Searcharxiv⌕ Search

arXiv subjects

Jie Liu

Publications and source records attributed to Jie Liu.

At least 109 records · Page 6Linked to original sources
arXiv2026

Personalization Meets Safety:Mechanisms,Risks,and Mitigations in Personalized LLMs

Large Language Models (LLMs) have enabled increasingly personalized interactions by adapting to users' preferences, contexts, and long-term histories. However, the mechanisms that enable personalization also expand the safety landscape in ways not systematically addressed by existing literature. Existing reviews typically focus either on personalization or safety, leaving their intersection largely unexplored. We present the first comprehensive, safety-aware review of personalized LLMs. We organize personalization along three dimensions-user representation, personalization paradigm, and evaluation-and introduce a unified taxonomy of safety risks. At the representation level, we analyze risks arising from diverse user representations. Across mainstream personalization paradigms, we delineate vulnerabilities inherent to prompting, retrieval augmentation, parameter fine-tuning, reinforcement learning, Mixture-of-Experts (MoE), pruning, agent frameworks, and multimodal personalization, and synthesize mitigation strategies across the model lifecycle. Beyond these fine-grained risks, we characterize paradigm-agnostic safety risks arising from personalized adaptation. We further summarize personalized datasets and evaluation methodologies. Through a case study of OpenClaw, we analyze deployment trends in personalized agent ecosystems. Our analysis reveals three structural inadequacies in existing research: safety is evaluated as user-invariant rather than relational, personalization techniques are analyzed in isolation rather than in composition, and evaluation frameworks cannot capture emergent long-term risks. By jointly examining personalized representations, personalization paradigms, safety risks, defenses, and evaluation methods, we provide a unified framework for developing safe personalized LLMs and highlight key directions for future research.

cs.AI↗
arXiv2026

CANS: Accelerating Multiuser Collaborative Edge Inference via Cooperative Autodidactic NeuroSurgeon

Recently, mobile edge computing (MEC)-enabled collaborative deep neural network (DNN) inference has emerged as a promising approach for delivering intelligent services to resource-constrained mobile devices. A representative scenario is multi-user collaborative edge inference, where distinct devices independently partition their DNN models and offload backend computation to a common edge server over wireless networks. However, determining the optimal DNN partition for each device is challenging due to unknown and time-varying system conditions, including fluctuating wireless links and diverse device capabilities. To address this problem, we propose Cooperative Autodidactic NeuroSurgeon (CANS), a collaborative edge inference framework that enables devices to adaptively learn optimal DNN partitions by sharing informative feedback during online inference. To handle the challenge of device heterogeneity and better leverage offline inference experience, we integrate a novel FedLinUCB-DW algorithm that groups devices of the same type and warm-starts online exploration using local offline early-exit inference experience. Furthermore, we provide theoretical guarantees for FedLinUCB-DW by deriving the regret upper bound. We also validate our method on both a simulated environment and a hardware prototype system. Empirical evaluations demonstrate that CANS achieves lower inference latency compared to state-of-the-art baselines. Especially, in prototype experiments on two edge devices, the proposed CANS reduced average inference latency by up to 50% compared to the non-cooperative baseline.

cs.LG↗
arXiv2026

SwiftVR: Real-Time One-Step Generative Video Restoration

Real-time video restoration (VR) for live streams requires high-resolution outputs under strict per-frame latency constraints. Existing one-step diffusion-based VR models remain difficult to deploy on consumer-grade GPUs due to two main bottlenecks: quadratic spatial attention at high resolutions and the latency-memory overhead of large video autoencoders. We present SwiftVR, a streaming one-step generative VR framework that reduces both bottlenecks under a causal chunk-wise protocol. For attention, mask-free shifted-window self-attention gathers each spatial window into a dense tensor via deterministic indexing, keeping all attention calls on the dense scaled dot-product attention path without masks, cyclic shifts, padding, or hardware-specific sparse kernels. Because SwiftVR uses only standard dense SDPA calls, the trained model transfers to consumer GPUs without retraining or custom kernels. For autoencoding, a lightweight Restoration-aware Autoencoder enables fast chunk-wise decoding while preserving reconstruction quality. On a single H100, SwiftVR sustains 31~FPS at 2560x1440 and 14~FPS at 3840x2160, whereas all compared diffusion-based VR baselines exceed the memory limit at 4K. On a consumer RTX~5090, SwiftVR reaches 26~FPS at 1920x1080. To our knowledge, SwiftVR is the first generative VR model to achieve real-time 1080p streaming on a consumer-grade GPU, while attaining strong no-reference perceptual quality with lower inference cost. Project is available at https://h-oliday.github.io/SwiftVR.

