arXiv subjects

Yu Zhang

Publications and source records attributed to Yu Zhang.

At least 181 records · Page 10Linked to original sources

arXiv2026

AERIS: Aerial-Edge Role-Driven Intelligence at Runtime via Orchestrated Language-Model Swarm

Integrating large language models into robotic systems holds promise for enhancing autonomy, yet practical deployment remains constrained by strict heartbeat-constrained scheduling and limited computational power. We propose AERIS: an edge deployment framework for aerial platforms. It organizes dedicated small language models combined with lightweight perception and control modules into roles that can be instantiated at runtime, and dynamically rebinds them across different executors as resources change, thereby pushing intelligent capabilities to the edge. AERIS achieves long-horizon instruction decomposition through an attention-subgoal alignment mechanism, which involves annotating the currently active instruction step in messages, thereby progressively approaching long-term objectives. We evaluate AERIS on a high-fidelity UAV Vision-and-Language Navigation benchmark. Under a heartbeat-timed execution mechanism, AERIS maintains a stable perception-decision-control loop between a low-frequency planner and a high-frequency controller, supporting real-time closed-loop operation. We further validate its deployability through two real-world experiments focused on planning and fast response. A demonstration video is provided in the supplementary materials.

cs.RO↗

arXiv2026

CLMASP: Coupling Large Language Models with Answer Set Programming for Robotic Task Planning

Large Language Models (LLMs) possess extensive foundational knowledge and moderate reasoning abilities, making them suitable for general task planning in open-world scenarios. However, it is challenging to ground a LLM-generated plan to be executable for the specified robot with certain restrictions. This paper introduces CLMASP, an approach that couples LLMs with Answer Set Programming (ASP) to overcome the limitations, where ASP is a non-monotonic logic programming formalism renowned for its capacity to represent and reason about a robot's action knowledge. CLMASP initiates with a LLM generating a basic skeleton plan, which is subsequently tailored to the specific scenario using a vector database. This plan is then refined by an ASP program with a robot's action knowledge, which integrates implementation details into the skeleton, grounding the LLM's abstract outputs in practical robot contexts. Our experiments conducted on the VirtualHome platform demonstrate CLMASP's efficacy. Compared to the baseline executable rate of under 2% with LLM approaches, CLMASP significantly improves this to over 90%.

cs.AI↗

arXiv2026

X-Mind: Efficient Visual Chain-of-Thought via Predictive World Model for End-to-End Driving

Predicting future states is essential for autonomous agents, yet current Vision-Language-Action (VLA) models fundamentally lack this capability, relying instead on reactive perception-action mapping. While integrating Predictive World Models (PWMs) addresses this gap, existing approaches either incur prohibitive cascaded latency or act as shallow terminal tasks that fail to deeply embed forward-looking reasoning. To endow VLA models with this reasoning capability, we propose X-Mind. Rather than treating PWMs as an external auxiliary module, this framework internalizes them as the Visual Chain-of-Thought (Visual CoT). By enforcing a world rollout prior to action, the model is constrained to imagine future evolution first, yielding a driving policy that is robustly grounded in environmental dynamics and aware of the future consequences its actions will unfold. The challenge here is efficiency, and we tackle it on two fronts. First, we introduce a compact representation of visual thinking: an abstract sketch that fuses a Bird's-Eye-View (BEV) layout with abstract driving priors (e.g., navigation intents and traffic rules). Rather than rolling out dense future frames, the model reasons over this sketch as a mental canvas; aided by a Deep Compression Autoencoder (DC-AE), a 12-frame future rollout is reduced to merely 96 tokens, alleviating the long-context computational bottleneck. Second, to accelerate generation further, we propose a recurrent block diffusion scheme that unrolls the denoising steps across the layers of the large drive model, folding iterative refinement into the backbone's one forward pass. Trained and validated on large-scale real-world data, X-Mind achieves competitive end-to-end driving performance, which makes it a highly practical, low-latency solution that successfully deploys large-scale cognitive reasoning directly onto resource-constrained vehicle platforms.

cs.CV↗

arXiv2026

Radiation Reaction effects on Coherent Emission in Relativistic Magnetized Shocks

