arXiv subjects

Bin Liu

Publications and source records attributed to Bin Liu.

At least 127 records · Page 7Linked to original sources

arXiv2025

Limiting Eccentricity in Restricted Hierarchical Three-Body Systems with Short-Range Forces

A hierarchical three-body model can be widely applied to diverse astrophysical settings, from satellite-planet-star systems to binaries around supermassive black holes. The octupole-order perturbation on the inner binary from the tertiary can induce extreme eccentricities and cause orbital flips of the binary, but short-range forces such as those due to General Relativity (GR) may suppress extreme eccentricity excitations. In this paper, we consider restricted hierarchical three-body systems, where the inner binary has a test-mass component. We investigate the maximum possible eccentricity (called "limiting eccentricity") attainable by the inner binary under the influence of the tertiary perturbations and GR effect. In systems with sufficiently high hierarchy, the double averaging (DA) model is a good approximation; we show that the orbits which can flip under the octupole-order perturbation reach the same limiting eccentricity, which can be calculated analytically using the quadrupole-order Hamiltonian. In systems with moderate hierarchy, DA breaks down and the so-called Brown Hamiltonian is often introduced as a correction term; we show that this does not change the limiting eccentricity. Finally, we employ the single averaging (SA) model and find that the limiting eccentricity in the SA model is higher than the one in the DA model. We derive an analytical scaling for the modified limiting eccentricity in the SA model.

astro-ph.EP↗

arXiv2025

Semantic-Aware Representation Learning via Conditional Transport for Multi-Label Image Classification

Multi-label image classification is a critical task in machine learning that aims to accurately assign multiple labels to a single image. While existing methods often utilize attention mechanisms or graph convolutional networks to model visual representations, their performance is still constrained by two critical limitations: the inability to learn discriminative semantic-aware features, and the lack of fine-grained alignment between visual representations and label embeddings. To tackle these issues in a unified framework, this paper proposes a novel approach named Semantic-aware representation learning via Conditional Transport for Multi-Label Image Classification (SCT). The proposed method introduces a semantic-related feature learning module that extracts discriminative label-specific features by emphasizing semantic relevance and interaction, along with a conditional transport-based alignment mechanism that enables precise visual-semantic alignment. Extensive experiments on two widely-used benchmark datasets, VOC2007 and MS-COCO, validate the effectiveness of SCT and demonstrate its superior performance compared to existing state-of-the-art methods.

cs.CV↗

arXiv2025

Think before Recommendation: Autonomous Reasoning-enhanced Recommender

The core task of recommender systems is to learn user preferences from historical user-item interactions. With the rapid development of large language models (LLMs), recent research has explored leveraging the reasoning capabilities of LLMs to enhance rating prediction tasks. However, existing distillation-based methods suffer from limitations such as the teacher model's insufficient recommendation capability, costly and static supervision, and superficial transfer of reasoning ability. To address these issues, this paper proposes RecZero, a reinforcement learning (RL)-based recommendation paradigm that abandons the traditional multi-model and multi-stage distillation approach. Instead, RecZero trains a single LLM through pure RL to autonomously develop reasoning capabilities for rating prediction. RecZero consists of two key components: (1) "Think-before-Recommendation" prompt construction, which employs a structured reasoning template to guide the model in step-wise analysis of user interests, item features, and user-item compatibility; and (2) rule-based reward modeling, which adopts group relative policy optimization (GRPO) to compute rewards for reasoning trajectories and optimize the LLM. Additionally, the paper explores a hybrid paradigm, RecOne, which combines supervised fine-tuning with RL, initializing the model with cold-start reasoning samples and further optimizing it with RL. Experimental results demonstrate that RecZero and RecOne significantly outperform existing baseline methods on multiple benchmark datasets, validating the superiority of the RL paradigm in achieving autonomous reasoning-enhanced recommender systems.

cs.IR↗

arXiv2025

Adversarial Attacks on LiDAR-Based Tracking Across Road Users: Robustness Evaluation and Target-Aware Black-Box Method