cs.CV↗
arXiv2026

Minimum Complete MR Subsets under Semantic-Mutation Fault Models: A Support-Set Domination Boundary

This paper asks when MR-subset selection is a real mutant-level requirement for minimum complete evidence in metamorphic testing rather than a coarse fault-class counting artifact. We define a layer-relative completeness criterion over an admitted mutant--draw coverage universe. The central result is a support-set domination boundary: it states when class-level abstraction is safe and when mutant-level MR minimization is necessary. The boundary is governed by kill-signature heterogeneity, which yields a scoped fault-signature kernel and separates the MR-specific question from ordinary fault-class counting. The resulting Min-MR-Complete problem is Set-Cover-equivalent over the selected coverage universe, giving NP-hardness, the classical logarithmic approximation boundary, a greedy approximation, an exact ILP formulation, and an SMS-rank upper bound that is not a lower bound or tight predictor. Artifact lanes provide lane-local minimization and audit evidence; separately, route witnesses instantiate both collapse and non-collapse regimes for the boundary theorem and are not pooled as population-level experiments. Other MR-class-proxy rows remain intermediate signals rather than route-admitted witness evidence.

cs.SE↗
arXiv2026

Widths of regular components for n-regular tree $T(n)$

Let $(T(n),Ω)$ be the covering of the generalized Kronecker quiver $K(n)$, where $Ω$ is a bipartite orientation. Given a regular Auslander--Reiten component $\cD$ of $\modd(T(n),Ω)$, we introduce two invariants: the width $\cW(\cD)$ and the number of flow modules $b(\cD)$. We show that $\cW(\cD)\geq \frac{b(\cD)+1}{2}$. In particular, we get $\{\cW(\cD)| \cD \text{ is a regular component} \}=\mathbb{N}$.

math.RT↗
arXiv2026

Quantifying Non-Abelian Stability in Majorana Qubits through Rabi Beating Signatures

Evaluating the stability of Majorana qubits (MQs) is a central challenge for topological quantum computation. Here we propose a simple and experimentally accessible protocol to quantify MQ stability by coupling a quantum dot (QD) to an MQ, which induces Rabi oscillations in the QD charge occupation that can be directly detected using recently developed single-shot readout techniques. In realistic systems, deviations from ideal MQ behavior lead to a characteristic beating pattern in the Rabi dynamics. We show that the beating frequency scales linearly with these deviations while remaining independent of the base Rabi frequency, thereby providing a direct and quantitative measure of MQ stability. Importantly, the beating signature is robust against weak dissipation, and we further demonstrate that the effective model remains quantitatively accurate when benchmarked against a realistic minimal Kitaev chain. Our results establish a practical and scalable route for quantitatively characterizing Majorana qubit stability in current experimental platforms.

cond-mat.mes-hall↗
arXiv2026

RASR: Retrieval-Augmented Super Resolution for Practical Reference-based Image Restoration

