arXiv subjects

Yu Yan

Publications and source records attributed to Yu Yan.

At least 37 records · Page 2Linked to original sources

arXiv2025

RT-DETRv4: Painlessly Furthering Real-Time Object Detection with Vision Foundation Models

Real-time object detection has achieved substantial progress through meticulously designed architectures and optimization strategies. However, the pursuit of high-speed inference via lightweight network designs often leads to degraded feature representation, which hinders further performance improvements and practical on-device deployment. In this paper, we propose a cost-effective and highly adaptable distillation framework that harnesses the rapidly evolving capabilities of Vision Foundation Models (VFMs) to enhance lightweight object detectors. Given the significant architectural and learning objective disparities between VFMs and resource-constrained detectors, achieving stable and task-aligned semantic transfer is challenging. To address this, on one hand, we introduce a Deep Semantic Injector (DSI) module that facilitates the integration of high-level representations from VFMs into the deep layers of the detector. On the other hand, we devise a Gradient-guided Adaptive Modulation (GAM) strategy, which dynamically adjusts the intensity of semantic transfer based on gradient norm ratios. Without increasing deployment and inference overhead, our approach painlessly delivers striking and consistent performance gains across diverse DETR-based models, underscoring its practical utility for real-time detection. Our new model family, RT-DETRv4, achieves state-of-the-art results on COCO, attaining AP scores of 49.7/53.5/55.4/57.0 at corresponding speeds of 273/169/124/78 FPS.

cs.CV↗

arXiv2025

Has the Two-Decade-Old Prophecy Come True? Artificial Bad Intelligence Triggered by Merely a Single-Bit Flip in Large Language Models

Recently, Bit-Flip Attack (BFA) has garnered widespread attention for its ability to compromise software system integrity remotely through hardware fault injection. With the widespread distillation and deployment of large language models (LLMs) into single file .gguf formats, their weight spaces have become exposed to an unprecedented hardware attack surface. This paper is the first to systematically discover and validate the existence of single-bit vulnerabilities in LLM weight files: in mainstream open-source models (e.g., DeepSeek and QWEN) using .gguf quantized formats, flipping just single bit can induce three types of targeted semantic level failures Artificial Flawed Intelligence (outputting factual errors), Artificial Weak Intelligence (degradation of logical reasoning capability), and Artificial Bad Intelligence (generating harmful content). By building an information theoretic weight sensitivity entropy model and a probabilistic heuristic scanning framework called BitSifter, we achieved efficient localization of critical vulnerable bits in models with hundreds of millions of parameters. Experiments show that vulnerabilities are significantly concentrated in the tensor data region, particularly in areas related to the attention mechanism and output layers, which are the most sensitive. A negative correlation was observed between model size and robustness, with smaller models being more susceptible to attacks. Furthermore, a remote BFA chain was designed, enabling semantic-level attacks in real-world environments: At an attack frequency of 464.3 times per second, a single bit can be flipped with 100% success in as little as 31.7 seconds. This causes the accuracy of LLM to plummet from 73.5% to 0%, without requiring high-cost equipment or complex prompt engineering.

cs.CR↗

arXiv2025

Noise-tolerant correlated coincidence imaging based on super-correlated light at 1550 nm

Single-photon-level imaging at 1550 nm is a key driver for significant advancements in the next-generation laser detection technology. This cutting-edge approach plays a vital role in space ranging, target recognition, and three-dimensional remote sensing. However, it has faced severe challenges such as insufficient noise-tolerant performance. Here, we introduced noise-tolerant correlated coincidence imaging (CCI) based on super-correlated light. The light source, generated through nonlinear interaction between a pulsed laser and a photonic crystal fiber, exhibits a broader power-law photon number probability distribution and extremely strong photon correlation (with second-order correlation function $g^{(2)}(0)$ up to 18,166). Our noise-tolerant CCI can resist random environmental noise up to 100,000 times stronger than the echo signal photons. Super-correlated light offers an exceptionally strong noise tolerance for single-photon-level imaging in extreme environments with intense noise, paving the way for the future development of extremely sensitive light detection.

physics.optics↗

arXiv2025

Confusion is the Final Barrier: Rethinking Jailbreak Evaluation and Investigating the Real Misuse Threat of LLMs