In this study, we delve into the robustness of neural network-based LiDAR point cloud tracking models under adversarial attacks, a critical aspect often overlooked in favor of performance enhancement. These models, despite incorporating advanced architectures like Transformer or Bird's Eye View (BEV), tend to neglect robustness in the face of challenges such as adversarial attacks, domain shifts, or data corruption. We instead focus on the robustness of the tracking models under the threat of adversarial attacks. We begin by establishing a unified framework for conducting adversarial attacks within the context of 3D object tracking, which allows us to thoroughly investigate both white-box and black-box attack strategies. For white-box attacks, we tailor specific loss functions to accommodate various tracking paradigms and extend existing methods such as FGSM, C\&W, and PGD to the point cloud domain. In addressing black-box attack scenarios, we introduce a novel transfer-based approach, the Target-aware Perturbation Generation (TAPG) algorithm, with the dual objectives of achieving high attack performance and maintaining low perceptibility. This method employs a heuristic strategy to enforce sparse attack constraints and utilizes random sub-vector factorization to bolster transferability. Our experimental findings reveal a significant vulnerability in advanced tracking methods when subjected to both black-box and white-box attacks, underscoring the necessity for incorporating robustness against adversarial attacks into the design of LiDAR point cloud tracking models. Notably, compared to existing methods, the TAPG also strikes an optimal balance between the effectiveness of the attack and the concealment of the perturbations.

cs.CV↗

arXiv2025

PAD: Phase-Amplitude Decoupling Fusion for Multi-Modal Land Cover Classification

The fusion of Synthetic Aperture Radar (SAR) and RGB imagery for land cover classification remains challenging due to modality heterogeneity and underexploited spectral complementarity. Existing approaches often fail to decouple shared structural features from modality-complementary radiometric attributes, resulting in feature conflicts and information loss. To address this, we propose Phase-Amplitude Decoupling (PAD), a frequency-aware framework that separates phase (modality-shared) and amplitude (modality-complementary) components in the Fourier domain. This design reinforces shared structures while preserving complementary characteristics, thereby enhancing fusion quality. Unlike previous methods that overlook the distinct physical properties encoded in frequency spectra, PAD explicitly introduces amplitude-phase decoupling for multi-modal fusion. Specifically, PAD comprises two key components: 1) Phase Spectrum Correction (PSC), which aligns cross-modal phase features via convolution-guided scaling to improve geometric consistency; and 2) Amplitude Spectrum Fusion (ASF), which dynamically integrates high- and low-frequency patterns using frequency-adaptive multilayer perceptrons, effectively exploiting SAR's morphological sensitivity and RGB's spectral richness. Extensive experiments on WHU-OPT-SAR and DDHR-SK demonstrate state-of-the-art performance. This work establishes a new paradigm for physics-aware multi-modal fusion in remote sensing. The code will be available at https://github.com/RanFeng2/PAD.

cs.CV↗

arXiv2025

Stable High-Order Vortices in Spin-Orbit-Coupled Spin-1 Bose-Einstein Condensates

The present contribution explores phase transitions that occur in the ground state (GS) of spin-1 Bose-Einstein condensates (BECs) with spin-orbit coupling (SOC) under the action of gradient magnetic fields. By solving the corresponding linearized system in an exact fashion, we identify the conditions under which the GS phase transitions occur, thus transforming excited states into GS. The study of the full nonlinear system, including both density-density and spin-spin interactions, is numerically analyzed. For the case of repulsive spin-spin interactions, the results resemble the linear case, while attractive spin-spin interactions lead to the formation of mixed-states near the GS phase-transition points. Additionally, higher-order vortex solitons are found to be stable even in the nonlinear regime. These findings demonstrate that arbitrary winding numbers can be achieved as corresponding to stable GS and thus contributing to the understanding of topological properties in SOC BECs.

cond-mat.quant-gas↗

arXiv2025

LLM Agents for Automated Web Vulnerability Reproduction: Are We There Yet?