Reference-based Super Resolution (RefSR) improves upon Single Image Super Resolution (SISR) by leveraging high-quality reference images to enhance texture fidelity and visual realism. However, a critical limitation of existing RefSR approaches is their reliance on manually curated target-reference image pairs, which severely constrains their practicality in real-world scenarios. To overcome this, we introduce Retrieval-Augmented Super Resolution (RASR), a new and practical RefSR paradigm that automatically retrieves semantically relevant high-resolution images from a reference database given only a low-quality input. This enables scalable and flexible RefSR in realistic use cases, such as enhancing mobile photos taken in environments like zoos or museums, where category-specific reference data (e.g., animals, artworks) can be readily collected or pre-curated. To facilitate research in this direction, we construct RASR-Flickr30, the first benchmark dataset designed for RASR. Unlike prior datasets with fixed target-reference pairs, RASR-Flickr30 provides per-category reference databases to support open-world retrieval. We further propose RASRNet, a strong baseline that combines a semantic reference retriever with a diffusion-based RefSR generator. It retrieves relevant references based on semantic similarity and employs a diffusion-based generator enhanced with semantic conditioning. Experiments on RASR-Flickr30 demonstrate that RASRNet consistently improves over SISR baselines, achieving +0.38 dB PSNR and -0.0131 LPIPS, while generating more realistic textures. These findings highlight retrieval augmentation as a promising direction to bridge the gap between academic RefSR research and real-world applicability.

cs.CV↗
arXiv2026

ObjFiller3D: Scaling 3D Object Inpainting to Dense Multi-View Consistency

3D object inpainting is commonly achieved via multi-view 2D image completion, yet independently inpainted views often suffer from cross-view inconsistencies, leading to blurred textures, geometric discontinuities, and visual artifacts in the reconstructed 3D objects. To overcome these limitations, we propose ObjFiller-3D, a novel method designed for the completion and editing of high-quality and consistent 3D objects. Instead of relying on sparse-view editing or per-view 2D inpainting, our method jointly optimizes a sequence of densely sampled views along a $360^\circ$ trajectory, enabling global coherence across viewpoints. We design a new framework with three complementary components: a Temporal-Driven Generative Encoder for modeling dense-view dependencies, a Semantic-Aware Completion Encoder for object-level inpainting, and a Cycle-Consistent 3D Encoder that enforces global coherence through a closed-loop formulation. Our framework also supports reference-guided 3D inpainting, allowing fine-grained control over appearance. Extensive experiments on diverse datasets demonstrate that ObjFiller-3D significantly outperforms prior methods, achieving higher reconstruction fidelity (PSNR 26.6 vs.\ 15.9 of NeRFiller) and perceptual quality (LPIPS 0.19 vs.\ 0.25 of Instant3dit), while reducing reconstruction time from over 40 minutes to under 10 minutes. These results highlight the effectiveness and practical potential of our approach for real-world 3D editing applications. Project page: https://objfiller3d.github.io/ Code: https://github.com/objfiller3d/ObjFiller-3D .

cs.CV↗
arXiv2026

Full-field prediction for engineering-scale three-dimensional aircraft with multigrid-hierarchical learning

High-fidelity computational fluid dynamics is essential for aerospace design, but engineering-scale simulations of practical three-dimensional aircraft remain computationally expensive. Learning-based flow-field initialization can improve efficiency by reducing the numerical distance between the initial and converged solutions, yet existing deep learning approaches remain difficult to scale to large three-dimensional aircraft flows with multiscale regional heterogeneity. Most prior studies therefore focus on two-dimensional problems, surface quantities, integral aerodynamic coefficients, or simplified three-dimensional cases with limited grid resolution.Here we propose MHLF, a multigrid-hierarchical learning framework for accelerating engineering-scale aircraft flow simulations while preserving high-fidelity numerical accuracy. MHLF combines a topologically consistent geometric multigrid representation with a hierarchical strategy that captures regional flow heterogeneity during both prediction and subsequent CFD correction. Across three engineering-scale aircraft cases spanning Mach 0.15 to 6.0 and covering subsonic, transonic and supersonic regimes, MHLF accelerates convergence without sacrificing flow-field accuracy, achieving a 3 to 8 times efficiency improvement over conventional initialization. These results demonstrate practical full-flow-field prediction for large three-dimensional aircraft within the CFD domain and provide a foundation for data-driven acceleration of high-fidelity aircraft flow simulation.

physics.flu-dyn↗
arXiv2026

Nonreciprocal Landau-Zener Tunneling in the Presence of Heat-Bath-Induced Colored Noise

