Searcharxiv⌕ Search

arXiv subjects

Kai Wang

Publications and source records attributed to Kai Wang.

At least 127 records · Page 7Linked to original sources
arXiv2026

MAGE: View-guided Point Cloud Completion with Efficient Modality Alignment and Adaptive Geometry Enhancement

View-based point cloud completion aims to recover a complete 3D shape from a partial point cloud, guided by a single-view image. However, existing approaches often suffer from limited performance due to weak modality alignment and limited self-geometry enhancement. To overcome these challenges, we propose a unified geometry-aware framework that integrates efficient modality alignment and adaptive geometry enhancement, mainly to address cross-modal geometric inconsistency of view-guided point cloud completion. Specifically, we propose a geometry-aware modality alignment by integrating a shared self-attention Transformer and cross-modality reconstruction supervision, which aims to bring features of the image and point cloud close to each other in a shared latent space describing the 3D object. To enhance the perception of global shape and local geometric details, we propose an adaptive geometry-aware self-attention module, which simultaneously considers local geometry-aware attention computation and the spatially-variant feature fusion. In addition, we apply a geometry-perceptive anchor refinement module to reorganize the anchor points (representing a local region of the shape) under appropriate supervision, further boosting the completion performance of our method. Extensive experiments on both synthetic and real-world datasets demonstrate that our method achieves superior performance over existing approaches. Our code will be available at https://github.com/weizequan/MAGE.

cs.CV↗
arXiv2026

Competing Accelerated Failure Time Models for Multiple Concurrent Failure Mechanisms

The rising prevalence of complex diseases characterised by multiple coexisting and interacting etiological processes poses critical challenges for survival analysis and precision medicine, particularly as population ageing renders mutually exclusive models increasingly untenable. We propose a competing accelerated failure time (cAFT) framework to understand the individual-specific temporal dynamics of disease competition and interaction based on a first-to-fail principle. Specifically, we introduce an individualised, time-varying winning probability to quantify the relative contributions of latent causes and provide an interpretable basis for patient stratification within distinct subtypes. Consistency and asymptotic normality are established for the maximum likelihood estimation of the parameters, with practical implementation via an expectation-maximisation (EM) algorithm. We illustrate the model's effectiveness and efficiency through numerical simulations and real-world applications, including biomarker discovery for 28-day survival in sepsis and overall survival in lung adenocarcinoma. Compared with standard AFT and Cox proportional hazards models, the cAFT model consistently improves predictive accuracy (C-index and iAUC gains of 5--10%) and reveals subtype-dependent gene effects within distinct biological pathways across heterogeneous patient subgroups. Conclusively, the cAFT model provides deeper insights into patient prognosis and potential personalised therapeutic strategies.

stat.ME↗
arXiv2026

Hyperfine-structure constants of the $^{45}\!$Sc II ion and the nuclear quadrupole moment

In this work, we calculate the hyperfine-structure constants of the $^{45}$Sc$^{+}$ ion using a relativistic hybrid approach that combines configuration-interaction and coupled-cluster singles-and-doubles methods. Magnetic-dipole and electric-quadrupole hyperfine-structure constants are determined for the states arising from the $3d4s$, $3d^{2}$, $4s^{2}$, $4s4p$, $3d4p$, $3d5s$, $3d4d$, and $3d5p$ configurations. For most of these states, our magnetic-dipole hyperfine-structure constants agree well with available experimental data and represent a substantial improvement over previous theoretical results. By combining our calculated electric-field gradients with the measured electric-quadrupole hyperfine-structure constants for the $^{3}F_{2,3,4}$, $^{3}P_{1,2}$, and $^{1}G_{4}$ states within the $3d^{2}$ configuration, we derive a nuclear quadrupole moment $Q=-0.222(5)$ b, which is fully consistent with the value recently obtained from molecular data ( J. P. Dognon and P. Pyykkö, Phys. Chem. Chem. Phys. 27, 20453 (2025).).

