Search arXiv⌕ Search

arXiv subjects

Yuqi Zhang

Publications and source records attributed to Yuqi Zhang.

At least 19 recordsLinked to original sources
arXiv2026

X-World 1.6: Building Controllable Virtual Cities with World Models

Deploying generative world models for end-to-end closed-loop evaluation and policy learning requires precise scenario control, consistent observations, and sustained generation quality during extended interactions. This report presents \emph{X-World~1.6}, advancing X-World~1.0 toward a more reliable and versatile driving simulator. The upgraded base model offers finer-grained control over traffic semantics, including traffic lights and road markings, together with improved spatial consistency across cameras. Virtual City capabilities broaden scenario construction through a family of models conditioned on diverse 2D and 3D references, including support for generating multi-camera future videos from a single image. An enhanced post-training framework enables efficient causal, few-step generation with stronger temporal coherence, better quality retention over longer rollouts, and improved alignment with human preferences. We also introduce a dedicated evaluation suite to support systematic assessment and guide model iteration. Together, these upgrades expand the scenarios X-World can simulate and improve the efficiency and reliability of its generated observations, supporting broader use in autonomous-driving development.

cs.AI↗
arXiv2026

RCCM: Diagnosing Gains and Harms in Reasoning-Prompt Transfer

A reasoning prompt can improve one deployment and degrade another. RCCM (Reasoning-Control Capability Mismatch) examines these reversals by pairing answers to the same questions with records of how generation ends. Across five open-weight deployments and nine strategies, aggregate accuracy hides substantial question-level gains and harms; a common-budget MATH500 evaluation examines transfer on a separate sample. On 60 additional questions, concise reasoning improves Phi's automatic answer matching at a 2,048-token cap across three collections, but sharply reduces Qwen's. Author-reviewed final-answer commitments give a smaller, statistically unresolved Phi gain. Reserving an answer stage also improves matching, with additional input and call costs. These results show why a prompt benefit must be interpreted alongside its execution and evaluation: matching a reference answer need not mean delivering it, and an apparent compression benefit may admit another explanation. RCCM records this evidence for reproducible transfer comparisons.

cs.CL↗
arXiv2026

Connected Self Forcing: Beyond Local Learning in Video Autoregression

To stream long videos while maintaining visual quality and temporal consistency, Self Forcing mitigates exposure bias through self-rollout training on self-generated histories with key-value (KV) caching. To keep memory manageable, it detaches historical caches, preserving forward dependencies between chunks but severing the backward gradient paths. We introduce Connected Self Forcing, a training framework that reconnects gradient paths across autoregressive chunks, allowing feedback from later predictions to guide how earlier context is generated. These connections go beyond historical KV-writing: gradients pass through generated latents into the computations that produced them, linking the generation of earlier context to its use in later predictions. To make this connected training memory-efficient, we develop shortcut gradient replay, which recovers cross-chunk gradients without retaining the full rollout computation graph. Integrated with distribution matching distillation, Connected Self Forcing trains historical chunks according to both their direct supervision and their contribution to subsequent generation. Experiments on autoregressive video generation show improvements in long-horizon visual quality and temporal consistency, without changing the inference procedure.

cs.CV↗
arXiv2026

Detection and Mode-Identification of Multiple Change Points in Tensor Factor Models

We study the problem of modeling high-dimensional tensor-valued time series under a Tucker decomposition-based factor model while permitting the presence of multiple structural change points. Such data call for a method that (i) handles high dimensionality and complex dependence while achieving consistency in multiple change points and further, (ii) addresses a unique challenge posed by the multi-dimensional array setting, of identifying the modes associated with each change while the shifts in different modes interact with one another. To this end, we propose a change point detection procedure utilizing the low-rank structure of the data for statistical and computational efficiency. In addition, we formalize the $\textit{mode-identifiability}$ of each change and propose an algorithm for detecting the modes at which the data undergo a mode-identifiable shift. We establish the consistency of both change point detection and mode-identification methods under a weak moment condition, and demonstrate their good performance on simulated datasets where, in particular, it is shown that the mode-identification step can improve the post-segmentation estimation of the mode-wise loading space. We also analyze the datasets on New York City taxi usage and Fama--French portfolio returns using the proposed suite of methods.

math.ST↗
arXiv2026

An Exact Polynomial Task-Risk Bridge for Time-Multiplexed Photonic Quantum Reservoirs