In this work, we investigate the effects of heat-bath-induced colored noise on nonreciprocal Landau-Zener tunneling. We perform numerical calculations of the instantaneous energy levels and find that noise induces stochastic fluctuations in these levels. Beyond such fluctuations, sufficiently large nonreciprocity parameters enable noise to further trigger the emergence of multiple exceptional points. The corresponding tunneling probability is significantly modified by colored noise. On the one hand, colored noise generally enhances the tunneling probability under nonadiabatic sweeping. On the other hand, it can break the reciprocity of Landau-Zener tunneling in the adiabatic limit. In particular, for large nonreciprocity parameters, the adiabatic tunneling probability is insensitive to noise and determined by exceptional points. We plot the phase diagram of tunneling probability as a function of the sweep rate and nonreciprocity parameter, for different amplitudes and correlation times of colored noise. Analytically, we derive the exact expression for the tunneling probability in the absence of noise and an approximate solution in the white-noise limit, employing Weber functions and the Wiener-Hermite expansion method. Some implications of our theory are discussed.

quant-ph↗
arXiv2026

A Neuroevolution Potential for Gallium Oxide: Accurate and Efficient Modeling of Polymorphism and Swift Heavy-Ion Irradiation

Gallium oxide (Ga2O3) is a wide-bandgap semiconductor with promising applications in high-power and high-frequency electronics. However, its complex polymorphic nature poses substantial challenges for fundamental studies, particularly in understanding phase-transformation behaviors under nonequilibrium conditions. Here, we develop a robust, accurate, and computationally efficient machine-learning interatomic potential (MLIP) for Ga2O3 based on the neuroevolution potential (NEP) framework combined with an energy-dependent weighting strategy. The resulting NEP potential demonstrates clear advantages over the state-of-the-art tabGAP potential with respect to both accuracy and computational efficiency. Furthermore, we introduce a physically process-oriented sampling strategy to systematically augment the training dataset, thereby enhancing the MLIP performance for targeted physical phenomena. As a representative application, a dedicated NEP potential is constructed for swift heavy-ion (SHI) irradiation simulations of \b{eta}-Ga2O3. The simulated results are in quantitative agreement with experimental observations and provide a consistent physical explanation for the reported experimental discrepancies regarding phase transformations in the ion track of \b{eta}-Ga2O3.

cond-mat.mtrl-sci↗
arXiv2026

Leveraging Verifier-Based Reinforcement Learning in Image Editing

While Reinforcement Learning from Human Feedback (RLHF) has become a pivotal paradigm for text-to-image generation, its application to image editing remains largely unexplored. A key bottleneck is the lack of a robust general reward model for all editing tasks. Existing edit reward models usually give overall scores without detailed checks, ignoring different instruction requirements and causing biased rewards. To address this, we argue that the key is to move from a simple scorer to a reasoning verifier. We introduce Edit-R1, a framework that builds a chain-of-thought (CoT) verifier-based reasoning reward model (RRM) and then leverages it for downstream image editing. The Edit-RRM breaks instructions into distinct principles, evaluates the edited image against each principle, and aggregates these checks into an interpretable, fine-grained reward. To build such an RRM, we first apply supervised fine-tuning (SFT) as a ``cold-start'' to generate CoT reward trajectories. Then, we introduce Group Contrastive Preference Optimization (GCPO), a reinforcement learning algorithm that leverages human pairwise preference data to reinforce our pointwise RRM. After building the RRM, we use GRPO to train editing models with this non-differentiable yet powerful reward model. Extensive experiments demonstrate that our Edit-RRM surpasses powerful VLMs such as Seed-1.5-VL and Seed-1.6-VL as an editing-specific reward model, and we observe a clear scaling trend, with performance consistently improving from 3B to 7B parameters. Moreover, Edit-R1 delivers gains to editing models like FLUX.1-kontext, highlighting its effectiveness in enhancing image editing.

cs.CV↗
arXiv2026

SkySeg: Collaborative Onboard Semantic Segmentation with Heterogeneous UAVs in the Wild