With the development of Large Language Models (LLMs), numerous efforts have revealed their vulnerabilities to jailbreak attacks. Although these studies have driven the progress in LLMs' safety alignment, it remains unclear whether LLMs have internalized authentic knowledge to deal with real-world crimes, or are merely forced to simulate toxic language patterns. This ambiguity raises concerns that jailbreak success is often attributable to a hallucination loop between jailbroken LLM and judger LLM. By decoupling the use of jailbreak techniques, we construct knowledge-intensive Q\&A to investigate the misuse threats of LLMs in terms of dangerous knowledge possession, harmful task planning utility, and harmfulness judgment robustness. Experiments reveal a mismatch between jailbreak success rates and harmful knowledge possession in LLMs, and existing LLM-as-a-judge frameworks tend to anchor harmfulness judgments on toxic language patterns. Our study reveals a gap between existing LLM safety assessments and real-world threat potential.

cs.CR↗

arXiv2025

AI Reasoning for Wireless Communications and Networking: A Survey and Perspectives

Artificial Intelligence (AI) techniques play a pivotal role in optimizing wireless communication networks. However, traditional deep learning approaches often act as closed boxes, lacking the structured reasoning abilities needed to tackle complex, multi-step decision problems. This survey provides a comprehensive review and outlook of reasoning-enabled AI in wireless communication networks, with a focus on Large Language Models (LLMs) and other advanced reasoning paradigms. In particular, LLM-based agents can combine reasoning with long-term planning, memory, tool utilization, and autonomous cross-layer control to dynamically optimize network operations with minimal human intervention. We begin by outlining the evolution of intelligent wireless networking and the limitations of conventional AI methods. We then introduce emerging AI reasoning techniques. Furthermore, we establish a classification system applicable to wireless network tasks. We also present a layer-by-layer examination for AI reasoning, covering the physical, data link, network, transport, and application layers. For each part, we identify key challenges and illustrate how AI reasoning methods can improve AI-based wireless communication performance. Finally, we discuss key research directions for AI reasoning toward future wireless communication networks. By combining insights from both communications and AI, this survey aims to chart a path for integrating reasoning techniques into the next-generation wireless networks.

cs.NI↗

arXiv2025

DistJoin: A Decoupled Join Cardinality Estimator based on Adaptive Neural Predicate Modulation

Research on learned cardinality estimation has made significant progress in recent years. However, existing methods still face distinct challenges that hinder their practical deployment in production environments. We define these challenges as the ``Trilemma of Cardinality Estimation'', where learned cardinality estimation methods struggle to balance generality, accuracy, and updatability. To address these challenges, we introduce DistJoin, a join cardinality estimator based on efficient distribution prediction using multi-autoregressive models. Our contributions are threefold: (1) We propose a method to estimate join cardinality by leveraging the probability distributions of individual tables in a decoupled manner. (2) To meet the requirements of efficiency for DistJoin, we develop Adaptive Neural Predicate Modulation (ANPM), a high-throughput distribution estimation model. (3) We demonstrate that an existing similar approach suffers from variance accumulation issues by formal variance analysis. To mitigate this problem, DistJoin employs a selectivity-based approach to infer join cardinality, effectively reducing variance. In summary, DistJoin not only represents the first data-driven method to support both equi and non-equi joins simultaneously but also demonstrates superior accuracy while enabling fast and flexible updates. The experimental results demonstrate that DistJoin achieves the highest accuracy, robustness to data updates, generality, and comparable update and inference speed relative to existing methods.

cs.DB↗

arXiv2025

Decoding RobKiNet: Insights into Efficient Training of Robotic Kinematics Informed Neural Network

In robots task and motion planning (TAMP), it is crucial to sample within the robot's configuration space to meet task-level global constraints and enhance the efficiency of subsequent motion planning. Due to the complexity of joint configuration sampling under multi-level constraints, traditional methods often lack efficiency. This paper introduces the principle of RobKiNet, a kinematics-informed neural network, for end-to-end sampling within the Continuous Feasible Set (CFS) under multiple constraints in configuration space, establishing its Optimization Expectation Model. Comparisons with traditional sampling and learning-based approaches reveal that RobKiNet's kinematic knowledge infusion enhances training efficiency by ensuring stable and accurate gradient optimization.Visualizations and quantitative analyses in a 2-DOF space validate its theoretical efficiency, while its application on a 9-DOF autonomous mobile manipulator robot(AMMR) demonstrates superior whole-body and decoupled control, excelling in battery disassembly tasks. RobKiNet outperforms deep reinforcement learning with a training speed 74.29 times faster and a sampling accuracy of up to 99.25%, achieving a 97.33% task completion rate in real-world scenarios.