Time-multiplexed (TDM) photonic reservoirs are usually judged by their scores on a few datasets, which say little about a chip's overall performance, and designed by enumerating candidate circuits and simulating each one, which is inefficient and gives no guarantee of finding a good structure. For a time-unrolled passive linear network with data-modulated gates or sources and a ridge readout, we derive an exact bridge from the task to the prediction risk in three steps. (i) Task features: the finite-shot risk depends on the time series only through finitely many statistics of its training windows and their correlations with the target, selected by the encoding and the optical paths. (ii) Encoding: every output moment is a polynomial in the features of the data-modulated sites, with degree and support bounded by tuples of optical paths. Gate encoding reads the characteristic function and creates interactions across time lags; squeezing encoding reads the moment-generating function and displacement encoding low-order moments, and with quadrature receivers they yield only additive and linear models, respectively, for every topology. (iii) Readout: for homodyne, heterodyne and photon-number receivers the risk closes exactly, and its dependence on the number of shots is an explicit sum over signal-to-noise modes; threshold clicks admit finite-dictionary approximations with certified error. Parts of the network that share no light carry independent states, which a receiver combines only through measurement events that join them. Checks on seven datasets confirm every exact statement to machine precision. The three steps thus yield a useful space of candidate TDM architectures, pruned by exact statements rather than by trial simulation, which can in future guide the selection of TDM chips for target requirements.

quant-ph↗
arXiv2026

Highly efficient on-chip erbium-ytterbium co-doped lithium niobate waveguide amplifiers

The ability to amplify optical signals is of paramount importance in photonic integrated circuits (PICs). Recently, lithium niobate on insulator (LNOI) has attracted increasing interests as an emerging PIC platform. However, the shortage of active devices on LNOI platform limits the development of optical amplification. Here, we firstly report an efficient waveguide amplifier based on erbium and ytterbium co-doped LNOI by using electron beam lithography and inductively coupled plasma reactive ion etching process. We have demonstrated that the net internal gain in the communication band is 15.70 dB/cm under the pumping of 974 nm continuous laser. Benefiting from the efficient pumping facilitated by energy transfer between ytterbium and erbium ions, signal amplification can be achieved at a low pump power of 0.1 mW. It is currently the most efficient waveguide amplifier under unidirectional pumping reported on the LNOI platform, with an internal conversion efficiency of 10%. This work proposes a new and efficient active device for LNOI integrated optical systems, which may become an important fundamental component of future lithium niobate photonic integration platforms.

physics.optics↗
arXiv2026

High-efficiency integrated laser on erbium-doped lithium niobate-on-insulator

Lithium niobate on insulator (LNOI) combines the outstanding optical properties of lithium niobate (LN) with strong optical confinement, scalable fabrication and high-density integration, making it a leading platform for integrated photonic chips. Recent advances in LNOI photonics have mainly centred on passive and electro-optic components, including couplers, waveguides, microcavities and modulators, whereas efficient on-chip laser sources remain insufficiently developed, limiting the realization of fully integrated LN photonic systems. Because LN is an indirect-bandgap material, lasing on LNOI generally relies on photoluminescence from rare-earth-ion doping, yet the conversion efficiency of doped LNOI lasers has remained low. By comparing LNOI microcavity lasers with fibre lasers and waveguide amplifiers, we identify the limited number of rare-earth ions participating in stimulated emission as a key factor responsible for inefficient pump utilization. Here we demonstrate an integrated Er-doped LNOI laser that combines high-quality, highly Er-doped LN, a large-diameter wide-microring resonator, a low-loss waveguide amplifier and bidirectional pumping. This architecture enables a slope efficiency of 16.91% at 1562 nm, exceeding 10% on the LNOI platform for the first time. Our results provide a route towards high-efficiency LNOI lasers for fully integrated photonic systems.