The demand for unmanned aerial vehicle (UAV)-based image acquisition and analysis has surged, with UAVs increasingly utilized for semantic segmentation tasks. To meet the real-time analysis requirements of UAV remote sensing missions, performing onboard computation and making decisions based on the results is a natural approach. However, deploying semantic segmentation on resource-constrained UAV platforms presents two significant challenges: 1) hardware constraints limit the ability of UAVs to perform real-time semantic segmentation, and 2) environmental variations during flight cause data distribution shifts, deviating from the original training data. To address these issues, this paper introduces SkySeg, a heterogeneous multi-UAV air-air cooperation framework that integrates computer vision and flight pattern to enable onboard semantic segmentation using low-cost sensors. SkySeg employs an efficient information fusion inference method, combining low-definition, wide-area images with high-definition, focused-area images. Additionally, it incorporates a cross-device test-time adaptation (TTA) strategy to enhance segmentation performance in dynamic environments by collaboratively addressing distribution shifts of test data streams across UAVs. Experimental results demonstrate that our SkySeg framework accelerates inference latency by approximately 3.6x, improves onboard segmentation accuracy by 5.91\%, and achieves a 10.91\% average accuracy gain in the wild.

cs.CV↗
arXiv2026

A connection between minimal nilpotent orbits of types A and D via Hamiltonian reduction

We establish a novel connection between the minimal nilpotent orbit $\mathbb{O}_n$ in $\mathfrak{sl}_n$ and the minimal nilpotent orbit closure $\overline{\mathbf{O}}_n$ in $\mathfrak{so}_{2n+2}$, which differs from the shared-orbit paradigm of Brylinski and Kostant, where no direct type-A--type-D relation appears. More precisely, we show that the affine closure of the cotangent bundle $\overline{T^*\mathbb{O}_n}^{\mathrm{aff}}$ is isomorphic to a $\mathbb{C}^*$-Hamiltonian reduction of $\overline{\mathbf{O}}_n$. This provides a quasi-classical analogue of a quantum result of Levasseur and Stafford. A detailed study of the geometry of this Hamiltonian reduction reveals that $\overline{T^*\mathbb{O}_n}^{\mathrm{aff}}$ has no symplectic resolution.

math.RT↗
arXiv2026

NOETHER: A Constructive Framework for Metamorphic Pattern Discovery from Operator Algebras

Context. Metamorphic Testing is recognised in IEEE/ISO software-testing standards and increasingly recommended for AI systems, but its progress is bottlenecked by metamorphic relation (MR) identification: existing approaches (structured frameworks, mining and evolutionary pipelines, LLM-assisted methods, MetaPattern catalogues) share an inductive grounding that leaves three foundational questions open: origin, closure, and transferability. Objective. We propose a framework whose downstream step from program-induced operator algebra to MetaPattern set is mechanical and provable, while the upstream curation of the algebra is a stated empirical hypothesis with explicit scope precondition. Method. NOETHER is a two-layer framework. The upstream layer is an eight-block decomposition over recurrent mathematical structures (symmetry, order, self-adjoint, time-reversal, limit, qualitative-dynamics, method-comparison, relational equivalence). The downstream CONSTRUCT-MP algorithm produces a MetaPattern set with algebraic-closure (Theorem 1) and polynomial-time decidability (Theorem 2) guarantees. We test the framework on three operator-algebraic domains. Results. On Boltzmann reactor physics NOETHER systematises a prior inductive catalogue; on equivariant ML it derives executable MRs for rotation invariance, adjoint duality, and training-trajectory reversibility; on relational query optimisers it exercises the relational-equivalence block. The central falsifiable prediction (L*-blindness on homogeneity-preserving mutators) holds on the in-scope substrate. The absolute-completeness conjecture (Theorem 1') is falsified on PWR core diffusion via two pairwise-independent counterexamples that identify five Translate-extension dimensions. Conclusion. Induction is relocated from per-program MR sampling to a per-domain algebraic layer; the downstream step is deductive and mechanical.

cs.SE↗
arXiv2026

R2H-Diff: Guided Spectral Diffusion Model for RGB-to-Hyperspectral Reconstruction

