arXiv subjects

Junkai Zhang

Publications and source records attributed to Junkai Zhang.

At least 37 records · Page 2Linked to original sources

arXiv2025

Synergistic Antenna-Modulator Integration for Monolithic Photonic RF Receiver

Integrated radio-frequency (RF) photonics plays a pivotal role in wireless communications, sensing, and radar due to its large intrinsic bandwidth, remote distribution capability, and compact footprint. However, despite significant advances in photonic integrated circuits (PICs), the practical deployment of these systems remains constrained by the bulky nature of essential RF components (e.g., bulky antennas, amplifiers, and cables), especially in covert, conformal, and space-constrained applications. To overcome these limitations, monolithic electronic-photonic integrated circuits (EPICs), enabling miniaturized and synergistic integration of both RF and photonic components, are gaining notable attention. As a groundbreaking advancement, we demonstrate a novel photonic RF receiver that monolithically integrates a bow-tie antenna and a microring modulator on a thin-film lithium niobate platform. The chip innovatively leverages dual-resonance enhancement mechanism, RF resonance from the antenna and optical resonance from the microring, to significantly boost the RF-to-optical conversion efficiency. A record-high figure of merit (FOM) of 3.88 W-1/2 is achieved within a compact footprint of 2*1.7 mm2. As the first demonstrations, the integrated receiver is deployed in an integrated sensing and communication (ISAC) system, achieving centimeter-level radar ranging accuracy and 3.2 Gbps wireless communication capacity, as well as real-time video transmission function in moving scenarios. This seminal work paves a new way for covert, conformal, and miniaturized frontends in wireless communication and sensing applications, including body area networks, unmanned aerial vehicles, high-speed vacuum maglevs, and electronic warfare systems.

physics.optics↗

arXiv2025

DynamicPAE: Generating Scene-Aware Physical Adversarial Examples in Real-Time

Physical adversarial examples (PAEs) are regarded as whistle-blowers of real-world risks in deep-learning applications, thus worth further investigation. However, current PAE generation studies show limited adaptive attacking ability to diverse and varying scenes, revealing the urgent requirement of dynamic PAEs that are generated in real time and conditioned on the observation from the attacker. The key challenge in generating dynamic PAEs is learning the sparse relation between PAEs and the observation of attackers under the noisy feedback of attack training. To address the challenge, we present DynamicPAE, the first generative framework that enables scene-aware real-time physical attacks. Specifically, to address the noisy feedback problem that obfuscates the exploration of scene-related PAEs, we introduce the residual-guided adversarial pattern exploration technique. Residual-guided training, which relaxes the attack training with a reconstruction task, is proposed to enrich the feedback information, thereby achieving a more comprehensive exploration of PAEs. To address the alignment problem between the trained generator and the real-world scenario, we introduce the distribution-matched attack scenario alignment, consisting of the conditional-uncertainty-aligned data module and the skewness-aligned objective re-weighting module. The former aligns the training environment with the incomplete observation of the real-world attacker. The latter facilitates consistent stealth control across different attack targets with the skewness controller. Extensive digital and physical evaluations demonstrate the superior attack performance of DynamicPAE, attaining a 2.07 $\times$ boost (58.8% average AP drop under attack) on representative object detectors (e.g., DETR) over state-of-the-art static PAE generating methods. Overall, our work opens the door to end-to-end modeling of dynamic PAEs.

cs.CV↗

arXiv2025

Static Retrieval Revisited: To Optimality and Beyond

In the static retrieval problem, a data structure must answer retrieval queries mapping a set of $n$ keys in a universe $[U]$ to $v$-bit values. Information-theoretically, retrieval data structures can use as little as $nv$ bits of space. For small value sizes $v$, it is possible to achieve $O(1)$ query time while using space $nv + o(n)$ bits -- whether or not such a result is possible for larger values of $v$ (e.g., $v = Θ(\log n)$) has remained open. In this paper, we obtain a tight lower bound (as well as matching upper bounds) for the static retrieval problem. In the case where values are large, we show that there is actually a significant tension between time and space. It is not possible, for example, to get $O(1)$ query time using $nv + o(n)$ bits of space, when $v = Θ(\log n)$ (and assuming the word RAM model with $O(\log n)$-bit words). At first glance, our lower bound would seem to render retrieval unusable in many settings that aim to achieve very low redundancy. However, our second result offers a way around this: We show that, whenever a retrieval data structure $D_1$ is stored along with another data structure $D_2$ (whose size is similar to or larger than the size of $D_1$), it is possible to implement the combined data structure $D_1 \cup D_2$ so that queries to $D_1$ take $O(1)$ time, operations on $D_2$ take the same asymptotic time as if $D_2$ were stored on its own, and the total space is $nv + \mathrm{Space}(D_2) + n^{0.67}$ bits.