physics.optics↗
arXiv2026

Benchmarking spiking neural networks across sensing modalities on edge devices

Edge computing systems need to support diverse sensing workloads under tight energy and memory constraints, thereby motivating deployment-aware model selection. Spiking neural networks (SNNs) are a promising alternative to conventional artificial neural networks (ANNs), yet systematic evidence for when and why they provide practical advantages remains limited. Here, we present a benchmark of SNNs across five sensing modalities and multiple edge devices, systematically evaluating spike encoding, neuron models, and network topologies under consistent training and deployment protocols. We find that SNN advantages are strongly modality-dependent: while SNNs achieve performance broadly comparable to ANNs across most workloads, wireless sensing emerges as a particularly favorable domain. Frequency-domain and feature-space analyses further explain this result by showing that spiking dynamics naturally align with the spectral-temporal structure of wireless signals. Our deployment analysis further shows that SNN advantages are not one-dimensional, with energy gains often accompanied by modality-dependent system costs. Finally, we provide an open-source framework for reproducible benchmarking and deployment profiling, offering a practical foundation for algorithm-software-hardware co-design on emerging edge and neuromorphic computing platforms.

cs.NE↗
arXiv2026

Three-Dimensional Dust Distribution in the Jovian System from Juno/Waves Observations: Insights into the Halo Ring and Magnetospheric Dust

Discoveries regarding the dusty rings of Jupiter and the Galilean satellites' dust environment have been continuously refined by orbiters and flybys. Leveraging Juno Waves instrument electric field data, we developed a hybrid recognition framework, coupling Kvammen's Convolutional Neural Network (CNN) with rule-based differential peak analysis, to systematically map the Jovian dust environment. This automated pipeline successfully identified over 150,000 dust impacts, effectively isolating dust signals from intense magnetospheric noise, providing a high-resolution catalog of Jovian microdust distribution and offering a robust technical foundation for future missions. Analysis of the vertical cross-section of the Jovian halo ring reveals a more detailed dust distribution structure, with a distinct number density enhancement near the center of the halo ring. Moreover, we report the continued evidence of dust populations near or in the Jovian magnetosheath through identification of background magnetic and plasma data instant variations during magnetospheric boundary crossings.

astro-ph.EP↗
arXiv2026

SkillShapley: Boundary-Adaptive Shapley Valuation for Skill Step Attribution in LLM Agents

Agent skills are crucial external instructions that enable language agents to execute long procedural tasks such as coding or document processing. Existing agent skills are primarily created through human manual crafting or agent execution traces, with limited understanding of how each step contributes to overall skill performance on specific tasks; i.e., there remains an open problem in quantifying the contribution of individual steps within an agent skill. To address this issue, we first model skill-step attribution as a Shapley value-based contribution estimation problem, and then propose SkillShapley, a step-level attribution framework for agent skills. Notably, SkillShapley operates in two phases, motivated by key empirical insights, i.e., discretized benchmark rewards that create sharp performance cliffs, and step interactions that are largely additive rather than synergistic. Specifically, it first identifies informative coalitional regions, and then adaptively samples new coalitions that can yield reusable marginal evidence. Experiments on skills from the widely adopted SkillsBench demonstrate that our SkillShapley can effectively and efficiently identify high- or low-value skill steps, providing several key takeaways for agent skill creation.

cs.AI↗
arXiv2026

VLZip: Unified Visual and Textual Compression for Interleaved Long-Context Modeling

Vision Language Models (VLMs) face significant challenges with ultra-long, interleaved image-text sequences due to the quadratic complexity of self-attention. Current solutions either resort to aggressive token pruning, risking irreversible information loss, or adopt efficient but less precise architectures, while largely ignoring the equally vital textual component. We introduce VLZip, a framework that unifies visual and textual compression for high-fidelity reasoning within a pure Transformer. At its core, VLZip hierarchically distills visual and textual segments into compact, layer-specific "soft prefixes" and injects them into each decoder layer's hidden states, drastically shortening the attention sequence while preserving fine-grained global context. To address deficient evaluations in the field, we also introduce LongVLBench, a new benchmark derived from video narratives that demands holistic, narrative-level reasoning. Extensive experiments show VLZip achieves leading performance on long-context multimodal reasoning, enabling training up to 120K tokens, a 6x increase over the baseline, and inference beyond 280K tokens with significantly reduced memory, while demonstrating the memory scalability to handle up to 2M tokens. By excelling at extreme context lengths where existing methods collapse, VLZip establishes an efficient and powerful new standard for long-context multimodal AI. Code is available at https://github.com/ShareLab-SII/VLZip.

cs.CV↗
arXiv2026

JoyAI-Talker: Full-Duplex Speech Interactive Large Model Built for Empathetic Voice Agents