cs.RO↗

arXiv2025

ForeSight: A Predictive-Scheduling Deterministic Database

Deterministic databases enable scalable replicated systems by executing transactions in a predetermined order. However, existing designs fail to capture transaction dependencies, leading to insufficient scheduling, high abort rates, and poor resource utilization. By addressing these challenges with lightweight conflict prediction and informed scheduling, we present ForeSight, a high-performance deterministic database system. Our system has three core improvements: (1) We design an Association Sum-Product Network to predict potential transaction conflicts, providing the input for dependency analysis without pre-obtained read/write sets. (2) We enhance the storage engine to integrate multi-version-based optimization, improving the execution process and fallback strategy to boost commit rates and concurrency. (3) We propose a matrix two-pass forward scan algorithm that performs dependency analysis to generate conflict-aware schedules, significantly reducing scheduling overhead. Experimental results on multiple benchmarks show that ForeSight achieves up to 2 times higher throughput on skewed workloads and maintains strong performance under contention, demonstrating that predictive scheduling substantially improves deterministic database scalability.

cs.DB↗

arXiv2025

Collaborative Stance Detection via Small-Large Language Model Consistency Verification

Stance detection on social media aims to identify attitudes expressed in tweets towards specific targets. Current studies prioritize Large Language Models (LLMs) over Small Language Models (SLMs) due to the overwhelming performance improving provided by LLMs. However, heavily relying on LLMs for stance detection, regardless of the cost, is impractical for real-world social media monitoring systems that require vast data analysis. To this end, we propose \textbf{\underline{Co}}llaborative Stance Detection via Small-Large Language Model Consistency \textbf{\underline{Ver}}ification (\textbf{CoVer}) framework, which enhances LLM utilization via context-shared batch reasoning and logical verification between LLM and SLM. Specifically, instead of processing each text individually, CoVer processes texts batch-by-batch, obtaining stance predictions and corresponding explanations via LLM reasoning in a shared context. Then, to exclude the bias caused by context noises, CoVer introduces the SLM for logical consistency verification. Finally, texts that repeatedly exhibit low logical consistency are classified using consistency-weighted aggregation of prior LLM stance predictions. Our experiments show that CoVer outperforms state-of-the-art methods across multiple benchmarks in the zero-shot setting, achieving 0.54 LLM queries per tweet while significantly enhancing performance. Our CoVer offers a more practical solution for LLM deploying for social media stance detection.

cs.CL↗

arXiv2025

SAM: A Stability-Aware Cache Manager for Multi-Tenant Embedded Databases

The co-location of multiple database instances on resource constrained edge nodes creates significant cache contention, where traditional schemes are inefficient and unstable under dynamic workloads. To address this, we present SAM(a Stability-Aware Manager), an autonomic cache manager that establishes decision stability as a first-class design principle. It achieves this through its core control policy, AURA(Autonomic Utility-balancing Resource Allocator), which resolves the classic exploitation-exploration dilemma by synthesizing two orthogonal factors: the H-factor, representing proven historical efficiency (exploitation), and the V-factor, for estimated marginal gain (exploration). Through this practical synthesis and adaptive control, SAM achieves sustained high performance with strategic stability and robustness in volatile conditions. Extensive experiments against 14 diverse baselines demonstrate SAM's superiority. It achieves top-tier throughput while being uniquely resilient to complex workload shifts and adversarial workloads like cache pollution. Furthermore, its decision latency is highly scalable, remaining nearly constant as the system grows to 120 databases. Crucially, SAM achieves superior decision stability -- maintaining consistent optimization directions despite noise, avoiding performance oscillations while ensuring predictable Quality of Service. These results prove that a principled, stability-aware design is essential for sustained high performance in real-world, large-scale systems.

cs.DB↗

arXiv2025

Flexible Readout and Unconditional Reset for Superconducting Multi-Qubit Processors with Tunable Purcell Filters

Achieving high-fidelity qubit readout and reset while preserving qubit coherence is essential for quantum error correction and other advanced quantum algorithms. Here, we design and experimentally demonstrate a scalable architecture employing frequency-tunable nonlinear Purcell filters, enabling flexible readout and fast unconditional reset of multiple superconducting qubits. Our readout protocol dynamically adjusts the effective linewidth of the readout resonator through a tunable Purcell filter, optimizing the signal-to-noise ratio during measurement while suppressing photon noise during idle periods. We achieve a readout fidelity of $99.3\%$ without any quantum-limited amplifier, even with a small dispersive shift. Moreover, by leveraging a reset channel formed via the adjacent coupling between the filter and the coupler, we realize unconditional qubit reset of both leakage-induced $|2\rangle$ and $|1\rangle$ states within 200 ns and reset of the $|1\rangle$ state alone within 75 ns, with error rates $\leq 1\%$. The filter also mitigates both photon-induced dephasing and the Purcell effect, thereby preserving qubit coherence. This scalable Purcell filter architecture shows exceptional performance in qubit readout, reset, and protection, marking it as a promising hardware component for advancing fault-tolerant quantum computing systems.