cs.DS↗

arXiv2025

HyP-ASO: A Hybrid Policy-based Adaptive Search Optimization Framework for Large-Scale Integer Linear Programs

Directly solving large-scale Integer Linear Programs (ILPs) using traditional solvers is slow due to their NP-hard nature. While recent frameworks based on Large Neighborhood Search (LNS) can accelerate the solving process, their performance is often constrained by the difficulty in generating sufficiently effective neighborhoods. To address this challenge, we propose HyP-ASO, a hybrid policy-based adaptive search optimization framework that combines a customized formula with deep Reinforcement Learning (RL). The formula leverages feasible solutions to calculate the selection probabilities for each variable in the neighborhood generation process, and the RL policy network predicts the neighborhood size. Extensive experiments demonstrate that HyP-ASO significantly outperforms existing LNS-based approaches for large-scale ILPs. Additional experiments show it is lightweight and highly scalable, making it well-suited for solving large-scale ILPs.

cs.LG↗

arXiv2025

WebShaper: Agentically Data Synthesizing via Information-Seeking Formalization

The advent of Large Language Model (LLM)-powered agents has revolutionized artificial intelligence by enabling solutions to complex, open-ended tasks through web-based information-seeking (IS) capabilities. The scarcity of high-quality training data has limited the development of IS agents. Existing approaches typically adopt an information-driven paradigm that first collects web data and then generates questions based on the retrieval. However, this may lead to inconsistency between information structure and reasoning structure, question and answer. To mitigate, we propose a formalization-driven IS data synthesis framework WebShaper to construct a dataset. WebShaper systematically formalizes IS tasks through set theory. Central to the formalization is the concept of Knowledge Projections (KP), which enables precise control over reasoning structure by KP operation compositions. During synthesis, we begin by creating seed tasks, then use a multi-step expansion process. At each step, an agentic Expander expands the current formal question more complex with retrieval and validation tools based on our formalization. We train our model on the synthesized dataset. Experiment results demonstrate that WebShaper achieves state-of-the-art performance among open-sourced IS agents on GAIA and WebWalkerQA benchmarks.

cs.CL↗

arXiv2025

WebSailor: Navigating Super-human Reasoning for Web Agent

Transcending human cognitive limitations represents a critical frontier in LLM training. Proprietary agentic systems like DeepResearch have demonstrated superhuman capabilities on extremely complex information-seeking benchmarks such as BrowseComp, a feat previously unattainable. We posit that their success hinges on a sophisticated reasoning pattern absent in open-source models: the ability to systematically reduce extreme uncertainty when navigating vast information landscapes. Based on this insight, we introduce WebSailor, a complete post-training methodology designed to instill this crucial capability. Our approach involves generating novel, high-uncertainty tasks through structured sampling and information obfuscation, RFT cold start, and an efficient agentic RL training algorithm, Duplicating Sampling Policy Optimization (DUPO). With this integrated pipeline, WebSailor significantly outperforms all opensource agents in complex information-seeking tasks, matching proprietary agents' performance and closing the capability gap.

cs.CL↗

arXiv2025

Step-Opt: Boosting Optimization Modeling in LLMs through Iterative Data Synthesis and Structured Validation

Large Language Models (LLMs) have revolutionized various domains but encounter substantial challenges in tackling optimization modeling tasks for Operations Research (OR), particularly when dealing with complex problem. In this work, we propose Step-Opt-Instruct, a framework that augments existing datasets and generates high-quality fine-tuning data tailored to optimization modeling. Step-Opt-Instruct employs iterative problem generation to systematically increase problem complexity and stepwise validation to rigorously verify data, preventing error propagation and ensuring the quality of the generated dataset. Leveraging this framework, we fine-tune open-source LLMs, including LLaMA-3-8B and Mistral-7B, to develop Step-Opt--a model that achieves state-of-the-art performance on benchmarks such as NL4OPT, MAMO, and IndustryOR. Extensive experiments demonstrate the superior performance of Step-Opt, especially in addressing complex OR tasks, with a notable 17.01\% improvement in micro average accuracy on difficult problems. These findings highlight the effectiveness of combining structured validation with gradual problem refinement to advance the automation of decision-making processes using LLMs.The code and dataset are available at https://github.com/samwu-learn/Step.

