arXiv subjects

Yue Su

Publications and source records attributed to Yue Su.

At least 37 records · Page 2Linked to original sources

arXiv2026

World Guidance: World Modeling in Condition Space for Action Generation

Leveraging future observation modeling to facilitate action generation presents a promising avenue for enhancing the capabilities of Vision-Language-Action (VLA) models. However, existing approaches struggle to strike a balance between maintaining efficient, predictable future representations and preserving sufficient fine-grained information to guide precise action generation. To address this limitation, we propose WoG (World Guidance), a framework that maps future observations into compact conditions by injecting them into the action inference pipeline. The VLA is then trained to simultaneously predict these compressed conditions alongside future actions, thereby achieving effective world modeling within the condition space for action inference. We demonstrate that modeling and predicting this condition space not only facilitates fine-grained action generation but also exhibits superior generalization capabilities. Moreover, it learns effectively from substantial human manipulation videos. Extensive experiments across both simulation and real-world environments validate that our method significantly outperforms existing methods based on future prediction. Project page is available at: https://selen-suyue.github.io/WoGNet/

cs.RO↗

arXiv2026

Combinatorial Optimization Augmented Machine Learning

Combinatorial optimization augmented machine learning (COAML) has recently emerged as a powerful paradigm for integrating predictive models with combinatorial decision-making. By embedding combinatorial optimization oracles into learning pipelines, COAML enables the construction of policies that are both data-driven and feasibility-preserving, bridging the traditions of machine learning, operations research, and stochastic optimization. This paper provides a comprehensive overview of the state of the art in COAML. We introduce a unifying framework for COAML pipelines, describe their methodological building blocks, and formalize their connection to empirical cost minimization. We then develop a taxonomy of problem settings based on the form of uncertainty and decision structure. Using this taxonomy, we review algorithmic approaches for static and dynamic problems, survey applications across domains such as scheduling, vehicle routing, stochastic programming, and reinforcement learning, and synthesize methodological contributions in terms of empirical cost minimization, imitation learning, and reinforcement learning. Finally, we identify key research frontiers. This survey aims to serve both as a tutorial introduction to the field and as a roadmap for future research at the interface of combinatorial optimization and machine learning.

cs.LG↗

arXiv2025

$η$ and $η'$ mesons from $N_f = 2+1$ lattice QCD at the physical point using topological charge operators

By fitting the two-point correlation functions of topological charge density operators calculated on two $2+1$-flavor gauge ensembles with physical pion mass, we determine both the $η$ and $η'$ masses and also the mixing angle to be $m_η= 0.505(72)(75)$ GeV, $m_{η'}=0.952(47)(40)$ GeV, and $θ_1 = -8.9(2.1)(1.8)^\circ$, respectively, where the first error is the statistical uncertainty and the second one is the systematic uncertainty. This is the first extraction of both $η/η'$ masses and the mixing angle $θ_1$ using topological charge operators. Compared with previous studies using quark bilinear operators, the error of the $η$ mass is relatively large, but the mixing angle has comparable precision. This demonstrates that the topological charge operators are well suited to study the $η$ and $η'$ mesons.

hep-lat↗

arXiv2025

The Bi-objective Electric Autonomous Dial-a-Ride Problem

The electric autonomous dial-a-ride problem (E-ADARP) introduces electric, autonomously driving vehicles and their unique requirements into the classic dial-a-ride problem, where people are transported between pickup and drop-off locations. Next to an electric autonomous vehicle fleet, in the literature, a weighted-sum objective function, which combines the classic routing cost-oriented objective with a user-oriented objective function, has usually been considered. The user-oriented objective function minimizes the total excess user ride time. In this work, we treat them as two separate objective functions, which are optimized concurrently. In order to address the resulting bi-objective E-ADARP, we develop a novel exact framework (called fragment-based checker), whose core part is a smart ``select-and-check" algorithm that iteratively constructs feasible solutions using fragments. Several enhancements are proposed to enforce the computational efficiency of the proposed method. In the computational experiments, we evaluate several variants of our checker algorithm by leveraging a previously developed branch-and-price algorithm. We benchmark the checker-based framework against state-of-the-art criterion space frameworks as well as a generalized branch-and-price algorithm. Numerical results on both bi-objective DARP and E-ADARP instances demonstrate the effectiveness of the proposed framework. With our proposed approaches, 21 out of 38 instances are solved optimally, where small-to-medium-sized instances are solved within seconds. On larger-scale instances, especially those requiring high battery end levels are computationally challenging to solve, our approaches provide high-quality approximations of the Pareto frontiers. Efficient solutions with varying energy restrictions are compared and we obtain valuable managerial insights for different kinds of service providers.