physics.atom-ph↗
arXiv2026

Electron Delocalization versus Emission Coherence of Quantum Dot Superlattices

Cooperative emission is a collective quantum optical process that requires macroscopic phase coherence among coupled emitters. Recent observations of cooperative emission in QD superlattices have renewed interest in how such coherence emerges in nanostructured solids. Meanwhile, theoretical studies have long discussed the relationship between electronic delocalization and coherence, particularly whether delocalized states necessarily give rise to cooperative emission. This study addresses this question through power-dependent steady-state PL and time-resolved PL decay measurements. The findings indicate that, although the quantum resonance peak exhibits delocalized excitonic characteristics, it shows no signatures of cooperative radiation. In particular, neither superlinear intensity scaling nor power-dependent emission delay was observed, indicating the absence of cooperative-radiation signatures. This can be understood from two disorder-related aspects. Temperature-dependent spectroscopy reveals pronounced inhomogeneous broadening and low-temperature dark-exciton participation, pointing to intra-domain static disorder and exciton-state mixing. These effects collectively hinder the establishment of macroscopic coherence. The temperature dependence of the quantum resonance peak decay lifetime is consistent with two-dimensional exciton dynamics. This work provides direct experimental evidence that electronic delocalization can be decoupled from cooperative coherence in CdSe quantum dot superlattices.

cond-mat.mes-hall↗
arXiv2026

SciFlow: Semantic Cross Interference for Self-Supervised Optical Flow Domain Generalization

Motions of objects and scenes carry essential intelligence in video understanding, offering rich cues for interpreting dynamic settings and interactions. Due to the cost and scarcity of high-quality annotation or ground truth of pixel-wise optical flow, however, motion estimation models are typically trained in synthetic domains while deployed in real-world domains. Addressing synthetic-to-real domain generalization challenges has been crucial for developing practical solutions in diverse open-world use cases. This paper introduces SciFlow, a simple yet effective, network-agnostic, training-based approach that leverages self-supervised learning to generalize motion estimation across synthetic and open-world domains. Specifically, SciFlow imposes semantic interference from open-world images onto synthetic images during training, blending indomain features with cross-domain interference, which enables the network to adapt to the real-world domains. Additionally, SciFlow utilizes geometric consistency to ensure validity of the self-supervision. Our experiment results show that SciFlow not only significantly enhances model robustness amidst domain variations, but also remarkably enables synthetic-to-real domain generalization without requiring any ground truth in the open world.

cs.CV↗
arXiv2026

Resilient Control Lyapunov Function-based Quadratic Program for Quadrotors Under Cyberattacks

Ensuring the operational safety of quadrotors under partial actuator failures, lumped external disturbances, and malicious cyberattacks is a critical challenge due to the system's underactuated and highly nonlinear nature. Building on the existing result of a fault-tolerant control approach for a quadrotor experiencing a complete loss of two opposing rotors \cite{chen2024quadrotor}, this letter further addresses the additional challenge of malicious cyberattacks, which could be unknown and unbounded. While the baseline control law, rooted in proportional-derivative (PD) feedback and observer-based decoupling, effectively handles mismatched disturbances, it remains vulnerable to maliciously injected cyberattacks on the pseudo-control channels. To address this, a Resilient Control Lyapunov Function-based Quadratic Program (RCLF-QP) is developed, where a resilient compensational term with real-time online adaptation is designed in the conventional CLF to compensate for the maliciously injected unknown and unbounded attacks. Compared with the PD feedback control, the proposed QP-based constrained optimization control framework provides a systematic and extensible framework that allows new control objectives and constraints to be seamlessly integrated without altering the underlying stability guarantees. The overall proposed controller integrates a model-based extended state observer with the proposed RCLF-QP mechanism to mitigate both lumped disturbances caused by aerodynamics and strong wind, and adversarial cyberattacks injected by malicious adversaries. Simulations in a high-fidelity environment demonstrate that the proposed RCLF-QP control architecture prevents trajectory divergence and system instability in scenarios where the baseline controller fails in maintaining the stability of Quadrotors under malicious attacks.

eess.SY↗
arXiv2026

On-Demand Service Zone Design for Energy-Constrained Spatial Queueing Systems

Electric service vehicles (ESVs), such as mobile chargers and drone-based service units, are becoming an important operational resource for on-demand service systems. Unlike conventional spatial servers, ESV operations are shaped by battery limits and recharging needs, which affect dispatch feasibility and spatial deployment decisions. We develop an energy-constrained hypercube spatial queueing model that embeds battery-state dynamics into the classical hypercube framework and uses a semi-Markov representation to estimate steady-state performance. We then formulate a joint location--zoning problem for station placement and service zone design. The resulting large-scale mixed-integer nonlinear program admits a set partitioning reformulation whose column coefficients are not available in closed form. We therefore develop a Branch-Price-and-Evaluation framework for set partitioning problems with externally computable column coefficients: upper-bounding surrogates guide pricing, and iterative exact evaluation updates the coefficients of active columns. Computational results show that explicit energy modeling significantly reduces false service promises and yields more credible planning decisions. They also reveal a load-dependent reversal in zoning: pooling is preferable under light demand, whereas tighter zoning becomes more profitable as demand increases. Over the tested range, profitability is driven more by zoning than by battery improvement, suggesting that managers should get service zone design right before investing in battery upgrades; this caution is reinforced by the counterintuitive finding that larger batteries may delay replenishment and reduce fleet readiness under sparse demand. These findings show that energy feasibility is not merely a matter of battery-capacity expansion, but a design dimension that shapes service-zone configuration.

