higher performance discharge (Ip of about 120 kA and core density of about 1*10e19m-3) was achieved with 150 kW 50GHz ECRH. The plasma current in EXL-50 was mainly carried by the energetic electrons.Multi-fluid equilibrium model has been successfully applied to reconstruct the magnetic flux surface and the measured plasma parameters of the EXL-50 equilibrium. The physics mechanisms for the solenoid-free ECRH current drive and the energetic electrons has also been investigated. Preliminary experimental results show that 100 kW of lower hybrid current drive (LHCD) waves can drive 20 kA of plasma current. Several boron injection systems were installed and tested in EXL-50, including B2H6 gas puffing, boron powder injection, boron pellet injection. The research plan of EXL-50U, which is the upgrade machine of EXL-50, is also presented.

physics.plasm-ph↗

arXiv2025

Graphene intercalation of the large gap quantum spin Hall insulator bismuthene

The quantum spin Hall insulator bismuthene, a two-third monolayer of bismuth on SiC(0001), is distinguished by helical metallic edge states that are protected by a groundbreaking 800 meV topological gap, making it ideal for room temperature applications. This massive gap inversion arises from a unique synergy between flat honeycomb structure, strong spin orbit coupling, and an orbital filtering effect that is mediated by the substrate. However, the rapid oxidation of bismuthene in air has severely hindered the development of applications, so far confining experiments to ultra-high vacuum conditions. Here, we successfully overcome this barrier, intercalating bismuthene between SiC and a protective sheet of graphene. As we demonstrate through scanning tunneling microscopy and photoemission spectroscopy, graphene intercalation preserves the structural and topological integrity of bismuthene, while effectively shielding it from oxidation in air. We identify hydrogen as the critical component that was missing in previous bismuth intercalation attempts. Our findings facilitate ex-situ experiments and pave the way for the development of bismuthene based devices, signaling a significant step forward in the development of next-generation technologies.

cond-mat.mtrl-sci↗

arXiv2024

Continual Learning Using Only Large Language Model Prompting

We introduce CLOB, a novel continual learning (CL) paradigm wherein a large language model (LLM) is regarded as a black box. Learning is done incrementally via only verbal prompting. CLOB does not fine-tune any part of the LLM or add any trainable parameters to it. It is particularly suitable for LLMs that are accessible via APIs. We also propose a new CL technique, called CIS, based on incremental summarization that also overcomes the LLM's input length limit. Experiments show CIS outperforms baselines by a very large margin.

cs.CL↗

arXiv2024

In-context Continual Learning Assisted by an External Continual Learner

Existing continual learning (CL) methods mainly rely on fine-tuning or adapting large language models (LLMs). They still suffer from catastrophic forgetting (CF). Little work has been done to exploit in-context learning (ICL) to leverage the extensive knowledge within LLMs for CL without updating any parameters. However, incrementally learning each new task in ICL necessitates adding training examples from each class of the task to the prompt, which hampers scalability as the prompt length increases. This issue not only leads to excessively long prompts that exceed the input token limit of the underlying LLM but also degrades the model's performance due to the overextended context. To address this, we introduce InCA, a novel approach that integrates an external continual learner (ECL) with ICL to enable scalable CL without CF. The ECL is built incrementally to pre-select a small subset of likely classes for each test instance. By restricting the ICL prompt to only these selected classes, InCA prevents prompt lengths from becoming excessively long, while maintaining high performance. Experimental results demonstrate that InCA significantly outperforms existing CL baselines, achieving substantial performance gains.