Relativistic magnetized shocks are natural sources of coherent radiation, representing a promising framework for fast radio bursts (FRBs). This study explores how the radiation reaction (RR) effect, triggered by high-energy photon emissions during shock radiation, significantly alters particle dynamics and coherent radiation properties. Using kinetic particle simulations, we demonstrate that RR severely suppresses electron energies from shock acceleration, resulting in multiple coherent gyration cycles at the shock front. It amplifies the intensity of coherent radiation and boosts energy efficiency by several fold, as compared to the single gyration cycle in the standard model of relativistic magnetized shocks. We further find that the coherent radiation spectrum from RR-mediated shocks is characterized by upshift peak frequency, broaden bandwidth, and narrow spectral peak. These RR-induced radiation changes may be related with several observed FRB phenomena, including the statistically positive correlation between luminosity and bandwidth in repeating and one-off FRBs, the narrow spectra seen in some FRB events, and the bimodal energy distribution reported in FRB 20121102A.

astro-ph.HE↗

arXiv2026

Audio Editing in the Era of Foundation Models: A Survey

Audio editing aims to modify a given synthetic or real-world audio signal to satisfy specific user needs. As a promising yet challenging direction in AIGC, it has attracted increasing attention. Recent advances in audio generation have made powerful generative models central to modern audio editing systems. This rapid progress has created a growing need to organize emerging tasks, methods, and resources into a coherent view. In this survey, we provide a comprehensive review of audio editing in the era of foundation models. We first present a unified taxonomy of existing editing tasks and then summarize the major foundation-model paradigms that support modern audio editing, covering representative approaches from both training-based and training-free perspectives. We further discuss related resources, including datasets, evaluation protocols, and data construction tools. Finally, we identify open challenges in this field and outline promising directions for future research. The project page is released at https://github.com/DaViD-Pigeon/AudioEditSurvey.

eess.AS↗

arXiv2026

Reconfigurable all-optical inference via tunable second-harmonic generation and spin-orbit coupling cascade

Spin-orbit coupling (SOC) is widely exploited as a fundamental mechanism for generating orbital angular momentum (OAM); however, conventional approaches typically lack flexibility and tunability. Here, we introduce a continuously tunable second-harmonic generation (SHG)-SOC cascade mechanism modulated by a spatially movable nonlinear crystal. Under linearly polarized excitation, the SHG-SOC cascade engages synchronously with both degenerate and nondegenerate SHG processes, thereby expanding the OAM spectrum and significantly enhancing the information density and feature-mapping capacity of the optical field. Moreover, the OAM spectral distribution can be continuously reconfigured simply by translating the nonlinear crystal. This deterministic physical evolution, which maps simple OAM modes onto a tunable high-dimensional OAM space, is mathematically analogous to the high-dimensional feature expansion performed by a kernel function of a support vector machine (SVM) in machine learning. Such dimensional expansion can project linearly inseparable input data into a high-dimensional space where they become linearly separable. Exploiting this physics-algorithm analogy, we develop a reconfigurable all-optical inference platform. As a proof of concept, we successfully perform classification tasks, including the recognition of Iris flowers and Palmer penguins. This work establishes a scalable, physically reconfigurable architecture for high-dimensional all-optical computing and neuromorphic photonics.

physics.optics↗

arXiv2026

Potential Applications of Quantum Computing at Los Alamos National Laboratory

The emergence of quantum computing technology over the last decade indicates the potential for a transformational impact in the study of quantum mechanical systems. It is natural to presume that such computing technologies would be valuable to large scientific institutions, such as United States national laboratories. However, detailed descriptions of what these institutions would like to use these computers for are limited. To help provide some initial insights into this topic, this report develops detailed use cases of how quantum computing technology could be utilized to enhance a variety of quantum physics research activities at Los Alamos National Laboratory, including quantum magnetic materials, high-temperature superconductivity and nuclear astrophysics simulations. The report discusses how current high-performance computers are used for scientific discovery today and develops detailed descriptions of the types of quantum physics simulations that Los Alamos National Laboratory scientists would like to conduct, if a sufficient computing technology became available. While the report strives to highlight the breadth of potential application areas for quantum computation, this investigation has also indicated that many more use cases exist at Los Alamos National Laboratory, which could be documented in similar detail with sufficient time and effort.

quant-ph↗

arXiv2026

AgenticOS: An Intent-Oriented Secure Operating System Architecture for Autonomous AI Agents

