arXiv subjects

Qi Zhao

Publications and source records attributed to Qi Zhao.

At least 55 records · Page 3Linked to original sources

arXiv2026

VL-DPO: Vision-Language-Guided Finetuning for Preference-Aligned Autonomous Driving

The rapid growth of autonomous driving datasets has enabled the scaling of powerful motion forecasting models. While large-scale pretraining provides strong performance, the standard imitation objective may not fully capture the complex nuances of human driving preferences. Meanwhile, recent advances in vision-language models (VLMs) have demonstrated impressive reasoning and commonsense understanding. Building on these capabilities, this paper presents VL-DPO, a vision-language-guided framework that aligns ego-vehicle motion forecasting models with human preferences. Our approach leverages a VLM as a zero-shot reasoner to automatically generate preference pairs from a pretrained model's rollouts, which are then used to finetune the model via Direct Preference Optimization (DPO). We finetune our models on the Waymo Open End-to-End Driving Dataset (WOD-E2E) and evaluate performance against held-out human preference annotations using rater feedback score (RFS) and average displacement error (ADE). Our experiments confirm that the VLM's trajectory selection is a high-quality proxy for human preference. Our final model, VL-DPO, yields an 11.94% increase in RFS and a 10.01% reduction in ADE over the pretrained model.

cs.CV↗

arXiv2026

RealDiffusion: Physics-informed Attention for Multi-character Storybook Generation

While modern diffusion models excel at generating diverse single images, extending this to sequential generation reveals a fundamental challenge: balancing narrative dynamism with multi-character coherence. Existing methods often falter at this trade-off, leading to artifacts where characters lose their identity or the story stagnates. To resolve this critical tension, we introduce RealDiffusion, a unified framework designed to reconcile robust coherence with narrative dynamism. Heat diffusion serves as a dissipative prior that averages neighboring features along the sequence and removes high-frequency noise within the subject region. This suppresses attribute drift and stabilizes identity across frames. A region-aware stochastic process then introduces small perturbations that explore nearby modes and prevent collapse so the story maintains pose change and scene evolution. We thus introduce a lightweight, training-free Physics-informed Attention mechanism that injects controllable physical priors into the self-attention layers during inference. By modeling feature evolution as a configurable physical system, our method regularizes spatio-temporal relationships without suppressing intentional, prompt-driven changes. Extensive experiments demonstrate that RealDiffusion achieves substantial gains in character coherence while preserving narrative dynamism, outperforming state-of-the-art approaches. Code is available at https://github.com/ShmilyQi-CN/RealDiffusion.

cs.CV↗

arXiv2026

CyberCane: Neuro-Symbolic RAG for Privacy-Preserving Phishing Detection with Formal Ontology Reasoning

Privacy-critical domains require phishing detection systems that satisfy contradictory constraints: near-zero false positives to prevent workflow disruption, transparent explanations for non-expert staff, strict regulatory compliance prohibiting sensitive data exposure to external APIs, and robustness against AI-generated attacks. Existing rule-based systems are brittle to novel campaigns, while LLM-based detectors violate privacy regulations through unredacted data transmission. We introduce CyberCane, a neuro-symbolic framework integrating deterministic symbolic analysis with privacy-preserving retrieval-augmented generation (RAG). Our dual-phase pipeline applies lightweight symbolic rules to email metadata, then escalates borderline cases to semantic classification via RAG with automated sensitive data redaction and retrieval from a phishing-only corpus. We further introduce PhishOnt, an OWL ontology enabling verifiable attack classification through formal reasoning chains. Evaluation on DataPhish2025 (12.3k emails; mixed human/LLM) and Nazario/SpamAssassin demonstrates a 78.6-point recall gain over symbolic-only detection on AI-generated threats, with precision exceeding 98% and FPR as low as 0.16%. Healthcare deployment projects a 542x ROI; tunable operating points support diverse risk tolerances, with open-source implementation at https://github.com/sbhakim/Cybercane.