quant-ph↗

arXiv2025

Platform for Representation and Integration of multimodal Molecular Embeddings

Existing machine learning methods for molecular (e.g., gene) embeddings are restricted to specific tasks or data modalities, limiting their effectiveness within narrow domains. As a result, they fail to capture the full breadth of gene functions and interactions across diverse biological contexts. In this study, we have systematically evaluated knowledge representations of biomolecules across multiple dimensions representing a task-agnostic manner spanning three major data sources, including omics experimental data, literature-derived text data, and knowledge graph-based representations. To distinguish between meaningful biological signals from chance correlations, we devised an adjusted variant of Singular Vector Canonical Correlation Analysis (SVCCA) that quantifies signal redundancy and complementarity across different data modalities and sources. These analyses reveal that existing embeddings capture largely non-overlapping molecular signals, highlighting the value of embedding integration. Building on this insight, we propose Platform for Representation and Integration of multimodal Molecular Embeddings (PRISME), a machine learning based workflow using an autoencoder to integrate these heterogeneous embeddings into a unified multimodal representation. We validated this approach across various benchmark tasks, where PRISME demonstrated consistent performance, and outperformed individual embedding methods in missing value imputations. This new framework supports comprehensive modeling of biomolecules, advancing the development of robust, broadly applicable multimodal embeddings optimized for downstream biomedical machine learning applications.

q-bio.BM↗

arXiv2025

GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace

This paper investigates the underlying mechanisms of toxicity generation in Large Language Models (LLMs) and proposes an effective detoxification approach. Prior work typically considers the Feed-Forward Network (FFN) as the main source of toxicity, representing toxic regions as a set of toxic vectors or layer-wise subspaces. However, our in-depth analysis reveals that the global toxic subspace offers a more effective and comprehensive representation of toxic region within the model. Building on this insight, we propose GloSS (Global Toxic Subspace Suppression), a lightweight, four-stage method that mitigates toxicity by identifying and removing the global toxic subspace from the parameters of FFN. Experiments across a range of LLMs show that GloSS achieves state-of-the-art detoxification performance while preserving the models general capabilities, without requiring large-scale data or model retraining.

cs.CL↗

arXiv2025

Lattice thermal conductivity of 16 elemental metals from molecular dynamics simulations with a unified neuroevolution potential

Metals play a crucial role in heat management in electronic devices, such as integrated circuits, making it vital to understand heat transport in elementary metals and alloys. In this work, we systematically study phonon thermal transport in 16 metals using the efficient homogeneous nonequilibrium molecular dynamics (HNEMD) method and the recently developed unified neuroevolution potential version 1 (UNEP-v1) for 16 metals and their alloys. We compare our results with existing ones based on the Boltzmann transport equation (BTE) approach and find that our HNEMD results align well with BTE results obtained by considering phonon-phonon scattering only. By contrast, HNEMD results based on the conventional embedded-atom method potential show less satisfactory agreement with BTE ones. Given the high accuracy of the UNEP-v1 model demonstrated in various metal alloys, we anticipate that the HNEMD method combined with the UNEP-v1 model will be a promising tool for exploring phonon thermal transport properties in complex systems such as high-entropy alloys.

cond-mat.mtrl-sci↗

arXiv2025

Super-bunching light with giant high-order correlations and extreme multi-photon events

Non-classical light sources emitting bundles of N-photons with strong correlation represent versatile resources of interdisciplinary importance with applications ranging from fundamental tests of quantum mechanics to quantum information processing. Yet, high-order correlations, gN(0),quantifying photon correlation, are still limited to hundreds. Here, we report the generation of a super-bunching light source in photonic crystal fiber with g2(0) reaching 5.86*104 and g5(0) up to 2.72*108, through measuring its photon number probability distributions. under giant g2(0) values, the super-bunching light source presents upturned-tail photon distributions and ubiquitous extreme multi-photon events, where 31 photons from a single light pulse at a mean of 1.99*10-4 photons per pulse have been determined. The probability of this extreme event has been enhanced by 10139 folds compared to a coherent laser with Poissonian distribution. By varying the power of the pumping laser, both photon number distributions and corresponding high-order correlations of this light source can be substantially tailored from Poissonian to super-bunching distributions. These phenomena are attributed to the synchronized nonlinear interactions in photonic crystal fibers pumping by bright squeezed light, and the theoretical simulations agree well with the experimental results. Our research showcases the ability to achieve non-classical light sources with giant high-order correlations and extreme multi-photon events, paving the way for high-order correlation imaging, extreme nonlinear optical effects, quantum information processing, and exploring light-matter interactions with multi-photon physics.