Traditional OS security models based on "resource exposure plus permission checks" face structural challenges as LLM-driven autonomous agents acquire capabilities for planning, tool use, network access, and code execution. Once an agent runtime is compromised through prompt injection or malicious tool outputs, an attacker can compose POSIX-style resource primitives into behaviors far beyond the user's task authorization. To address this, we propose AgenticOS, an intent-oriented secure OS architecture that consolidates delegable, auditable software capabilities into OS-native ones rather than replacing all applications. The core insight is to reframe the OS from a "resource manager" into an "intent filter": instead of requesting low-level resources directly, agents submit structured intent declarations, from which the system synthesizes a least-privilege environment with mandatory mediation, auditing, and information-flow constraints. At the implementation level, we introduce a four-layer architecture -- Ghost Kernel, Logic Shutter, Agent Capsule, and Semantic Boundary Gateway -- together with the Intent ABI, Manifest-Only Runtime, Weaver-based capability generation, and an admission model for AgenticOS-native Skills.

cs.CR↗

arXiv2026

Heavy Quarkonium Spectrum and Decay Constants from a Neural-Network-Based Holographic Model

We present a data-driven inverse construction of the dilaton field in a bottom-up AdS/QCD description of heavy vector quarkonia. Instead of adopting an \emph{ad hoc} analytic ansatz, we use a multilayer perceptron to learn $Φ'(z)$ as a smooth function of the holographic coordinate, with $Φ(0)=0$ imposed to ensure ultraviolet consistency. The dilaton and its derivatives obtained by automatic differentiation generate the holographic potential $U(z)$, and the associated Schrödinger-like equation is discretized and diagonalized to extract the low-lying eigenmodes. Masses and decay constants are then evaluated from the eigenvalues and the near-boundary behavior of the bulk-to-boundary modes. Training on PDG data for charmonium and bottomonium yields a non-quadratic dilaton profile that resolves the longstanding difficulty of simultaneously reproducing both the heavy-quarkonium spectrum and the monotonic suppression of leptonic decay constants with radial excitation. The combined fit achieves RMS deviations of $1.26\%$ (charmonium) and $3.32\%$ (bottomonium). This work establishes neural-network reconstruction as a flexible tool for holographic modeling and provides a basis for future extensions incorporating additional channels, lattice constraints, or finite-temperature backgrounds.

hep-ph↗

arXiv2026

Seeing the Scene Matters: Revealing Forgetting in Video Understanding Models with a Scene-Aware Long-Video Benchmark

Long video understanding (LVU) remains a core challenge in multimodal learning. Although recent vision-language models (VLMs) have made notable progress, existing benchmarks mainly focus on either fine-grained perception or coarse summarization, offering limited insight into temporal understanding over long contexts. In this work, we define a scene as a coherent segment of a video in which both visual and semantic contexts remain consistent, aligning with human perception. This leads us to a key question: can current VLMs reason effectively over long, scene-level contexts? To answer this, we introduce a new benchmark, SceneBench, designed to provide scene-level challenges. Our evaluation reveals a sharp drop in accuracy when VLMs attempt to answer scene-level questions, indicating significant forgetting of long-range context. To further validate these findings, we propose Scene Retrieval-Augmented Generation (Scene-RAG), which constructs a dynamic scene memory by retrieving and integrating relevant context across scenes. This Scene-RAG improves VLM performance by +2.50%, confirming that current models still struggle with long-context retention. We hope SceneBench will encourage future research toward VLMs with more robust, human-like video comprehension.

cs.CV↗

arXiv2026

Improving Scientific Document Retrieval with Academic Concept Index

Adapting general-domain retrievers to scientific domains is challenging due to the scarcity of large-scale domain-specific relevance annotations and the substantial mismatch in vocabulary and information needs. Recent approaches address these issues through two independent directions that leverage large language models (LLMs): (1) generating synthetic queries for fine-tuning, and (2) generating auxiliary contexts to support relevance matching. However, both directions overlook the diverse academic concepts embedded within scientific documents, often producing redundant or conceptually narrow queries and contexts. To address this limitation, we introduce an academic concept index, which extracts key concepts from papers and organizes them guided by an academic taxonomy. This structured index serves as a foundation for improving both directions. First, we enhance the synthetic query generation with concept coverage-based generation (CCQGen), which adaptively conditions LLMs on uncovered concepts to generate complementary queries with broader concept coverage. Second, we strengthen the context augmentation with concept-focused auxiliary contexts (CCExpand), which leverages a set of document snippets that serve as concise responses to the concept-aware CCQGen queries. Extensive experiments show that incorporating the academic concept index into both query generation and context augmentation leads to higher-quality queries, better conceptual alignment, and improved retrieval performance.