math.OC↗

arXiv2025

Mock Observations for the CSST Mission: Multi-Channel Imager--Instrument Simulation

The Chinese Space Station Survey Telescope (CSST), a two-meter aperture astronomical space telescope under China's manned space program, is equipped with multiple back-end scientific instruments. As an astronomical precision measurement module of the CSST, the Multi-Channel Imager (MCI) can cover a wide wavelength range from ultraviolet to near-infrared with three-color simultaneous high-precision photometry and imaging, which meets the scientific requirements for various fields. The diverse scientific objectives of MCI require not only a robust airborne platform, advanced optical systems, and observing facilities but also comprehensive software support for scientific operations and research. To this end, it is essential to develop realistic observational simulation software to thoroughly evaluate the MCI data stream and provide calibration tools for future scientific investigations. The MCI instrument simulation software will serve as a foundation for the development of the MCI data processing pipeline and will facilitate improvements in both hardware and software, as well as in the observational operation strategy, in alignment with the mission's scientific goals. In conclusion, we present a comprehensive overview of the MCI instrument simulation and some corresponding performances of the MCI data processing pipeline.

astro-ph.IM↗

arXiv2025

Meta-Learning for Cross-Task Generalization in Protein Mutation Property Prediction

Protein mutations can have profound effects on biological function, making accurate prediction of property changes critical for drug discovery, protein engineering, and precision medicine. Current approaches rely on fine-tuning protein-specific transformers for individual datasets, but struggle with cross-dataset generalization due to heterogeneous experimental conditions and limited target domain data. We introduce two key innovations: (1) the first application of Model-Agnostic Meta-Learning (MAML) to protein mutation property prediction, and (2) a novel mutation encoding strategy using separator tokens to directly incorporate mutations into sequence context. We build upon transformer architectures integrating them with MAML to enable rapid adaptation to new tasks through minimal gradient steps rather than learning dataset-specific patterns. Our mutation encoding addresses the critical limitation where standard transformers treat mutation positions as unknown tokens, significantly degrading performance. Evaluation across three diverse protein mutation datasets (functional fitness, thermal stability, and solubility) demonstrates significant advantages over traditional fine-tuning. In cross-task evaluation, our meta-learning approach achieves 29% better accuracy for functional fitness with 65% less training time, and 94% better accuracy for solubility with 55% faster training. The framework maintains consistent training efficiency regardless of dataset size, making it particularly valuable for industrial applications and early-stage protein design where experimental data is limited. This work establishes a systematic application of meta-learning to protein mutation analysis and introduces an effective mutation encoding strategy, offering transformative methodology for cross-domain generalization in protein engineering.

cs.LG↗

arXiv2025

DSPv2: Improved Dense Policy for Effective and Generalizable Whole-body Mobile Manipulation

Learning whole-body mobile manipulation via imitation is essential for generalizing robotic skills to diverse environments and complex tasks. However, this goal is hindered by significant challenges, particularly in effectively processing complex observation, achieving robust generalization, and generating coherent actions. To address these issues, we propose DSPv2, a novel policy architecture. DSPv2 introduces an effective encoding scheme that aligns 3D spatial features with multi-view 2D semantic features. This fusion enables the policy to achieve broad generalization while retaining the fine-grained perception necessary for precise control. Furthermore, we extend the Dense Policy paradigm to the whole-body mobile manipulation domain, demonstrating its effectiveness in generating coherent and precise actions for the whole-body robotic platform. Extensive experiments show that our method significantly outperforms existing approaches in both task performance and generalization ability. Project page is available at: https://selen-suyue.github.io/DSPv2Net/.

cs.RO↗

arXiv2025

S-Leak: Leakage-Abuse Attack Against Efficient Conjunctive SSE via s-term Leakage