cs.CR↗

arXiv2026

Context Unrolling in Omni Models

We present Omni, a unified multimodal model natively trained on diverse modalities, including text, images, videos, 3D geometry, and hidden representations. We find that such training enables Context Unrolling, where the model explicitly reasons across multiple modal representations before producing predictions. This process enables the model to aggregate complementary information across heterogeneous modalities, facilitating a more faithful approximation of the shared multimodal knowledge manifold and improving downstream reasoning fidelity. As a result, Omni achieves strong performance on both multimodal generation and understanding benchmarks, while demonstrating advanced multimodal reasoning capabilities, including in-context generation of text, image, video, and 3D geometry.

cs.CV↗

arXiv2026

Crepe: A Mobile Screen Data Collector Using Graph Query

Collecting mobile datasets remains challenging for academic researchers due to limited data access and technical barriers. Commercial organizations often possess exclusive access to mobile data, leading to a "data monopoly" that restricts the independence of academic research. Existing open-source mobile data collection frameworks primarily focus on mobile sensing data rather than screen content, which is crucial for various research studies. We present Crepe, a no-code Android app that enables researchers to collect information displayed on screen through simple demonstrations of target data. Crepe utilizes a novel Graph Query technique which augments the structures of mobile UI screens to support flexible identification, location, and collection of specific data pieces. The tool emphasizes participants' privacy and agency by providing full transparency over collected data and allowing easy opt-out. We designed and built Crepe for research purposes only and in scenarios where researchers obtain explicit consent from participants. Code for Crepe will be open-sourced to support future academic research data collection.

cs.HC↗

arXiv2026

Xpertbench: Expert Level Tasks with Rubrics-Based Evaluation

As Large Language Models (LLMs) exhibit plateauing performance on conventional benchmarks, a pivotal challenge persists: evaluating their proficiency in complex, open-ended tasks characterizing genuine expert-level cognition. Existing frameworks suffer from narrow domain coverage, reliance on generalist tasks, or self-evaluation biases. To bridge this gap, we present XpertBench, a high-fidelity benchmark engineered to assess LLMs across authentic professional domains. XpertBench consists of 1,346 meticulously curated tasks across 80 categories, spanning finance, healthcare, legal services, education, and dual-track research (STEM and Humanities). These tasks are derived from over 1,000 submissions by domain experts--including researchers from elite institutions and practitioners with extensive clinical or industrial experience--ensuring superior ecological validity. Each task uses detailed rubrics with mostly 15-40 weighted checkpoints to assess professional rigor. To facilitate scalable yet human-aligned assessment, we introduce ShotJudge, a novel evaluation paradigm that employs LLM judges calibrated with expert few-shot exemplars to mitigate self-rewarding biases. Our empirical evaluation of state-of-the-art LLMs reveals a pronounced performance ceiling: even leading models achieve a peak success rate of only ~66%, with a mean score around 55%. Models also exhibit domain-specific divergence, showing non-overlapping strengths in quantitative reasoning versus linguistic synthesis.. These findings underscore a significant "expert-gap" in current AI systems and establish XpertBench as a critical instrument for navigating the transition from general-purpose assistants to specialized professional collaborators.

cs.AI↗

arXiv2026

Linear Feedback Controller for Homogeneous Polynomial Systems

This paper studies stabilization and its corresponding closed-loop region-of-attraction (ROA) for homogeneous polynomial dynamical systems whose nonlinear term admits an orthogonally decomposable (ODECO) tensor representation. While recent tensor-based results provide explicit solutions and sharp global characterizations for open-loop ODECO systems, closed-loop synthesis and computable ROA estimates are still often dominated by local linearization or Lyapunov/SOS (sum of squares) methods, which can be conservative and computationally demanding. We propose a structure-preserving linear feedback design that shares the ODECO eigenbasis of the system's tensor, thereby enabling closed-form trajectory expressions, explicit convergence/escape thresholds, and sharp ROA characterizations. Under mild conditions, we further derive robustness/ISS-type bounds for bounded disturbances. Numerical examples validate the theoretical results.