cs.IR↗

arXiv2026

Ensuring Trustworthy Online A/B Testing: Addressing Five Key Questions on CUPED

A/B testing has become the gold standard for data-driven decision-making in large-scale online experimentation, providing critical guidance for feature launch, pricing optimization, and user experience enhancement. To maximize statistical sensitivity, many technology companies routinely employ Controlled-experiment Using Pre-Experiment Data (CUPED), a technique that achieves substantial variance reduction while preserving the unbiasedness of estimating the average treatment effect. Despite its widespread adoption, several critical methodological and practical nuances of CUPED remain underexplored. This paper systematically addresses five frequently encountered yet overlooked questions regarding the application of CUPED. First, we provide a comparative analysis of various post-CUPED estimators to identify the optimal adjustment specification. Second, we evaluate the validity of regression-based adjustments and delineate robust variance estimation methods tailored for such frameworks. Finally, we extend our investigation to complex but common scenarios, including multi-arm experiments and two-stage sampling designs. Our findings reveal that in these settings, naive reliance on standard variance estimators can lead to severely misleading inferences. By offering rigorous theoretical insights and extensive experimental validation, this work deepens the conceptual understanding of CUPED. Notably, the recommended methodologies have been successfully deployed and integrated into ByteDance's experimentation platform.

stat.AP↗

arXiv2026

Invertible Neural Network Adapter for One-Step Flow Matching in Robot Manipulation

This paper presents an invertible neural network adapter for general robotic manipulation, designed to generate precise high-dimensional actions conditioned on multimodal observations, including visual, linguistic, and proprioceptive inputs, through a one-step denoising process. Built upon a flow-matching formulation, the proposed adapter effectively constrains the action generation trajectory within an invertible latent space, thereby enabling efficient and high-quality dexterous action synthesis with only a single inference step. Compared with conventional iterative flow-matching policies, the proposed framework substantially reduces inference complexity while maintaining strong action prediction accuracy and stability. Extensive experiments are conducted across a diverse set of simulation benchmarks and real-world robotic platforms to evaluate the effectiveness of the proposed method. Across simulation benchmarks, the proposed adapter consistently demonstrates superior or near state-of-the-art performance on a wide range of manipulation tasks. Furthermore, real-world experiments reveal a significant improvement in inference efficiency for vision-language-action (VLA) models, reducing the average inference latency from 110 ms to 61 ms while maintaining strong task performance.

cs.RO↗

arXiv2026

A Survey of Full-Duplex Spoken Dialogue Systems: Architectural Hierarchy, Interaction Ontology, and Decision State Machine

More than a dozen spoken dialogue systems have recently claimed to be "full-duplex," yet the term has been used to describe substantially different capabilities. Existing surveys collapse them onto a single axis (cascaded/end-to-end, or engineered/learned) and miss the distinctions that matter most for builders. We argue that much of this ambiguity is taxonomical: current terminology does not specify where duplex decisions are made, which interaction types are supported, or how a system behaves moment by moment. This paper introduces three complementary frameworks: (i) an L0-L3 Architectural Hierarchy that locates where duplex decisions are made; (ii) a $T\times I\times R$ Interaction Ontology that specifies the temporal relation, user intent, and required system response for each interaction; and (iii) a Decision State Machine (IDLE/LISTEN/SPEAK/WAIT/DUAL) that describes how systems move between states. Across published systems and benchmarks, our audit documents a realization gap: although many architectures can in principle operate in full-duplex states, their observed behavior remains constrained by the interaction patterns represented in training and evaluation. We point to the limited public training-data coverage relative to the (largely undisclosed) industrial corpora, together with the still-unrealized goal of L3 representation-level modeling, as the key frontiers for future research on full-duplex dialogue. The related material is available at https://github.com/DuplexLM/DuplexSurvey.

eess.AS↗

arXiv2026

Spatio-Temporal Fusion Model for Standard View Classification of Echocardiographic Videos