We present JoyAI-Talker, a full-duplex speech dialogue system that delivers robust foundation model capabilities while empowering empathetic interaction and voice agent intelligence. JoyAI-Talker adopts a modular Thinker-Talker architecture and further implements a unified speech-text joint training pipeline to mitigate the common "cognitive degradation" bottleneck, thereby largely preserving the model's core textual reasoning, STEM, and logical capabilities while extending them to speech-based interaction. For expressive speech synthesis, the Talker module employs a text-controllable generation paradigm that enables natural-language instructions to flexibly control vocal attributes and localized paralinguistic events, such as laughter and sighs, supporting more expressive and fine-grained speech responses. To enhance conversational empathy, we introduce the Persona-Adaptive Empathetic Response (PAER) framework. PAER employs a hierarchical cognitive pipeline to extract non-verbal speaker cues, such as gender, age, and emotional state, from raw input audio, incorporate them into the Thinker's CoT reasoning, and generate context-adaptive responses that align semantically appropriate text with fine-grained control over utterance-level expressiveness and localized paralinguistic events, including sighs, speaking rate, and volume. We further integrate Joy-Duplex, a state-driven, plug-and-play full-duplex framework that functions as an efficient gating engine for real-time turn control. Extensive evaluations show that JoyAI-Talker achieves highly competitive performance on foundational T2T and S2T benchmarks. In full-duplex evaluation, the system reaches a high response rate of 0.88 under user interruptions while maintaining an extremely low false-trigger rate under background speech, demonstrating its readiness for fluid and natural speech dialogue.

cs.SD↗
arXiv2026

AerialMetric: Benchmarking and Adapting UAV Monocular Metric Depth Estimation in the Real World

This paper addresses the problem of monocular metric depth estimation in aerial UAV imagery. Although recent data-driven methods have achieved remarkable progress in ground-level scenarios, models trained primarily on street-view and indoor datasets exhibit significant domain gaps when applied to aerial viewpoints. To tackle these challenges, we introduce AerialMetric, a benchmark dataset designed to evaluate and facilitate the adaptation of monocular metric depth estimation under UAV aerial viewpoints. The dataset consists of four complementary subsets collected from different sources, jointly covering real-world photogrammetry data, controlled aerial acquisition settings, photorealistic synthetic scenes, and in-the-wild Internet imagery. Totally, AerialMetric provides 52K real-world and 16K synthetic image-depth pairs with reliable metric ground truth. Based on this dataset, we conduct systematic evaluations of existing state-of-the-art models under aerial settings and investigate the impact of viewpoint, altitude, and camera parameters on metric depth prediction. In addition, by fine-tuning representative metric depth model on our dataset, we establish a comprehensive aerial benchmark and achieve state-of-the-art performance across diverse aerial imagery. Our dataset, code, and model weight are publicly available at https://kuieless.github.io/AerialMetric-ECCV2026-page/.

cs.CV↗
arXiv2026

Scene-SAM3D: Multi-View Scene Asset Generation Without Fine-Tuning

High-quality 3D scene assets are critical for embodied applications such as robotic manipulation, navigation, and simulation. Despite their strong object priors, recent single-image 3D generation models such as SAM3D remain insufficient for real-world scenes, where severe occlusions, redundant observations, and cross-view inconsistencies make reliable scene generation challenging. We introduce Scene-SAM3D, a training-free framework that extends SAM3D from single-view object generation to calibrated multi-view scene asset generation. Scene-SAM3D selects a compact set of complementary views, reducing observation redundancy while providing additional evidence for regions occluded in individual views. Based on the selected views, it performs step-efficient latent velocity fusion to integrate multi-view evidence and suppress cross-view conflicts in canonical space. Finally, a lightweight rigid-object Gaussian optimization refines the scene layout within 200 iterations while preserving the generated object geometry. Experiments on Replica and ScanNet++ demonstrate consistent improvements at both instance and scene levels, with our method reducing scene-level CD by 43.8% on Replica and 30.9% on ScanNet++, while cutting flow-model sampling FLOPs and wall-time latency by nearly 20% under the same multi-view setting. Code will be released at https://github.com/xibi777/Scene-SAM3D.

cs.CV↗
arXiv2026

Quantum Sampling Architecture for Protein Structure Reconstruction on Utility-Scale Hardware