eess.SY↗

arXiv2026

Invariance of Competition Outcomes in Hypergraph Competitive Dynamics

Winner-take-all (WTA)--type selection is a fundamental mechanism in networked competition, yet its dependence on higher-order interactions remains insufficiently understood. We study a Lotka--Volterra competitive dynamics on higher-order networks, where classical pairwise inhibition is augmented by multi-way interaction terms induced by hyperedges of uniform hypergraphs. The proposed model shows multiple competitive outcomes, including WTA, winner-share-all (WSA), and variant winner-take-all (VWTA). The existence, uniqueness and stability of equilibria are rigorously proved through mathematical analysis, which relies on classical stability theory and recent advances in tensor algebra. We show that the eventual selection outcome is relatively insensitive to the hyperedge order and the specific higher-order coupling structure, and is instead determined by a small set of interpretable scalar parameters, such as the ratio between self-inhibition and lateral-inhibition and the external inputs. Numerical experiments support the theory by showing that higher-order interactions affect convergence and steady states, yet yield the similar outcome taxonomy (WTA/WSA/VWTA) as in standard graphs. These results provide a network-scientific explanation of the robustness of WTA-type outcomes under complex group interactions and offer principled guidance for designing selection mechanisms on higher-order networks.

eess.SY↗

arXiv2026

Bra-ket entanglement, an indicator bridging entanglement, magic, and coherence

Understanding the intricate interplay between distinct quantum resources is a fundamental prerequisite for rigorously characterizing the boundary between classical and quantum technologies. Among the vast landscape of quantum resources, entanglement, magic, and coherence have arguably attracted the most intense investigation. However, while universally recognized as the core drivers of quantum advantage, our understanding of their structural interplay remains fragmented and compartmentalized. In this work, we introduce an indicator called {\em bra-ket entanglement} (BKE) defined in the operator vectorization space to bridge all three quantum resources. Specifically, we show that BKE governs a resource dependence transition in the generation of entanglement: in the low-BKE regime, the growth of entanglement is dominated by coherence, largely independent of magic. However, as BKE increases, the dependence on coherence will gradually be replaced by a dependence on magic. Consequently, in the high-BKE regime, entanglement generation becomes dominated by magic, largely independent of coherence. These results are built on a series of new entropy-theoretic relations and are verified through numerical experiments. We also discuss implications of our results for the resource transitions in classical simulations of mixed states and marginal probabilities and for relating different classical simulation methods.

quant-ph↗

arXiv2026

NeuroSymb-MRG: Differentiable Abductive Reasoning with Active Uncertainty Minimization for Radiology Report Generation

Automatic generation of radiology reports seeks to reduce clinician workload while improving documentation consistency. Existing methods that adopt encoder-decoder or retrieval-augmented pipelines achieve progress in fluency but remain vulnerable to visual-linguistic biases, factual inconsistency, and lack of explicit multi-hop clinical reasoning. We present NeuroSymb-MRG, a unified framework that integrates NeuroSymbolic abductive reasoning with active uncertainty minimization to produce structured, clinically grounded reports. The system maps image features to probabilistic clinical concepts, composes differentiable logic-based reasoning chains, decodes those chains into templated clauses, and refines the textual output via retrieval and constrained language-model editing. An active sampling loop driven by rule-level uncertainty and diversity guides clinician-in-the-loop adjudication and promptbook refinement. Experiments on standard benchmarks demonstrate consistent improvements in factual consistency and standard language metrics compared to representative baselines.