Automated classification of standard echocardiographic views is crucial for efficient clinical workflow but faces three main challenges. First, publicly available datasets are scarce and limited in scale and view coverage. Second, the performance of some modern video-level architectures for echocardiographic view classification remains underexplored. Third, some view categories exhibit highly similar spatial appearances, making single-frame features insufficient for discrimination, while heterogeneous frame quality complicates robust temporal information fusion. To address these challenges, we release the Echocardiographic Videos of Nine Views (EV9V) dataset, comprising 5,138 videos, 910,579 frames, and 9 standard views, which is, to the best of our knowledge, the largest publicly available echocardiography video dataset. Using EV9V, we systematically benchmark representative video classification architectures, including Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Transformers. Furthermore, we propose a Spatio-Temporal Fusion Model (STFM), an efficient dual-stream CNN-LSTM (Long Short-Term Memory) framework that jointly captures spatial anatomical structures and temporal cardiac dynamics. The proposed framework leverages uncertainty-aware learning to preferentially sample representative video segments during training and evidence-based fusion during inference, improving robustness to variations in frame quality across echocardiographic videos. Extensive experiments demonstrate that our method achieves competitive performance across diverse video classification models, validating the effectiveness of uncertainty-aware spatio-temporal learning for echocardiographic view classification. The code is available at https://github.com/bgx666/stfm.

cs.CV↗

arXiv2026

Principles and Practices of Large-Scale Code Analysis at Ant Group: A Data- and Logic-Oriented Approach

Large-scale software development requires dynamic and multifaceted static code analysis that extends beyond the capabilities of traditional tools. Existing tools like CodeQL lack cross-language analysis capabilities and can be time-consuming and resource-intensive. We present CodeFuse-Query, a data system tailored for large-scale code analysis. First, CodeFuse-Query adopts a Logic-Oriented Computation Design, employing Datalog with a two-tiered schema, COREF, to convert source code into data facts, and Godel to express complex analysis tasks in logical terms. Furthermore, CodeFuse-Query adopts a Domain-Optimized System Design. This approach optimizes resource utilization, prioritizes data reusability, applies incremental code extraction, and introduces task-type characteristics specifically for code changes, underscoring its domain-optimized design. We present empirical results demonstrating CodeFuse-Query's robustness, scalability, and efficiency in large-scale real-world scenarios at Ant Group, where it serves as a core static analysis infrastructure. Deployed in production environments, CodeFuse-Query processes up to 10 billion lines of code daily across more than 300,000 distinct analysis tasks. CodeFuse-Query has been open-sourced.

cs.SE↗

arXiv2026

Semi-Supervised Noise Adaptation: Transferring Knowledge from Noise Domain

Transfer learning aims to facilitate the learning of a target domain by transferring knowledge from a source domain. The source domain typically contains semantically meaningful samples (*e.g.*, images) to facilitate effective knowledge transfer. However, a recent study observes that the noise domain constructed from simple distributions (*e.g.*, Gaussian distributions) can serve as a surrogate source domain in the semi-supervised setting, where only a small proportion of target samples are labeled while most remain unlabeled. Based on this surprising observation, we formulate a novel problem termed *Semi-Supervised Noise Adaptation* (SSNA), which aims to leverage a synthetic noise domain to improve the generalization of the target domain. To address this problem, we first establish a generalization bound characterizing the effect of the noise domain on generalization, based on which we propose a Noise Adaptation Framework (NAF). Extensive experiments demonstrate that NAF effectively leverages the noise domain to tighten the generalization bound of the target domain, leading to improved performance. The codes are available at https://github.com/AIResearch-Group/SSNA.

cs.LG↗

arXiv2026

EvoRec: Self Evolving Agentic Recommender Systems

Optimizing modern recommender systems still relies heavily on engineers iterating by hand, which is slow and bounded by individual expertise. LLM-based agents open a path toward automating this loop, yet two issues remain. First, the agent is used only as a code translator and accumulates no methodology across iterations. Second, the optimization space is confined to a predefined range and rarely introduces structurally new ideas. To address these problems, we propose EvoRec, a multi-agent framework that co-evolves the recommendation model and the optimization methodology driving it. Four collaborating agents carry out a dual-track loop: the Research Agent and Code Agent iterate the model each round, while the Skill Evolver periodically distills reusable methodology from a persistent Memory of past experiments. Experiments on two public benchmarks and one large-scale industrial dataset show that EvoRec improves offline metrics by up to 5.54% over the strongest baseline, and an online A/B test delivers a 1.85% revenue lift and a 1.02% CTR gain.

cs.IR↗