cs.PF↗
arXiv2026

Improving Vision-Language-Action Model Fine-Tuning with Structured Stage and Keyframe Supervision

Vision-Language-Action (VLA) models have shown strong potential for generalizable robotic manipulation. During fine-tuning, however, action supervision applies equally across all timesteps, without structured supervision on which manipulation stage the robot is in or what the next gripper-event target should be. This causes failures to concentrate around challenging gripper-event transitions. To address this, we propose StaKe, a plug-in auxiliary supervision framework that automatically derives two complementary signals from demonstration gripper states without manual annotation: a stage classifier that identifies the current manipulation stage, and a keyframe predictor that estimates the target joint action at the next gripper transition. Both are modeled as lightweight auxiliary heads that enrich the learned representations during training, while leaving the base VLA policy architecture and inference loop unchanged. Experiments on bimanual simulation and single-arm Franka real-robot tasks show that StaKe consistently improves success rates (relative gains of 14% and 56%, respectively), with larger improvements on longer-horizon tasks that involve more gripper-event transitions. Ablation studies validate each design choice, and qualitative analysis confirms that the learned representations faithfully track manipulation stages. These results indicate that structured supervision is an effective and general strategy for enhancing VLA fine-tuning in long-horizon manipulation. Project website: https://hi-yuanxu.github.io/StaKe-Web/

cs.RO↗
arXiv2026

Disk-Based Interval Indexes Under the Increasing Ending Time Assumption

Indexes for large collections of intervals are common in temporal databases, where each record has a lifespan, or validity interval. Despite their conceptual differences, we demonstrate that interval indexes can be captured by some corner structure in a 2D space. This representation facilitates the optimization of query processing by identifying nodes that must contain query results versus nodes that may contain results. In addition, we explore the assumption that intervals arrive in order of increasing ending time (IET) to develop disk-based indexes that have compact size, efficient insertions, and fast query processing. Specifically, we first develop CEB, an index in the corner space defined by the interval center and endpoint. Our second contribution is TIDE, which organizes intervals by their duration and endpoint. CEB and TIDE adopt a two-layer architecture, where the leaf nodes of a top tree (ordering intervals by their center or duration) correspond to the root nodes of bottom trees, ordering intervals by their endpoints. Both top and bottom trees are append-only B+-trees to facilitate fast insertions. CEB and TIDE outperform state-of-the-art competitors in terms of index size and insertion speed. In addition, TIDE is always faster in query processing, sometimes by orders of magnitude.

cs.DB↗
arXiv2026

Trip+: Benchmarking Agents in Personalized Interactive Travel Planning

Interactive travel planning has become a popular use case for language models. Agents are deployed to manage evolving preferences and unexpected disruptions over multiple turns. Such settings require models to make complex, profile-conditioned planning decisions. However, existing benchmarks often evaluate feasibility, personalization, or interaction in relatively isolated settings. We therefore introduce Trip+ to measure the ability of agents to plan travel holistically. In Trip+, given traveler profiles and dynamic interactions, agents must generate and revise minute-level itineraries. End-to-end traveler experiences are evaluated via an LLM-based simulator, enabling the assessment of subjective metrics like fatigue. Our scenarios range from simple request resolutions to complex environment-driven replanning. We evaluate 18 LMs and find a consistent gap in experiential quality. Models favor technically feasible but exhausting itineraries that diverge sharply from profiled traveler preferences.

cs.AI↗
arXiv2026

HY-WU (Part I): An Extensible Functional Neural Memory Framework and An Instantiation in Text-Guided Image Editing

Foundation models are transitioning from offline predictors to deployed systems expected to operate over long time horizons. In real deployments, objectives are not fixed: domains drift, user preferences evolve, and new tasks appear after the model has shipped. This elevates continual learning and instant personalization from optional features to core architectural requirements. Yet most adaptation pipelines still follow a static weight paradigm: after training (or after any adaptation step), inference executes a single parameter vector regardless of user intent, domain, or instance-specific constraints. This treats the trained or adapted model as a single point in parameter space. In heterogeneous and continually evolving regimes, distinct objectives can induce separated feasible regions over parameters, forcing any single shared update into compromise, interference, or overspecialization. As a result, continual learning and personalization are often implemented as repeated overwriting of shared weights, risking degradation of previously learned behaviors. We propose HY-WU (Weight Unleashing), a memory-first adaptation framework that shifts adaptation pressure away from overwriting a single shared parameter point. HY-WU implements functional (operator-level) memory as a neural module: a generator that synthesizes weight updates on-the-fly from the instance condition, yielding instance-specific operators without test-time optimization.