Large language model (LLM) agents have demonstrated remarkable capabilities in software engineering and cybersecurity tasks, including code generation, vulnerability discovery, and automated testing. One critical but underexplored application is automated web vulnerability reproduction, which transforms vulnerability reports into working exploits. Although recent advances suggest promising potential, challenges remain in applying LLM agents to real-world web vulnerability reproduction scenarios. In this paper, we present the first comprehensive evaluation of state-of-the-art LLM agents for automated web vulnerability reproduction. We systematically assess 20 agents from software engineering, cybersecurity, and general domains across 16 dimensions, including technical capabilities, environment adaptability, and user experience factors, on 3 representative web vulnerabilities. Based on the results, we select three top-performing agents (OpenHands, SWE-agent, and CAI) for in-depth evaluation on our benchmark dataset of 80 real-world CVEs spanning 7 vulnerability types and 6 web technologies. Our results reveal that while LLM agents achieve reasonable success on simple library-based vulnerabilities, they consistently fail on complex service-based vulnerabilities requiring multi-component environments. Complex environment configurations and authentication barriers create a gap where agents can execute exploit code but fail to trigger actual vulnerabilities. We observe high sensitivity to input guidance, with performance degrading by over 33% under incomplete authentication information. Our findings highlight the significant gap between current LLM agent capabilities and the demands of reliable automated vulnerability reproduction, emphasizing the need for advances in environmental adaptation and autonomous problem-solving capabilities.

cs.SE↗

arXiv2025

Reinforced Preference Optimization for Recommendation

Recent breakthroughs in large language models (LLMs) have fundamentally shifted recommender systems from discriminative to generative paradigms, where user behavior modeling is achieved by generating target items conditioned on historical interactions. Yet current generative recommenders still suffer from two core limitations: the lack of high-quality negative modeling and the reliance on implicit rewards. Reinforcement learning with verifiable rewards (RLVR) offers a natural solution by enabling on-policy sampling of harder negatives and grounding optimization in explicit reward signals. However, applying RLVR to generative recommenders remains non-trivial. Its unique generation space often leads to invalid or repetitive items that undermine sampling efficiency, and ranking supervision is sparse since most items receive identical zero rewards. To address these challenges, we propose Reinforced Preference Optimization for Recommendation (ReRe), a reinforcement-based paradigm tailored to LLM-based recommenders, an important direction in generative recommendation. ReRe incorporates constrained beam search to improve sampling efficiency and diversify hard negatives, while augmenting rule-based accuracy rewards with auxiliary ranking rewards for finer-grained supervision. Extensive experiments on three real-world datasets demonstrate that ReRe consistently outperforms both traditional and LLM-based recommenders in ranking performance. Further analysis shows that ReRe not only enhances performance across both base and SFT-initialized models but also generalizes robustly across different backbone families and scales. Beyond empirical gains, we systematically investigate the design space of RLVR in recommendation across generation, sampling strategy, reward modeling, and optimization algorithm, offering insights for future research.

cs.IR↗

arXiv2025

New global Carleman estimates and null controllability for forward/backward semi-linear parabolic SPDEs

In this paper, we study the null controllability for parabolic SPDEs involving both the state and the gradient of the state. To start with, an improved global Carleman estimate for linear forward (resp. backward) parabolic SPDEs with general random coefficients and square-integrable source terms is derived. Based on this, we further develop a new global Carleman estimate for linear forward (resp. backward) parabolic SPDEs with source terms in the Sobolev space of negative order, which enables us to deal with the global null controllability for linear backward (resp. forward) parabolic SPDEs with gradient terms. As a byproduct, a special weighted energy-type estimate for the controlled system that explicitly depends on the parameters $λ,μ$ and the weighted function $θ$ is obtained, which makes it possible to extend the previous linear null controllability to semi-linear backward (resp. forward) parabolic SPDEs by applying the fixed-point argument in an appropriate Banach space.