quant-ph↗

arXiv2025

Prethermalization by Random Multipolar Driving on a 78-Qubit Superconducting Processor

Time-dependent drives hold the promise of realizing non-equilibrium many-body phenomena that are absent in undriven systems. Yet, drive-induced heating normally destabilizes the systems, which can be parametrically suppressed in the high-frequency regime by using periodic (Floquet) drives. It remains largely unknown to what extent highly controllable quantum simulators can suppress heating in non-periodically driven systems. Using the 78-qubit superconducting quantum processor, Chuang-tzu 2.0, we report the experimental observation of long-lived prethermal phases in many-body systems with tunable heating rates, driven by structured random protocols, characterized by $n$-multipolar temporal correlations. By measuring both the particle imbalance and subsystem entanglement entropy, we monitor the entire heating process over 1,000 driving cycles and observe the existence of the prethermal plateau. The prethermal lifetime is `doubly tunable': one way by driving frequency, the other by multipolar order; it grows algebraically with the frequency with the universal scaling exponent $2n{+}1$. Using quantum state tomography on different subsystems, we demonstrate a non-uniform spatial entanglement distribution and observe a crossover from area-law to volume-law entanglement scaling. With 78 qubits and 137 couplers in a 2D configuration, the entire far-from-equilibrium heating dynamics are beyond the reach of simulation using tensor-network numerical techniques. Our work highlights superconducting quantum processors as a powerful platform for exploring universal scaling laws and non-equilibrium phases of matter in driven systems in regimes where classical simulation faces formidable challenges.

quant-ph↗

arXiv2025

CONCERTO: Complex Query Execution Mechanism-Aware Learned Cost Estimation

With the growing demand for massive data analysis, many DBMSs have adopted complex underlying query execution mechanisms, including vectorized operators, parallel execution, and dynamic pipeline modifications. However, there remains a lack of targeted Query Performance Prediction (QPP) methods for these complex execution mechanisms and their interactions, as most existing approaches focus on traditional tree-shaped query plans and static serial executors. To address this challenge, this paper proposes CONCERTO, a Complex query executiON meChanism-awaE leaRned cosT estimatiOn method. CONCERTO first establishes independent resource cost models for each physical operator. It then constructs a Directed Acyclic Graph (DAG) consisting of a dataflow tree backbone and resource competition relationships among concurrent operators. After calibrating the cost impact of parallel operator execution using Graph Attention Networks (GATs) with additional attention mechanisms, CONCERTO extracts and aggregates cost vector trees through Temporal Convolutional Networks (TCNs), ultimately achieving effective query performance prediction. Experimental results demonstrate that CONCERTO achieves higher prediction accuracy than existing methods.

cs.DB↗

arXiv2025

Na'vi or Knave: Jailbreaking Language Models via Metaphorical Avatars

Metaphor serves as an implicit approach to convey information, while enabling the generalized comprehension of complex subjects. However, metaphor can potentially be exploited to bypass the safety alignment mechanisms of Large Language Models (LLMs), leading to the theft of harmful knowledge. In our study, we introduce a novel attack framework that exploits the imaginative capacity of LLMs to achieve jailbreaking, the J\underline{\textbf{A}}ilbreak \underline{\textbf{V}}ia \underline{\textbf{A}}dversarial Me\underline{\textbf{TA}} -pho\underline{\textbf{R}} (\textit{AVATAR}). Specifically, to elicit the harmful response, AVATAR extracts harmful entities from a given harmful target and maps them to innocuous adversarial entities based on LLM's imagination. Then, according to these metaphors, the harmful target is nested within human-like interaction for jailbreaking adaptively. Experimental results demonstrate that AVATAR can effectively and transferablly jailbreak LLMs and achieve a state-of-the-art attack success rate across multiple advanced LLMs. Our study exposes a security risk in LLMs from their endogenous imaginative capabilities. Furthermore, the analytical study reveals the vulnerability of LLM to adversarial metaphors and the necessity of developing defense methods against jailbreaking caused by the adversarial metaphor. \textcolor{orange}{ \textbf{Warning: This paper contains potentially harmful content from LLMs.}}

cs.CL↗