cs.CV↗
arXiv2026

Finite and disordered Kitaev chains: a large deviation study

Topological edge states are celebrated for their robustness against disorder, yet the interplay between disorder and system size remains poorly understood. We use large deviations theory as a framework to study finite-size effects beyond the central limit theorem. We analyze Lyapunov exponent fluctuations in the static and periodically driven disordered Kitaev chain and find an asymmetry in the large deviations statistics that makes stronger edge localizations of Majorana zero modes exponentially more likely than weaker ones. We demonstrate that this fluctuation asymmetry is not tied to the topological phase. This asymmetry endows topological edge states with an additional protection against disorder and persists across a broad class of disorder distribution. We show how to use our framework to find the minimum system size required to satisfy topological quantum computing constraints.

cond-mat.dis-nn↗
arXiv2026

Advances in 4D Representation: Geometry, Motion, and Interaction

We present a survey on 4D generation and reconstruction, a fast-evolving subfield of computer graphics whose developments have been propelled by recent advances in neural fields, geometric and motion deep learning, as well as 3D generative artificial intelligence (GenAI). While our survey is not the first of its kind, we build our coverage of the domain from a unique and distinctive perspective of 4D representations, to model 3D geometry evolving over time while exhibiting motion and interaction. Specifically, instead of offering an exhaustive enumeration of many works, we take a more selective approach by focusing on representative works to highlight both the desirable properties and ensuing challenges of each representation under different computation, application, and data scenarios. The main take-away message we aim to convey to the readers is on how to select and then customize the appropriate 4D representations for their tasks. Organizationally, we separate the 4D representations based on three key pillars: geometry, motion, and interaction. Our discourse will not only encompass the most popular representations of today, such as neural radiance fields (NeRFs) and 3D Gaussian Splatting (3DGS), but also bring attention to relatively under-explored representations in the 4D context, such as structured models and long-range motions. Throughout our survey, we will reprise the role of large language models (LLMs) and video foundational models (VFMs) in a variety of 4D applications, while steering our discussion towards their current limitations and how they can be addressed. We also provide a dedicated coverage on what 4D datasets are currently available, as well as what is lacking, in driving the subfield forward. Project page:https://mingrui-zhao.github.io/4DRep-GMI/

cs.CV↗
arXiv2026

A Fully First-Order Layer for Differentiable Optimization

Differentiable optimization layers enable learning systems to make decisions by solving embedded optimization problems. However, computing gradients via implicit differentiation requires solving a linear system with Hessian terms, which is both compute- and memory-intensive. To address this challenge, we propose a novel algorithm that computes the gradient using only first-order information. The key insight is to rewrite the differentiable optimization as a bilevel optimization problem and leverage recent advances in bilevel methods. Specifically, we introduce an active-set Lagrangian hypergradient oracle that avoids Hessian evaluations and provides finite-time, non-asymptotic approximation guarantees. We show that an approximate hypergradient can be computed using only first-order information in $\tilde{O}(1)$ time, leading to an overall complexity of $\tilde{O}(δ^{-1}ε^{-3})$ for constrained bilevel optimization, which matches the best known rate for non-smooth non-convex optimization. Furthermore, we release an open-source Python library that can be easily adapted from existing solvers. The source code is available at https://github.com/guaguakai/FFOLayer.

cs.LG↗
arXiv2026

LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies

Vision-Language-Action models (VLAs) leverage large-scale vision-language pretraining for semantic robot control, but often lack explicit foresight into how robot actions change the scene. World-Action Models (WAMs) address this limitation by conditioning policies on predicted futures, yet existing approaches typically rely on computationally expensive video generation with substantial pixel-level redundancy. We present LaWAM, a Latent World Action Model that exposes predictive dynamics to robot policies through compact latent visual subgoals instead of reconstructed future video. At the core of LaWAM is a latent-action-conditioned Latent World Model (LaWM). We obtain LaWM by training a latent action model in the latent space of a pretrained vision foundation model and repurposing its forward decoder to predict future observation features for scene evolution. LaWAM then conditions action generation on these predicted latent visual subgoals to enable dynamics-aware robot control. LaWAM achieves state-of-the-art or competitive success rates (SRs) across LIBERO (98.6% SR), RoboTwin (91.22% SR), and real-world manipulation tasks while retaining low-latency inference. LaWAM runs in 187 ms per action-chunk prediction and achieves up to 24x lower wall-clock latency than pixel-space WAMs.