math.OC↗

arXiv2025

The influence of the mean anomaly on the dynamical quantities of binary black hole mergers in eccentric orbits

In studies of binary black hole (BBH) mergers in eccentric orbits, the mean anomaly, traditionally regarded as less significant than eccentricity, has been thought to encode only the orbital phase, leading to the assumption that it exerts minimal influence on the dynamics of eccentric mergers. In a previous investigation, we identified consistent oscillations in dynamical quantities peak luminosity $L_{\text{peak}}$, remnant mass $M_{\text{rem}}$, spin $α_{\text{rem}}$, and recoil velocity $V_{\text{rem}}$ in relation to the initial eccentricity $e_0$. These oscillations are associated with integer orbital cycles within a phenomenological framework. In this paper, we aim to explore the underlying physical nature of these oscillations through gravitational waveforms. Our examination of remnant mass and spin reveals that while the initial ADM mass $M_{\mathrm{ADM}}$ and orbital angular momentum $L_0$ exhibit gradual variations with $e_0$, the radiated energy $E_{\text{rad}}$ and angular momentum $L_{\text{rad}}$ display oscillatory patterns akin to those observed in $M_{\text{rem}}$ and $α_{\text{rem}}$. By decomposing the waveforms into three distinct phases inspiral, late inspiral to merger, and ringdown, we demonstrate that these oscillations persist across all phases, suggesting a common origin. Through a comparative analysis of $E_{\text{rad}}$ and $L_{\text{rad}}$ derived from numerical relativity (NR), post-Newtonian (PN) waveforms, and orbital-averaged PN fluxes during the inspiral phase, we identify the initial mean anomaly $l_0$ as the source of the observed oscillations. ...

gr-qc↗

arXiv2025

IRNet: Iterative Refinement Network for Noisy Partial Label Learning

Partial label learning (PLL) is a typical weakly supervised learning, where each sample is associated with a set of candidate labels. Its basic assumption is that the ground-truth label must be in the candidate set, but this assumption may not be satisfied due to the unprofessional judgment of annotators. Therefore, we relax this assumption and focus on a more general task, noisy PLL, where the ground-truth label may not exist in the candidate set. To address this challenging task, we propose a novel framework called ``Iterative Refinement Network (IRNet)'', aiming to purify noisy samples through two key modules (i.e., noisy sample detection and label correction). To achieve better performance, we exploit smoothness constraints to reduce prediction errors in these modules. Through theoretical analysis, we prove that IRNet is able to reduce the noise level of the dataset and eventually approximate the Bayes optimal classifier. Meanwhile, IRNet is a plug-in strategy that can be integrated with existing PLL approaches. Experimental results on multiple benchmark datasets show that IRNet outperforms state-of-the-art approaches on noisy PLL. Our source code is available at: https://github.com/zeroQiaoba/IRNet.

cs.CV↗

arXiv2025

Finetuning Large Language Model as an Effective Symbolic Regressor

Deriving governing equations from observational data, known as Symbolic Regression (SR), is a cornerstone of scientific discovery. Large Language Models, (LLMs) have shown promise in this task by leveraging their vast cross-disciplinary scientific knowledge. However, existing LLM-based methods primarily rely on direct inference or prompt engineering, often requiring excessive inference iterations to converge on correct formulas or failing to treat complex equation targets. These limitations in effectiveness and generalization stem from an inherent tension between pre-trained LLMs' proficiency in approximate reasoning and the high-precision demands of SR tasks. To bridge this gap, we propose to fine-tune LLMs for enhanced SR capability. Yet, the absence of dedicated datasets for SR-oriented fine-tuning remains a critical barrier. We thus introduce SymbArena, specifically engineered to optimize LLMs for SR. This benchmark comprises over 148,000 diverse equations formulated as corpora of 1.83 billion tokens for LLM utilization, enabling effective training and inference. Further, to ensure a more comprehensive and fair evaluation, SymbArena proposes a heuristics metric to precisely quantify form-level consistency, going beyond existing SR numerical-oriented evaluation strategies. With this benchmark, we explore mainstream LLM fine-tuning techniques for SR tasks and establish Symbolic-R1, a simple yet effective LLM-based SR strong baseline. Experimental results validate Symbolic-R1 as the first LLM to exceed traditional numerical methods in both numerical precision and symbolic form accuracy, outperforming the second-best LLM baseline with improvements of 2-fold gains in R2 score and 10.3% in form-level consistency score.