cs.CV↗

arXiv2026

Efficient Quantum Algorithm for Robust Training

Adversarial training is a standard defense against malicious input perturbations in security-critical machine-learning systems. Its main burden is structural: before every parameter update, the current model must first be attacked to find a new adversarial perturbation, making training increasingly expensive and hard to sustain at large-model scale. Here we give an end-to-end quantum procedure for projected-gradient robust training under local stability and sparsity assumptions. The key step is to reformulate the coupled attacker--learner dynamics as a high-dimensional sparse linear system whose terminal block yields the final network-parameter state. In this formulation, the dominant query cost scales linearly with training time steps, up to logarithmic factors, and polylogarithmically with model size, while the full gate complexity records separate input-preparation and sparse-access overheads. This places core computational tasks for AI security on a concrete quantum footing and identifies a regime in which robust-training overhead can be reduced.

quant-ph↗

arXiv2026

Distilling the knowledge with quantum neural networks

Quantum Neural Networks (QNNs) are a promising class of quantum machine learning models with potential quantum advantages when implemented on scalable, error-corrected quantum computers. However, as system sizes increase, deploying QNNs becomes challenging. Similar to their classical counterparts, a key obstacle to their practical applications is that large-scale QNNs may not be easily deployed on smaller systems that have limited resources. Here, we tackle this challenge by compressing QNNs via knowledge distillation. We demonstrate how well-trained QNNs on large systems can be distilled into smaller architectures with similar configurations. We numerically show that knowledge distillation helps reduce the training cost of QNNs in terms of the number of qubits and circuit depth. Additionally, we find that a self-knowledge-distillation approach can accelerate training convergence. We believe our results offer new strategies for the efficient compression and practical deployment of QNNs.

quant-ph↗

arXiv2026

Joint Deployment and Beamforming Design of Aerial STAR-RIS Aided Networks with Reinforcement Learning

Aerial simultaneous transmitting and reflecting reconfigurable intelligent surfaces (STAR-RIS) enables full-space coverage in dynamic wireless networks. However, most existing works assume fixed user grouping, overlooking the fact that STAR-RIS deployment inherently determines whether users are served via transmission or reflection. To address this, we propose a joint deployment and beamforming framework, where an aerial STAR-RIS dynamically adjusts its location and orientation to adaptively control user grouping and enhance hybrid beamforming. We formulate a Markov decision process (MDP) capturing the coupling among deployment, grouping, and signal design. To solve the resulting non-convex and time-varying problem, we develop a PPO-based reinforcement learning algorithm that adaptively balances user grouping and beamforming resources through online policy learning. Simulation results show 57.1\% and 285\% sum-rate gains over fixed-deployment and RIS-free baselines, respectively, demonstrating the benefit of user-grouping-aware control in STAR-RIS-aided systems.

eess.SY↗

arXiv2026

VINCIE: Unlocking In-context Image Editing from Video

In-context image editing aims to modify images based on a contextual sequence comprising text and previously generated images. Existing methods typically depend on task-specific pipelines and expert models (e.g., segmentation and inpainting) to curate training data. In this work, we explore whether an in-context image editing model can be learned directly from videos. We introduce a scalable approach to annotate videos as interleaved multimodal sequences. To effectively learn from this data, we design a block-causal diffusion transformer trained on three proxy tasks: next-image prediction, current segmentation prediction, and next-segmentation prediction. Additionally, we propose a novel multi-turn image editing benchmark to advance research in this area. Extensive experiments demonstrate that our model exhibits strong in-context image editing capabilities and achieves state-of-the-art results on two multi-turn image editing benchmarks. Despite being trained exclusively on videos, our model also shows promising abilities in multi-concept composition, story generation, and chain-of-editing applications.