cs.CL↗

arXiv2025

Adaptive Implicit-Based Deep Learning Channel Estimation for 6G Communications

With the widespread deployment of fifth-generation (5G) wireless networks, research on sixth-generation (6G) technology is gaining momentum. Artificial Intelligence (AI) is anticipated to play a significant role in 6G, particularly through integration with the physical layer for tasks such as channel estimation. Considering resource limitations in real systems, the AI algorithm should be designed to have the ability to balance the accuracy and resource consumption according to the scenarios dynamically. However, conventional explicit multilayer-stacked Deep Learning (DL) models struggle to adapt due to their heavy reliance on the structure of deep neural networks. This article proposes an adaptive Implicit-layer DL Channel Estimation Network (ICENet) with a lightweight framework for vehicle-to-everything communications. This novel approach balances computational complexity and channel estimation accuracy by dynamically adjusting computational resources based on input data conditions, such as channel quality. Unlike explicit multilayer-stacked DL-based channel estimation models, ICENet offers a flexible framework, where specific requirements can be achieved by adaptively changing the number of iterations of the iterative layer. Meanwhile, ICENet requires less memory while maintaining high performance. The article concludes by highlighting open research challenges and promising future research directions.

cs.IT↗

arXiv2025

MetamatBench: Integrating Heterogeneous Data, Computational Tools, and Visual Interface for Metamaterial Discovery

Metamaterials, engineered materials with architected structures across multiple length scales, offer unprecedented and tunable mechanical properties that surpass those of conventional materials. However, leveraging advanced machine learning (ML) for metamaterial discovery is hindered by three fundamental challenges: (C1) Data Heterogeneity Challenge arises from heterogeneous data sources, heterogeneous composition scales, and heterogeneous structure categories; (C2) Model Complexity Challenge stems from the intricate geometric constraints of ML models, which complicate their adaptation to metamaterial structures; and (C3) Human-AI Collaboration Challenge comes from the "dual black-box'' nature of sophisticated ML models and the need for intuitive user interfaces. To tackle these challenges, we introduce a unified framework, named MetamatBench, that operates on three levels. (1) At the data level, we integrate and standardize 5 heterogeneous, multi-modal metamaterial datasets. (2) The ML level provides a comprehensive toolkit that adapts 17 state-of-the-art ML methods for metamaterial discovery. It also includes a comprehensive evaluation suite with 12 novel performance metrics with finite element-based assessments to ensure accurate and reliable model validation. (3) The user level features a visual-interactive interface that bridges the gap between complex ML techniques and non-ML researchers, advancing property prediction and inverse design of metamaterials for research and applications. MetamatBench offers a unified platform deployed at http://zhoulab-1.cs.vt.edu:5550 that enables machine learning researchers and practitioners to develop and evaluate new methodologies in metamaterial discovery. For accessibility and reproducibility, we open-source our benchmark and the codebase at https://github.com/cjpcool/Metamaterial-Benchmark.

physics.optics↗

arXiv2025

Hierarchical Modeling for Medical Visual Question Answering with Cross-Attention Fusion

Medical Visual Question Answering (Med-VQA) answers clinical questions using medical images, aiding diagnosis. Designing the MedVQA system holds profound importance in assisting clinical diagnosis and enhancing diagnostic accuracy. Building upon this foundation, Hierarchical Medical VQA extends Medical VQA by organizing medical questions into a hierarchical structure and making level-specific predictions to handle fine-grained distinctions. Recently, many studies have proposed hierarchical MedVQA tasks and established datasets, However, several issues still remain: (1) imperfect hierarchical modeling leads to poor differentiation between question levels causing semantic fragmentation across hierarchies. (2) Excessive reliance on implicit learning in Transformer-based cross-modal self-attention fusion methods, which obscures crucial local semantic correlations in medical scenarios. To address these issues, this study proposes a HiCA-VQA method, including two modules: Hierarchical Prompting for fine-grained medical questions and Hierarchical Answer Decoders. The hierarchical prompting module pre-aligns hierarchical text prompts with image features to guide the model in focusing on specific image regions according to question types, while the hierarchical decoder performs separate predictions for questions at different levels to improve accuracy across granularities. The framework also incorporates a cross-attention fusion module where images serve as queries and text as key-value pairs. Experiments on the Rad-Restruct benchmark demonstrate that the HiCA-VQA framework better outperforms existing state-of-the-art methods in answering hierarchical fine-grained questions. This study provides an effective pathway for hierarchical visual question answering systems, advancing medical image understanding.