Conjunctive Searchable Symmetric Encryption (CSSE) enables secure conjunctive searches over encrypted data. While leakage-abuse attacks (LAAs) against single-keyword SSE have been extensively studied, their extension to conjunctive queries faces a critical challenge: the combinatorial explosion of candidate keyword combinations, leading to enormous time and space overhead for attacks. In this paper, we reveal a fundamental vulnerability in state-of-the-art CSSE schemes: s-term leakage, where the keyword with the minimal document frequency in a query leaks distinct patterns. We propose S-Leak, the first passive attack framework that progressively recovers conjunctive queries by exploiting s-term leakage and global leakage. Our key innovation lies in a three-stage approach: identifying the s-term of queries, pruning low-probability keyword conjunctions, and reconstructing full queries. We propose novel metrics to better assess attacks in conjunctive query scenarios. Empirical evaluations on real-world datasets demonstrate that our attack is effective in diverse CSSE configurations. When considering 161,700 conjunctive keyword queries, our attack achieves a 95.15% accuracy in recovering at least one keyword, 82.57% for at least two, 58% for all three keywords, and maintains efficacy against defenses such as SEAL padding and CLRZ obfuscation. Our work exposes the underestimated risks of s-term leakage in practical SSE deployments and calls for a redesign of leakage models for multi-keyword search scenarios.

cs.CR↗

arXiv2025

Tuning Incommensurate Charge Order in Ba$_{1-x}$Sr$_x$Al$_4$ and Ba$_{1-y}$Eu$_y$Al$_4$

The BaAl$_4$-type structure family is home to a vast landscape of interesting and exotic properties, with descendant crystal structures hosting a variety of electronic ground states including magnetic, superconducting and strongly correlated electron phenomena. BaAl$_4$ itself hosts a non-trivial topological band structure, but is otherwise a paramagnetic metal. However, the other members of the $A$Al$_4$ family ($A$= alkali earth), including SrAl$_4$ and EuAl$_4$, exhibit symmetry-breaking ground states including charge density wave (CDW) and magnetic orders. Here we investigate the properties of the solid solution series Ba$_{1-x}$Sr$_x$Al$_4$ and Ba$_{1-y}$Eu$_y$Al$_4$ using transport, thermodynamic and scattering experiments to study the evolution of the charge-ordered state as it is suppressed with Ba substitution to zero near 50% substitution in both systems. Neutron and x-ray diffraction measurements reveal an incommensurate CDW state in SrAl$_4$ with $c$-axis-oriented ordering vector (0, 0, 0.097) that evolves with Ba substitution toward a shorter wavelength. A similar progression is observed in the Ba$_{1-y}$Eu$_y$Al$_4$ series that also scales with the ordering temperature, revealing a universal correlation between charge-order transition temperature and ordering vector that points to a critical wavevector that stabilizes CDW order in both systems. We study the evolution of the phonon band structure in the Ba$_{1-x}$Sr$_x$Al$_4$ system, revealing the suppression of the CDW phase matches the suppression of a phonon instability at precisely the same momentum as observed in experiments, confirming the electron-phonon origin of charge order in this system.

cond-mat.str-el↗

arXiv2025

SafeScientist: Toward Risk-Aware Scientific Discoveries by LLM Agents

Recent advancements in large language model (LLM) agents have significantly accelerated scientific discovery automation, yet concurrently raised critical ethical and safety concerns. To systematically address these challenges, we introduce \textbf{SafeScientist}, an innovative AI scientist framework explicitly designed to enhance safety and ethical responsibility in AI-driven scientific exploration. SafeScientist proactively refuses ethically inappropriate or high-risk tasks and rigorously emphasizes safety throughout the research process. To achieve comprehensive safety oversight, we integrate multiple defensive mechanisms, including prompt monitoring, agent-collaboration monitoring, tool-use monitoring, and an ethical reviewer component. Complementing SafeScientist, we propose \textbf{SciSafetyBench}, a novel benchmark specifically designed to evaluate AI safety in scientific contexts, comprising 240 high-risk scientific tasks across 6 domains, alongside 30 specially designed scientific tools and 120 tool-related risk tasks. Extensive experiments demonstrate that SafeScientist significantly improves safety performance by 35\% compared to traditional AI scientist frameworks, without compromising scientific output quality. Additionally, we rigorously validate the robustness of our safety pipeline against diverse adversarial attack methods, further confirming the effectiveness of our integrated approach. The code and data will be available at https://github.com/ulab-uiuc/SafeScientist. \textcolor{red}{Warning: this paper contains example data that may be offensive or harmful.}

cs.AI↗

arXiv2025

Motion Before Action: Diffusing Object Motion as Manipulation Condition

Inferring object motion representations from observations enhances the performance of robotic manipulation tasks. This paper introduces a new paradigm for robot imitation learning that generates action sequences by reasoning about object motion from visual observations. We propose MBA (Motion Before Action), a novel module that employs two cascaded diffusion processes for object motion generation and robot action generation under object motion guidance. MBA first predicts the future pose sequence of the object based on observations, then uses this sequence as a condition to guide robot action generation. Designed as a plug-and-play component, MBA can be flexibly integrated into existing robotic manipulation policies with diffusion action heads. Extensive experiments in both simulated and real-world environments demonstrate that our approach substantially improves the performance of existing policies across a wide range of manipulation tasks. Project page: https://selen-suyue.github.io/MBApage/