RGB-to-hyperspectral image reconstruction is a highly ill-posed inverse problem, since multiple plausible spectral distributions may correspond to the same RGB observation. Existing regression-based methods usually learn a deterministic mapping, which limits their ability to model reconstruction uncertainty and often leads to over-smoothed spectral responses. Although diffusion models provide strong distribution modeling capability, their direct application to hyperspectral reconstruction remains challenging due to the high spectral dimensionality, strong inter-band correlations, and strict requirement for spectral fidelity. To this end, we propose R2H-Diff, an efficient diffusion-based framework tailored for RGB-to-HSI reconstruction. Specifically, R2H-Diff formulates spectral recovery as a conditional iterative refinement process, enabling progressive reconstruction under RGB guidance. We proposed a Guided Spectral Refinement Module for RGB-conditioned feature fusion and a Hyperspectral-Adaptive Transposed Attention module for efficient spatial--spectral dependency modeling. Furthermore, a normalization-free denoising backbone is adopted to preserve spectral amplitude consistency, while a task-adapted linear noise schedule enables high-quality reconstruction with only five denoising steps. Extensive experiments on NTIRE2022, CAVE, and Harvard demonstrate that R2H-Diff achieves a favorable balance between reconstruction quality and computational efficiency. Notably, on NTIRE2022, R2H-Diff obtains 35.37 dB PSNR with a sub-million-parameter model of 0.58M parameters and 12.25G FLOPs, achieving the lowest model complexity among the evaluated methods while maintaining strong reconstruction fidelity.

cs.CV↗
arXiv2026

Accelerating Noisy Variational Quantum Algorithms with Physics-Informed Denoising Networks

Variational quantum algorithms are promising for near-term quantum computing, but are severely limited by hardware noise and the substantial circuit overhead required for error mitigation methods such as Zero-Noise Extrapolation (ZNE). We propose a Physics-Informed Denoising Network (PIDN) that reduces the cost of ZNE by learning a surrogate model of its optimization dynamics. By viewing the variational update as a trajectory in the parameter space, PIDN is trained to reproduce ZNE-mitigated expectation values and gradient directions while incorporating a physics-informed loss that preserves the gradient descent dynamics. Once trained, PIDN replaces repeated multi-noise evaluations with denoised expectation and gradient estimation directly from the current noisy observation and the historical trajectory, significantly reducing circuit executions. We benchmark the approach on the quantum approximate optimization algorithm for 3-regular graphs, Sherrington-Kirkpatrick, and transverse-field Ising models, as well as the variational quantum eigensolver for LiH, BeH$_2$ and H$_2$O. Across all tasks, PIDN attains performance comparable to ZNE, while reducing the number of circuit executions by a factor of approximately 4 to 6. Gradient cosine similarity with ZNE remains above 0.95 throughout training. Robustness analysis shows that PIDN fails only when ZNE itself becomes unreliable, and ablation studies confirm the necessity of the physics-informed loss for maintaining directional consistency. We further find that PIDN tracks optimization dynamics most accurately when the effective loss landscape retains strong low-frequency structure. These results establish PIDN as a scalable, resource-efficient strategy for noise-resilient variational optimization in the noisy intermediate-scale quantum regime.

quant-ph↗
arXiv2026

Charge-dependent spectral softenings of primary cosmic-rays below the knee

In most particle acceleration or propagation theories, the characteristic features of the cosmic ray spectra due to acceleration limits or propagation phase changes are charge dependent. Alternatively, the interaction scenario would expect mass dependent spectral features in general. The observational verification of which relation takes effect in nature is still lack due to the difficulty of measuring the spectra of individual particles up to very high energies. Here we report direct measurements of the carbon, oxygen, and iron spectra from ~20 gigavolts to ~100 teravolts (~60 teravolts for iron) with 9 years of on-orbit data collected by the Dark Matter Particle Explorer. Distinct spectral softenings have been directly detected in these spectra for the first time. Combined with the updated proton and helium spectra, the spectral softening appears universally at a rigidity of ~15 teravolts. A nuclei mass dependent softening is rejected at a confidence level of >99.999%. Possible interpretations of these results, including a nearby cosmic ray source and other models such as the propagation effect, are discussed.

astro-ph.HE↗