cs.CE↗

arXiv2025

Cluster-Level Sparse Multi-Instance Learning for Whole-Slide Images

Multi-Instance Learning (MIL) is pivotal for analyzing complex, weakly labeled datasets, such as whole-slide images (WSIs) in computational pathology, where bags comprise unordered collections of instances with sparse diagnostic relevance. Traditional MIL approaches, including early statistical methods and recent attention-based frameworks, struggle with instance redundancy and lack explicit mechanisms for discarding non-informative instances, limiting their robustness and interpretability. We propose Cluster-level Sparse MIL (csMIL), a novel framework that integrates global-local instance clustering, within-cluster attention, and cluster-level sparsity induction to address these challenges. Our csMIL first performs global clustering across all bags to establish $K$ cluster centers, followed by local clustering within each bag to assign cluster labels. Attention scores are computed within each cluster, and sparse regularization is applied to cluster weights, enabling the selective retention of diagnostically relevant clusters while discarding irrelevant ones. This approach enhances robustness to noisy instances, improves interpretability by identifying critical regions, and reduces computational complexity. Theoretical analysis demonstrates that csMIL requires $O(s log K)$ bags to recover $s$ relevant clusters, aligning with compressed sensing principles. Empirically, csMIL achieves state-of-the-art performance on two public histopathology benchmarks (CAMELYON16, TCGA-NSCLC).

cs.CV↗

arXiv2025

MICACL: Multi-Instance Category-Aware Contrastive Learning for Long-Tailed Dynamic Facial Expression Recognition

Dynamic facial expression recognition (DFER) faces significant challenges due to long-tailed category distributions and complexity of spatio-temporal feature modeling. While existing deep learning-based methods have improved DFER performance, they often fail to address these issues, resulting in severe model induction bias. To overcome these limitations, we propose a novel multi-instance learning framework called MICACL, which integrates spatio-temporal dependency modeling and long-tailed contrastive learning optimization. Specifically, we design the Graph-Enhanced Instance Interaction Module (GEIIM) to capture intricate spatio-temporal between adjacent instances relationships through adaptive adjacency matrices and multiscale convolutions. To enhance instance-level feature aggregation, we develop the Weighted Instance Aggregation Network (WIAN), which dynamically assigns weights based on instance importance. Furthermore, we introduce a Multiscale Category-aware Contrastive Learning (MCCL) strategy to balance training between major and minor categories. Extensive experiments on in-the-wild datasets (i.e., DFEW and FERV39k) demonstrate that MICACL achieves state-of-the-art performance with superior robustness and generalization.

cs.CV↗

arXiv2025

Local asymmetry in spatial interactions: A generalized slide-vector approach

The conceptualization of space is crucial for comprehending the processes that shape geographic phenomena. Functional space exhibits asymmetric spatial separations, which deviate from the symmetry axiom of metric space commonly adopted as a representation of the geographical space. However, existing literature has paid scant attention to the issue of asymmetry of spatial separation. Technically, spatial models and analysis methods grounded in a Euclidean representation of the geographical space have their capability to handle the functional space of geographical phenomena restricted by the inherency of the symmetry axiom. In this study, we aim at differentiating and characterizing the spatial dependency and heterogeneity of asymmetric spatial separations. Specifically, we propose a local slide-vector model based on spatially constrained multi-dimensional unfolding. The model takes account of spatial dependency and heterogeneity of asymmetry and can capture local asymmetric structures of spatial separations. Furthermore, we examine the dynamics of local asymmetric structures and introduce a potential field method to infer inter-regional asymmetries. To demonstrate the validity of our approach, we apply it to study the spatial separations derived from U.S. interstate migration data. Our approach sheds light on the distortion of geographic space from the perspective of migrants' relocation preferences and improves the understanding of domestic human migration patterns.