cs.CL↗

arXiv2024

Continual Learning Using a Kernel-Based Method Over Foundation Models

Continual learning (CL) learns a sequence of tasks incrementally. This paper studies the challenging CL setting of class-incremental learning (CIL). CIL has two key challenges: catastrophic forgetting (CF) and inter-task class separation (ICS). Despite numerous proposed methods, these issues remain persistent obstacles. This paper proposes a novel CIL method, called Kernel Linear Discriminant Analysis (KLDA), that can effectively avoid CF and ICS problems. It leverages only the powerful features learned in a foundation model (FM). However, directly using these features proves suboptimal. To address this, KLDA incorporates the Radial Basis Function (RBF) kernel and its Random Fourier Features (RFF) to enhance the feature representations from the FM, leading to improved performance. When a new task arrives, KLDA computes only the mean for each class in the task and updates a shared covariance matrix for all learned classes based on the kernelized features. Classification is performed using Linear Discriminant Analysis. Our empirical evaluation using text and image classification datasets demonstrates that KLDA significantly outperforms baselines. Remarkably, without relying on replay data, KLDA achieves accuracy comparable to joint training of all classes, which is considered the upper bound for CIL performance. The KLDA code is available at https://github.com/salehmomeni/klda.

cs.LG↗

arXiv2024

Nuclear de-excitation line emissions from giant molecular clouds

Understanding how cosmic rays (CRs) propagate within the giant molecular clouds (GMCs) is critical for studying the dynamics and chemical processes inside the clouds. The flux of low-energy CRs inside the dense cores of GMCs strongly affects the heating and ionization of the gases and further influences the star-forming process. We analytically calculated the CR distribution inside GMCs assuming different diffusion coefficients, and estimated the corresponding nuclear de-excitation line emission and the ionization rate resulting from the interaction between the penetrating CRs and gases. We find that future MeV observations can be used as a unique probe to measure the low-energy CR density in situ and test different CR propagation scenario inside GMCs.

astro-ph.HE↗

arXiv2024

DESIRE: Dynamic Knowledge Consolidation for Rehearsal-Free Continual Learning

Continual learning aims to equip models with the ability to retain previously learned knowledge like a human. Recent work incorporating Parameter-Efficient Fine-Tuning has revitalized the field by introducing lightweight extension modules. However, existing methods usually overlook the issue of information leakage caused by the fact that the experiment data have been used in pre-trained models. Once these duplicate data are removed in the pre-training phase, their performance can be severely affected. In this paper, we propose a new LoRA-based rehearsal-free method named DESIRE. Our method avoids imposing additional constraints during training to mitigate catastrophic forgetting, thereby maximizing the learning of new classes. To integrate knowledge from old and new tasks, we propose two efficient post-processing modules. On the one hand, we retain only two sets of LoRA parameters for merging and propose dynamic representation consolidation to calibrate the merged feature representation. On the other hand, we propose decision boundary refinement to address classifier bias when training solely on new class data. Extensive experiments demonstrate that our method achieves state-of-the-art performance on multiple datasets and strikes an effective balance between stability and plasticity. Our code will be publicly available.

cs.LG↗

arXiv2024

Low-Energy Cosmic Rays and Associated MeV Gamma-Ray Emissions in the Protoplanetary System

Low-energy cosmic rays (LECRs) play a crucial role in the formation of planetary systems, and detecting and reconstructing the properties of early LECRs is essential for understanding the mechanisms of planetary system formation. Given that LECRs interact with the surrounding medium to produce nuclear de-excitation line emissions, which are gamma-ray emissions with energy mainly within 0.1--10 MeV and are unaffected by stellar wind modulation, these emissions can accurately reflect the properties of LECRs. This study introduces an innovative method for using gamma-ray emissions to infer LECR properties. We employed the Parker transport equation to simulate the propagation and spectral evolution of LECRs in a protoplanetary disk and calculated the characteristic gamma-ray emissions resulting from interactions between LECRs and disk material. These gamma-ray emissions encapsulate the spectral information of LECRs, providing a powerful tool to reconstruct the cosmic ray environment at that time. This method, supported by further theoretical developments and observations, will fundamentally enhance our understanding of the impact of CRs on the origin and evolution of planetary systems and address significant scientific questions regarding the cosmic ray environment at the origin of life.

astro-ph.HE↗