cs.CV↗

arXiv2026

A building block of quantum repeaters for scalable quantum networks

Quantum networks, integrating quantum communication, quantum metrology, and distributed quantum computing, could provide secure and efficient information transfer, high-resolution sensing, and an exponential speed-up in information processing. Deterministic entanglement distribution over long distances is a prerequisite for scalable quantum networks, enabling the utilization of device-independent quantum key distribution (DI-QKD) and quantum teleportation to achieve secure and efficient information transfer. However, the exponential photon loss in optical fibres prohibits efficient and deterministic entanglement distribution. Quantum repeaters, incorporating entanglement swapping and entanglement purification with quantum memories, offer the most promising means to overcome this limitation in fibre-based quantum networks. Despite numerous pioneering efforts toward realizing quantum repeaters, a critical bottleneck remains, as remote memory-memory entanglement suffers from decoherence more rapidly than it can be established and purified over long distances. We overcome this by developing long-lived trapped-ion memories, an efficient telecom interface, and a high-visibility single-photon entanglement protocol. This allows us to establish and maintain memory-memory entanglement over a 10 km fibre within the average entanglement establishment time for the same distance. As a direct application, we demonstrate metropolitan-scale DI-QKD, distilling 1,917 secret keys out of 4.05*10^5 Bell pairs over 10 km. We further report a positive key rate over 101 km in the asymptotic limit, extending the achievable distance by more than two orders of magnitude. Our work provides a critical building block for quantum repeaters and marks an important step toward scalable quantum networks.

quant-ph↗

arXiv2026

Traveling waves near shear flows for the inhomogeneous Euler equations with non-constant density

We investigate the existence and nonexistence of traveling wave solutions near monotonic shear flows with non-constant background density for the two-dimensional inhomogeneous Euler equations in a finite channel. For any small $τ>0$, first, we construct nontrivial traveling waves with velocity and density in $H^{5/2-τ}$ and $H^{3/2-τ}$, respectively, showing that inviscid damping fails at these regularities. Second, when the distorted Rayleigh operator has no eigenvalues, we prove that such traveling wave solutions cannot exist in higher regularity spaces ($H^{5/2+τ}$ for velocity and $H^{3/2+τ}$ for density).

math.AP↗

arXiv2026

Tensor Network Assisted Distributed Variational Quantum Algorithm for Large Scale Combinatorial Optimization Problem

Although quantum computing holds promise for solving Combinatorial Optimization Problems (COPs), the limited qubit capacity of NISQ hardware makes large-scale instances intractable. Conventional methods attempt to bridge this gap through decomposition or compression, yet they frequently fail to capture global correlations of subsystems, leading to solutions of limited quality. We propose the Distributed Variational Quantum Algorithm (DVQA) to overcome these limitations, enabling the solution of 1,000-variable instances on constrained hardware. A key innovation of DVQA is its use of the truncated higher-order singular value decomposition to preserve inter-variable dependencies without relying on complex long-range entanglement, leading to a natural form of noise localization where errors scale with subsystem size rather than total qubit count, thus reconciling scalability with accuracy. Theoretical bounds confirm the algorithm's robustness for p-local Hamiltonians. Empirically, DVQA achieves state-of-the-art performance in simulations and has been experimentally validated on the Wu Kong quantum computer for portfolio optimization. This work provides a scalable, noise-resilient framework that advances the timeline for practical quantum optimization algorithms.

quant-ph↗

arXiv2026

Randomization Accelerates Series-Truncated Quantum Algorithms

Quantum algorithms typically demand prohibitively complicated circuits to solve practical problems. Previous studies have shown that classical randomness can accelerate some specific quantum algorithms. In this work, we introduce the Randomized Truncated Series (RTS) which extends this acceleration to all quantum algorithms that rely on truncated series approximations. RTS offers two key advantages: it quadratically suppresses truncation errors and allows for continuous adjustment of the effective truncation order. By leveraging random mixing between two quantum circuits, RTS ensures that their probabilistic combination accurately realizes the desired algorithm, while significantly reducing the average circuit size. We demonstrate the versatility of RTS through concrete applications. Our results shed light on the path toward practical quantum advantage.

quant-ph↗