physics.soc-ph↗

arXiv2025

VLASCD: A Visual Language Action Model for Simultaneous Chatting and Decision Making

Recent large pretrained models such as LLMs (e.g., GPT series) and VLAs (e.g., OpenVLA) have achieved notable progress on multimodal tasks, yet they are built upon a multi-input single-output (MISO) paradigm. We show that this paradigm fundamentally limits performance in multi-input multi-output (MIMO) scenarios, where parallel task execution is required. In MISO architectures, tasks compete for a shared output channel, creating mutual exclusion effects that cause unbalanced optimization and degraded performance. To address this gap, we introduce MIMO-VLA (VLASCD), a unified training framework that enables concurrent multi-task outputs, exemplified by simultaneous dialogue generation and decision-making. Inspired by human cognition, MIMO-VLA eliminates interference between tasks and supports efficient parallel processing. Experiments on the CARLA autonomous driving platform demonstrate that MIMO-VLA substantially outperforms state-of-the-art MISO-based LLMs, reinforcement learning models, and VLAs in MIMO settings, establishing a new direction for multimodal and multitask learning.

cs.AI↗

arXiv2025

Graph Neural Poisson Models for Supply Chain Relationship Forecasting

In supply chain networks, firms dynamically form or dissolve partnerships to adapt to market fluctuations, posing a challenge for predicting future supply relationships. We model the occurrence of supply edges (firm i to firm j) as a non-homogeneous Poisson process (NHPP), using historical event counts to estimate the Poisson intensity function up to time t. However, forecasting future intensities is hindered by the limitations of historical data alone. To overcome this, we propose a novel Graph Double Exponential Smoothing (GDES) model, which integrates graph neural networks (GNNs) with a nonparametric double exponential smoothing approach to predict the probability of future supply edge formations.Recognizing the interdependent economic dynamics between upstream and downstream firms, we assume that the Poisson intensity functions of supply edges are correlated, aligning with the non-homogeneous nature of the process.Our model is interpretable, decomposing intensity increments into contributions from the current edge's historical data and influences from neighboring edges in the supply chain network. Evaluated on a large-scale supply chain dataset with 87,969 firms, our approach achieves an AUC of 93.84 % in dynamic link prediction, demonstrating its effectiveness in capturing complex supply chain interactions for accurate forecasting.

stat.AP↗

arXiv2025

Exploring the Link Between Bayesian Inference and Embodied Intelligence: Toward Open Physical-World Embodied AI Systems

Embodied intelligence posits that cognitive capabilities fundamentally emerge from - and are shaped by - an agent's real-time sensorimotor interactions with its environment. Such adaptive behavior inherently requires continuous inference under uncertainty. Bayesian statistics offers a principled probabilistic framework to address this challenge by representing knowledge as probability distributions and updating beliefs in response to new evidence. The core computational processes underlying embodied intelligence - including perception, action selection, learning, and even higher-level cognition - can be effectively understood and modeled as forms of Bayesian inference. Despite the deep conceptual connection between Bayesian statistics and embodied intelligence, Bayesian principles have not been widely or explicitly applied in today's embodied intelligence systems. In this work, we examine both Bayesian and contemporary embodied intelligence approaches through two fundamental lenses: search and learning - the two central themes in modern AI, as highlighted in Rich Sutton's influential essay "The Bitter Lesson". This analysis sheds light on why Bayesian inference has not played a central role in the development of modern embodied intelligence. At the same time, it reveals that current embodied intelligence systems remain largely confined to closed-physical-world environments, and highlights the potential for Bayesian methods to play a key role in extending these systems toward truly open physical-world embodied intelligence.

cs.AI↗