cs.RO↗

arXiv2025

Dense Policy: Bidirectional Autoregressive Learning of Actions

Mainstream visuomotor policies predominantly rely on generative models for holistic action prediction, while current autoregressive policies, predicting the next token or chunk, have shown suboptimal results. This motivates a search for more effective learning methods to unleash the potential of autoregressive policies for robotic manipulation. This paper introduces a bidirectionally expanded learning approach, termed Dense Policy, to establish a new paradigm for autoregressive policies in action prediction. It employs a lightweight encoder-only architecture to iteratively unfold the action sequence from an initial single frame into the target sequence in a coarse-to-fine manner with logarithmic-time inference. Extensive experiments validate that our dense policy has superior autoregressive learning capabilities and can surpass existing holistic generative policies. Our policy, example data, and training code will be publicly available upon publication. Project page: https: //selen-suyue.github.io/DspNet/.

cs.RO↗

arXiv2025

A Low-cost and Ultra-lightweight Binary Neural Network for Traffic Signal Recognition

The deployment of neural networks in vehicle platforms and wearable Artificial Intelligence-of-Things (AIOT) scenarios has become a research area that has attracted much attention. With the continuous evolution of deep learning technology, many image classification models are committed to improving recognition accuracy, but this is often accompanied by problems such as large model resource usage, complex structure, and high power consumption, which makes it challenging to deploy on resource-constrained platforms. Herein, we propose an ultra-lightweight binary neural network (BNN) model designed for hardware deployment, and conduct image classification research based on the German Traffic Sign Recognition Benchmark (GTSRB) dataset. In addition, we also verify it on the Chinese Traffic Sign (CTS) and Belgian Traffic Sign (BTS) datasets. The proposed model shows excellent recognition performance with an accuracy of up to 97.64%, making it one of the best performing BNN models in the GTSRB dataset. Compared with the full-precision model, the accuracy loss is controlled within 1%, and the parameter storage overhead of the model is only 10% of that of the full-precision model. More importantly, our network model only relies on logical operations and low-bit width fixed-point addition and subtraction operations during the inference phase, which greatly simplifies the design complexity of the processing element (PE). Our research shows the great potential of BNN in the hardware deployment of computer vision models, especially in the field of computer vision tasks related to autonomous driving.

cs.AI↗

arXiv2024

Generative Adversarial Patches for Physical Attacks on Cross-Modal Pedestrian Re-Identification

Visible-infrared pedestrian Re-identification (VI-ReID) aims to match pedestrian images captured by infrared cameras and visible cameras. However, VI-ReID, like other traditional cross-modal image matching tasks, poses significant challenges due to its human-centered nature. This is evidenced by the shortcomings of existing methods, which struggle to extract common features across modalities, while losing valuable information when bridging the gap between them in the implicit feature space, potentially compromising security. To address this vulnerability, this paper introduces the first physical adversarial attack against VI-ReID models. Our method, termed Edge-Attack, specifically tests the models' ability to leverage deep-level implicit features by focusing on edge information, the most salient explicit feature differentiating individuals across modalities. Edge-Attack utilizes a novel two-step approach. First, a multi-level edge feature extractor is trained in a self-supervised manner to capture discriminative edge representations for each individual. Second, a generative model based on Vision Transformer Generative Adversarial Networks (ViTGAN) is employed to generate adversarial patches conditioned on the extracted edge features. By applying these patches to pedestrian clothing, we create realistic, physically-realizable adversarial samples. This black-box, self-supervised approach ensures the generalizability of our attack against various VI-ReID models. Extensive experiments on SYSU-MM01 and RegDB datasets, including real-world deployments, demonstrate the effectiveness of Edge- Attack in significantly degrading the performance of state-of-the-art VI-ReID methods.

cs.CV↗

arXiv2024

Terahertz channel modeling based on surface sensing characteristics

The dielectric properties of environmental surfaces, including walls, floors and the ground, etc., play a crucial role in shaping the accuracy of terahertz (THz) channel modeling, thereby directly impacting the effectiveness of communication systems. Traditionally, acquiring these properties has relied on methods such as terahertz time-domain spectroscopy (THz-TDS) or vector network analyzers (VNA), demanding rigorous sample preparation and entailing a significant expenditure of time. However, such measurements are not always feasible, particularly in novel and uncharacterized scenarios. In this work, we propose a new approach for channel modeling that leverages the inherent sensing capabilities of THz channels. By comparing the results obtained through channel sensing with that derived from THz-TDS measurements, we demonstrate the method's ability to yield dependable surface property information. The application of this approach in both a miniaturized cityscape scenario and an indoor environment has shown consistency with experimental measurements, thereby verifying its effectiveness in real-world settings.