cs.RO↗
arXiv2026

WAM-Nav: Asymmetric Latent World-Action Modeling for Unified Visual Navigation

Visual navigation requires generating smooth and collision-free trajectories under complex geometric and physical constraints. Existing reactive policies that directly map observations to actions lack anticipatory reasoning, limiting their ability to proactively avoid obstacles. While visual imagination offers predictive foresight, conventional modular approaches separate scene prediction from policy learning, often leading to error accumulation and inefficient inference. To address these limitations, we propose WAM-Nav, a Latent World-Action Model for embodied visual navigation that jointly learns action generation and latent visual foresight, enabling more robust and foresighted navigation decisions without compromising inference efficiency. Specifically, WAM-Nav utilizes a shared Diffusion Transformer for asymmetric joint diffusion to concurrently generate long-horizon actions and short-horizon visual foresight, reducing the inference latency and visual error accumulation inherent in multi-step autoregressive rollouts. To further encourage smooth and consistent trajectory generation, we introduce a dual-stream contextual conditioning mechanism that integrates episode-level ego-motion history with sequential visual observations. Combined with a unified goal alignment module that preserves balanced representations across goal types, WAM-Nav naturally supports Image-Goal, Point-Goal, and No-Goal exploration within a single policy. Extensive experiments on the challenging ClutterScenes and InternScenes benchmarks demonstrate strong generalization of WAM-Nav, particularly on Image-Goal and Point-Goal navigation, where it improves success rates by 15.7% and 3.3%, respectively. Real-world deployment further validates effective zero-shot sim-to-real transfer, achieving an average 85% task success rate across diverse indoor and outdoor environments.

cs.RO↗
arXiv2026

PaLMR: Towards Faithful Visual Reasoning via Multimodal Process Alignment

Reinforcement learning has recently improved the reasoning ability of Large Language Models and Multimodal LLMs, yet prevailing reward designs emphasise final-answer correctness and consequently tolerate process hallucinations--cases where models reach the right answer while misperceiving visual evidence. We address this process-level misalignment with PaLMR, a framework that aligns not only outcomes but also the reasoning process itself. PaLMR comprises two complementary components: a perception-aligned data layer that constructs process-aware reasoning data with structured pseudo-ground-truths and verifiable visual facts, and a process-aligned optimisation layer that constructs a hierarchical reward fusion scheme with a process-aware scoring function to encourage visually faithful chains-of-thought and improve training stability. Experiments on Qwen2.5-VL-7B show that our approach substantially reduces reasoning hallucinations and improves visual reasoning fidelity, achieving state-of-the-art results on HallusionBench while maintaining strong performance on MMMU, MathVista, and MathVerse. These findings indicate that PaLMR offers a principled and practical route to process-aligned multimodal reasoning, advancing the reliability and interpretability of MLLMs.

cs.CV↗
arXiv2026

UAOR: Uncertainty-aware Observation Reinjection for Vision-Language-Action Models

Vision-Language-Action (VLA) models leverage pretrained Vision-Language Models (VLMs) as backbones to map images and instructions to actions, demonstrating remarkable potential for generalizable robotic manipulation. To enhance performance, existing methods often incorporate extra observation cues (e.g., depth maps, point clouds) or auxiliary modules (e.g., object detectors, encoders) to enable more precise and reliable task execution, yet these typically require costly data collection and additional training. Inspired by the finding that Feed-Forward Network (FFN) in language models can act as "key-value memory", we propose Uncertainty-aware Observation Reinjection (UAOR), an effective, training-free and plug-and-play module for VLA models. Specifically, when the current language model layer exhibits high uncertainty, measured by Action Entropy, it reinjects key observation information into the next layer's Feed-Forward Network (FFN) through attention retrieval. This mechanism directly augments the hidden states with observation evidence at high-uncertainty layers, enabling more accurate and reliable action generation. Comprehensive experiments show that our method consistently improves diverse VLA models across simulation and real-world tasks with minimal overhead. Notably, UAOR eliminates the need for additional observation cues or modules, making it a versatile and practical plug-in for existing VLA pipelines. The project page is at https://uaor.jiabingyang.cn.

cs.CV↗