cs.CV↗

arXiv2025

Optimal Static Dictionary with Worst-Case Constant Query Time

In this paper, we design a new succinct static dictionary with worst-case constant query time. A dictionary data structure stores a set of key-value pairs with distinct keys in $[U]$ and values in $[σ]$, such that given a query $x\in [U]$, it quickly returns if $x$ is one of the input keys, and if so, also returns its associated value. The textbook solution to dictionaries is hash tables. On the other hand, the (information-theoretical) optimal space to encode such a set of key-value pairs is only $\text{OPT} := \log\binom{U}{n}+n\log σ$. We construct a dictionary that uses $\text{OPT} + n^ε$ bits of space, and answers queries in constant time in worst case. Previously, constant-time dictionaries are only known with $\text{OPT} + n/\text{poly}\log n$ space [Pǎtraşcu 2008], or with $\text{OPT}+n^ε$ space but expected constant query time [Yu 2020]. We emphasize that most of the extra $n^ε$ bits are used to store a lookup table that does not depend on the input, and random bits for hash functions. The "main" data structure only occupies $\text{OPT}+\text{poly}\log n$ bits.

cs.DS↗

arXiv2025

Protein Large Language Models: A Comprehensive Survey

Protein-specific large language models (Protein LLMs) are revolutionizing protein science by enabling more efficient protein structure prediction, function annotation, and design. While existing surveys focus on specific aspects or applications, this work provides the first comprehensive overview of Protein LLMs, covering their architectures, training datasets, evaluation metrics, and diverse applications. Through a systematic analysis of over 100 articles, we propose a structured taxonomy of state-of-the-art Protein LLMs, analyze how they leverage large-scale protein sequence data for improved accuracy, and explore their potential in advancing protein engineering and biomedical research. Additionally, we discuss key challenges and future directions, positioning Protein LLMs as essential tools for scientific discovery in protein science. Resources are maintained at https://github.com/Yijia-Xiao/Protein-LLM-Survey.

q-bio.BM↗

arXiv2024

MetaScientist: A Human-AI Synergistic Framework for Automated Mechanical Metamaterial Design

The discovery of novel mechanical metamaterials, whose properties are dominated by their engineered structures rather than chemical composition, is a knowledge-intensive and resource-demanding process. To accelerate the design of novel metamaterials, we present MetaScientist, a human-in-the-loop system that integrates advanced AI capabilities with expert oversight with two primary phases: (1) hypothesis generation, where the system performs complex reasoning to generate novel and scientifically sound hypotheses, supported with domain-specific foundation models and inductive biases retrieved from existing literature; (2) 3D structure synthesis, where a 3D structure is synthesized with a novel 3D diffusion model based on the textual hypothesis and refined it with a LLM-based refinement model to achieve better structure properties. At each phase, domain experts iteratively validate the system outputs, and provide feedback and supplementary materials to ensure the alignment of the outputs with scientific principles and human preferences. Through extensive evaluation from human scientists, MetaScientist is able to deliver novel and valid mechanical metamaterial designs that have the potential to be highly impactful in the metamaterial field.

cs.AI↗

arXiv2024

Fast Sampling via Discrete Non-Markov Diffusion Models with Predetermined Transition Time

Discrete diffusion models have emerged as powerful tools for high-quality data generation. Despite their success in discrete spaces, such as text generation tasks, the acceleration of discrete diffusion models remains under-explored. In this paper, we propose discrete non-Markov diffusion models (DNDM), which naturally induce the predetermined transition time set. This enables a training-free sampling algorithm that significantly reduces the number of function evaluations (i.e., calls to the neural network), making the sampling process much faster. Furthermore, we study the transition from finite to infinite step sampling, offering new insights into bridging the gap between discrete and continuous-time processes for discrete diffusion models. Extensive experiments on natural language generation and machine translation tasks demonstrate the superior performance of our method in terms of both generation speed and sample quality compared to existing methods for discrete diffusion models.

cs.LG↗

arXiv2024

Intrinsic Action Tendency Consistency for Cooperative Multi-Agent Reinforcement Learning