physics.app-ph↗

arXiv2024

A Branch-and-Price Algorithm for the Electric Autonomous Dial-A-Ride Problem

The Electric Autonomous Dial-A-Ride Problem (E-ADARP) consists in scheduling a fleet of electric autonomous vehicles to provide ride-sharing services for customers that specify their origins and destinations. The E-ADARP differs from the classical DARP in two aspects: (i) a weighted-sum objective that minimizes both total travel time and total excess user ride time; (ii) the employment of electric autonomous vehicles and a partial recharging policy. This paper presents a highly-efficient labeling algorithm, which is integrated into Branch-and-Price (B&P) algorithms to solve the E-ADARP. To handle (i), we introduce a fragment-based representation of paths. A novel approach is invoked to abstract fragments to arcs while ensuring excess-user-ride-time optimality. We then construct a new graph that preserves all feasible routes of the original graph by enumerating all feasible fragments, abstracting them to arcs, and connecting them with each other, depots, and recharging stations in a feasible way. On the new graph, partial recharging (ii) is tackled exactly by tailored Resource Extension Functions (REFs). We apply strong dominance rules and constant-time feasibility checks to compute the shortest paths efficiently. These methods construct the first labeling algorithm that can deal with minimizing (excess) user ride time. In the computational experiments, the B&P algorithm achieves optimality in 71 out of 84 instances. Remarkably, among these instances, 50 were solved optimally at the root node without branching. We identify 26 new best solutions, improve 30 previously reported lower bounds, and provide 17 new lower bounds for large-scale instances with up to 8 vehicles and 96 requests. In total 42 new best solutions are generated on previously solved and unsolved instances.

math.OC↗

arXiv2023

Two classes of reducible cyclic codes with large minimum symbol-pair distances

The high-density data storage technology aims to design high-capacity storage at a relatively low cost. In order to achieve this goal, symbol-pair codes were proposed by Cassuto and Blaum \cite{CB10,CB11} to handle channels that output pairs of overlapping symbols. Such a channel is called symbol-pair read channel, which introduce new concept called symbol-pair weight and minimum symbol-pair distance. In this paper, we consider the parameters of two classes of reducible cyclic codes under the symbol-pair metric. Based on the theory of cyclotomic numbers and Gaussian period over finite fields, we show the possible symbol-pair weights of these codes. Their minimum symbol-pair distances are twice the minimum Hamming distances under some conditions. Moreover, we obtain some three symbol-pair weight codes and determine their symbol-pair weight distribution. A class of MDS symbol-pair codes is also established. Among other results, we determine the values of some generalized cyclotomic numbers.

cs.IT↗

arXiv2023

A Deterministic Annealing Local Search for the Electric Autonomous Dial-A-Ride Problem

This paper investigates the Electric Autonomous Dial-A-Ride Problem (E-ADARP), which consists in designing a set of minimum-cost routes that accommodates all customer requests for a fleet of Electric Autonomous Vehicles (EAVs). Problem-specific features of the E-ADARP include: (i) the employment of EAVs and a partial recharging policy; (ii) the weighted-sum objective function that minimizes the total travel time and the total excess user ride time. In this work, we propose a Deterministic Annealing (DA) algorithm and provide the first heuristic results for the static E-ADARP. Partial recharging (i) is handled by an exact route evaluation scheme of linear time complexity. To tackle (ii), we propose a new method that allows effective computations of minimum excess user ride time by introducing a fragment-based representation of paths. These two methods compose an exact and efficient optimization of excess user ride time for a generated E-ADARP route. To validate the performance of the DA algorithm, we compare our algorithm results to the best-reported Branch-and-Cut (B\&C) algorithm results on existing instances. Our algorithm provides 25 new best solutions and 45 equal solutions on 84 existing instances. To test the algorithm performance on larger-sized instances, we establish new instances with up to 8 vehicles and 96 requests, and we provide 19 new solutions for these instances. Our final investigation extends the state-of-the-art model and explores the effect of allowing multiple visits to recharging stations. This relaxation can efficiently improve the solution's feasibility and quality.

math.OC↗