Predicting the structure of short peptides in protein binding pockets remains difficult because this regime requires physics-based conformational search, yet existing methods do not provide a practical way to carry out that search on current hardware. We present QSAD, a quantum-classical framework that reformulates peptide structure prediction as amino-acid-level Hamiltonian sampling and replaces iterative optimization with non-iterative Hamiltonian evolution. Executed entirely on IBM Heron R2 across 101 binding-pocket peptides (5-18 residues), QSAD improves prediction accuracy by 27-71% over all evaluated AI and quantum baselines while maintaining the lowest variance across tested lengths. QSAD also tolerates noise levels 3-5x beyond typical hardware error rates, where iterative methods fail, and reduces mean quantum execution time by 27x relative to VQE. The sampled ensemble further supports approximate reconstruction of protein energy landscapes. These results establish coarse-grained quantum sampling as a practical computational path for structure prediction in regimes where data-driven methods lack sufficient signal.

cs.ET↗
arXiv2026

Graph-VQE: A CUDA-Q Multi-QPU Simulation Framework for Hamiltonian-Aware Protein-Folding VQE

The Variational Quantum Eigensolver (VQE) is essential for molecular simulation in drug discovery, but hardware noise and algorithmic limits restrict its precision. While the NVIDIA CUDA-Q platform mitigates some hardware issues via exact simulation, it lacks Qiskit support and restricts parallelization. To solve this, we introduce Graph-VQE, a novel framework that extends CUDA-Q with optimization-level parallelism. Graph-VQE leverages amino acid sequence structures by partitioning Hamiltonian interaction graphs into weakly coupled clusters using Louvain community detection. These clusters undergo restricted updates on the full-Hamiltonian objective, followed by a global refinement stage utilizing Hamiltonian batching. Furthermore, a custom Qiskit-CUDA-Q integration layer enables standard workflows with GPU acceleration. Evaluations on protein folding tasks prove that Graph-VQE outperforms baselines, achieving lower final energies. It delivers competitive RMSD and binding affinity compared to AlphaFold3 and IBM quantum processors while maintaining stable quality across multi-GPU environments, thereby providing a highly practical path toward high-fidelity biomolecular simulations.

cs.ET↗
arXiv2026

REGRID-QAOA: A Resource-Efficient Hybrid QAOA Framework for Physics-Constrained Power System Islanding

Quantum computing has rapidly emerged as a powerful paradigm for tackling computationally demanding problems. In particular, quantum optimization shows strong promise for hard combinatorial problems in power systems, where increasing distributed energy penetration heightens the need for intentional islanding to maintain grid reliability and resilience. However, power system islanding is an NP-hard combinatorial optimization problem that becomes computationally prohibitive for classical solvers as network size grows, motivating the use of quantum computing as a promising alternative pipeline. This study develops a resource-efficient hybrid QAOA islanding framework that brings physics-constrained power-system partitioning into the quantum optimization workflow. The framework combines coherency-informed graph reduction, physics-aware constraint modeling, and structured post-processing to efficiently convert shallow-circuit QAOA samples into high-quality feasible islanding decisions without deep circuits or large shot budgets. The proposed framework is validated on the standard IEEE benchmark systems (9-, 14-, 24-, 30-, 39-, and 57-bus), demonstrating that the hybrid workflow achieves Gurobi-optimal solution quality with a clear quantum resource advantage over vanilla QAOA, while the resulting islanding solutions satisfy all physical feasibility requirements after network separation. This study establishes QAOA-based islanding as a viable quantum approach for critical infrastructure, with structured post-processing as the key enabler of quantum resource efficiency.

quant-ph↗
arXiv2026

Instrumental and Proximal Causal Inference with Gaussian Processes

Instrumental variable (IV) and proximal causal learning (Proxy) methods are central frameworks for causal inference in the presence of unobserved confounding. Despite substantial methodological advances, existing approaches rarely provide reliable epistemic uncertainty (EU) quantification. We address this gap through a Deconditional Gaussian Process (DGP) framework for uncertainty-aware causal learning. Our formulation recovers popular kernel estimators as the posterior mean, ensuring predictive precision, while the posterior variance yields principled and well-calibrated EU. Moreover, the probabilistic structure enables systematic model selection via marginal log-likelihood optimization. Empirical results demonstrate strong predictive performance alongside informative EU quantification, evaluated via empirical coverage frequencies and decision-aware accuracy rejection curves. Together, our approach provides a unified, practical solution for causal inference under unobserved confounding with reliable uncertainty.

stat.ML↗