Efficient collaboration in the centralized training with decentralized execution (CTDE) paradigm remains a challenge in cooperative multi-agent systems. We identify divergent action tendencies among agents as a significant obstacle to CTDE's training efficiency, requiring a large number of training samples to achieve a unified consensus on agents' policies. This divergence stems from the lack of adequate team consensus-related guidance signals during credit assignments in CTDE. To address this, we propose Intrinsic Action Tendency Consistency, a novel approach for cooperative multi-agent reinforcement learning. It integrates intrinsic rewards, obtained through an action model, into a reward-additive CTDE (RA-CTDE) framework. We formulate an action model that enables surrounding agents to predict the central agent's action tendency. Leveraging these predictions, we compute a cooperative intrinsic reward that encourages agents to match their actions with their neighbors' predictions. We establish the equivalence between RA-CTDE and CTDE through theoretical analyses, demonstrating that CTDE's training process can be achieved using agents' individual targets. Building on this insight, we introduce a novel method to combine intrinsic rewards and CTDE. Extensive experiments on challenging tasks in SMAC and GRF benchmarks showcase the improved performance of our method.

cs.MA↗

arXiv2024

Uncertainty-Aware Reward-Free Exploration with General Function Approximation

Mastering multiple tasks through exploration and learning in an environment poses a significant challenge in reinforcement learning (RL). Unsupervised RL has been introduced to address this challenge by training policies with intrinsic rewards rather than extrinsic rewards. However, current intrinsic reward designs and unsupervised RL algorithms often overlook the heterogeneous nature of collected samples, thereby diminishing their sample efficiency. To overcome this limitation, in this paper, we propose a reward-free RL algorithm called \alg. The key idea behind our algorithm is an uncertainty-aware intrinsic reward for exploring the environment and an uncertainty-weighted learning process to handle heterogeneous uncertainty in different samples. Theoretically, we show that in order to find an $ε$-optimal policy, GFA-RFE needs to collect $\tilde{O} (H^2 \log N_{\mathcal F} (ε) \mathrm{dim} (\mathcal F) / ε^2 )$ number of episodes, where $\mathcal F$ is the value function class with covering number $N_{\mathcal F} (ε)$ and generalized eluder dimension $\mathrm{dim} (\mathcal F)$. Such a result outperforms all existing reward-free RL algorithms. We further implement and evaluate GFA-RFE across various domains and tasks in the DeepMind Control Suite. Experiment results show that GFA-RFE outperforms or is comparable to the performance of state-of-the-art unsupervised RL algorithms.

cs.LG↗

arXiv2024

Visualizing the Shadows: Unveiling Data Poisoning Behaviors in Federated Learning

This demo paper examines the susceptibility of Federated Learning (FL) systems to targeted data poisoning attacks, presenting a novel system for visualizing and mitigating such threats. We simulate targeted data poisoning attacks via label flipping and analyze the impact on model performance, employing a five-component system that includes Simulation and Data Generation, Data Collection and Upload, User-friendly Interface, Analysis and Insight, and Advisory System. Observations from three demo modules: label manipulation, attack timing, and malicious attack availability, and two analysis components: utility and analytical behavior of local model updates highlight the risks to system integrity and offer insight into the resilience of FL systems. The demo is available at https://github.com/CathyXueqingZhang/DataPoisoningVis.

cs.CR↗

arXiv2024

Performance Analysis of In-Band-Full-Duplex Multi-Cell Wideband IAB Networks

This paper analyzes the performance of the 3rd Generation Partnership Project (3GPP)-inspired multi-cell wideband single-hop backhaul millimeter-wave-in-band-full-duplex (IBFD)-integrated access and backhaul (IAB) networks by using stochastic geometry. We model the wired-connected Next Generation NodeBs (gNBs) as the Matérn hard-core point process (MHCPP) to meet the real-world deployment requirement and reduce the cost caused by wired connection in the network. We first derive association probabilities that reflect how likely the typical user-equipment is served by a gNB or an IAB-node based on the maximum long-term averaged biased-received-desired-signal power criteria. Further, by leveraging the composite Gamma-Lognormal distribution, we derive the closed-form signal to interference plus noise ratio coverage, capacity with outage, and ergodic capacity of the network. In order to avoid underestimating the noise, we consider the sidelobe gain on inter-cell interference links and the analog to digital converter quantization noise. Compared with the half-duplex transmission, numerical results show an enhanced capacity with outage and ergodic capacity provided by IBFD under successful self-interference cancellation. We also study how the power bias and density ratio of the IAB-node to gNB, and the hard-core distance can affect system performances.

cs.IT↗