arXiv subjects

Kai Xu

Publications and source records attributed to Kai Xu.

At least 127 records · Page 7Linked to original sources

arXiv2025

MonoMobility: Zero-Shot 3D Mobility Analysis from Monocular Videos

Accurately analyzing the motion parts and their motion attributes in dynamic environments is crucial for advancing key areas such as embodied intelligence. Addressing the limitations of existing methods that rely on dense multi-view images or detailed part-level annotations, we propose an innovative framework that can analyze 3D mobility from monocular videos in a zero-shot manner. This framework can precisely parse motion parts and motion attributes only using a monocular video, completely eliminating the need for annotated training data. Specifically, our method first constructs the scene geometry and roughly analyzes the motion parts and their initial motion attributes combining depth estimation, optical flow analysis and point cloud registration method, then employs 2D Gaussian splatting for scene representation. Building on this, we introduce an end-to-end dynamic scene optimization algorithm specifically designed for articulated objects, refining the initial analysis results to ensure the system can handle 'rotation', 'translation', and even complex movements ('rotation+translation'), demonstrating high flexibility and versatility. To validate the robustness and wide applicability of our method, we created a comprehensive dataset comprising both simulated and real-world scenarios. Experimental results show that our framework can effectively analyze articulated object motions in an annotation-free manner, showcasing its significant potential in future embodied intelligence applications.

cs.CV↗

arXiv2025

ArticulatedGS: Self-supervised Digital Twin Modeling of Articulated Objects using 3D Gaussian Splatting

We tackle the challenge of concurrent reconstruction at the part level with the RGB appearance and estimation of motion parameters for building digital twins of articulated objects using the 3D Gaussian Splatting (3D-GS) method. With two distinct sets of multi-view imagery, each depicting an object in separate static articulation configurations, we reconstruct the articulated object in 3D Gaussian representations with both appearance and geometry information at the same time. Our approach decoupled multiple highly interdependent parameters through a multi-step optimization process, thereby achieving a stable optimization procedure and high-quality outcomes. We introduce ArticulatedGS, a self-supervised, comprehensive framework that autonomously learns to model shapes and appearances at the part level and synchronizes the optimization of motion parameters, all without reliance on 3D supervision, motion cues, or semantic labels. Our experimental results demonstrate that, among comparable methodologies, our approach has achieved optimal outcomes in terms of part segmentation accuracy, motion estimation accuracy, and visual quality.

cs.CV↗

arXiv2025

Angio-Diff: Learning a Self-Supervised Adversarial Diffusion Model for Angiographic Geometry Generation

Vascular diseases pose a significant threat to human health, with X-ray angiography established as the gold standard for diagnosis, allowing for detailed observation of blood vessels. However, angiographic X-rays expose personnel and patients to higher radiation levels than non-angiographic X-rays, which are unwanted. Thus, modality translation from non-angiographic to angiographic X-rays is desirable. Data-driven deep approaches are hindered by the lack of paired large-scale X-ray angiography datasets. While making high-quality vascular angiography synthesis crucial, it remains challenging. We find that current medical image synthesis primarily operates at pixel level and struggles to adapt to the complex geometric structure of blood vessels, resulting in unsatisfactory quality of blood vessel image synthesis, such as disconnections or unnatural curvatures. To overcome this issue, we propose a self-supervised method via diffusion models to transform non-angiographic X-rays into angiographic X-rays, mitigating data shortages for data-driven approaches. Our model comprises a diffusion model that learns the distribution of vascular data from diffusion latent, a generator for vessel synthesis, and a mask-based adversarial module. To enhance geometric accuracy, we propose a parametric vascular model to fit the shape and distribution of blood vessels. The proposed method contributes a pipeline and a synthetic dataset for X-ray angiography. We conducted extensive comparative and ablation experiments to evaluate the Angio-Diff. The results demonstrate that our method achieves state-of-the-art performance in synthetic angiography image quality and more accurately synthesizes the geometric structure of blood vessels. The code is available at https://github.com/zfw-cv/AngioDiff.

eess.IV↗

arXiv2025

Finite Landscape of 6d N=(1,0) Supergravity

We present a bottom-up argument showing that the number of massless fields in six-dimensional quantum gravitational theories with eight supercharges is uniformly bounded. Specifically, we show that the number of tensor multiplets is bounded by $T\leq 193$, and the rank of the gauge group is restricted to $r(V)\leq 480$. Given that F-theory compactifications on elliptic CY 3-folds are a subset, this provides a bound on the Hodge numbers of elliptic CY 3-folds: $h^{1,1}({\rm CY_3})\leq 491$, $h^{1,1}({\rm Base})\leq 194$ which are saturated by special elliptic CY 3-folds. This establishes that our bounds are sharp and also provides further evidence for the string lamppost principle. These results are derived by a comprehensive examination of the boundaries of the tensor moduli branch, showing that any consistent supergravity theory with $T\neq0$ must include a BPS string in its spectrum corresponding to a "little string theory" (LST) or a critical heterotic string. From this tensor branch analysis, we establish a containment relationship between SCFTs and LSTs embedded within a gravitational theory. Combined with the classification of 6d SCFTs and LSTs, this then leads to the above bounds. Together with previous works, this establishes the finiteness of the supergravity landscape for $d\geq 6$.

hep-th↗

arXiv2025

Unlearning-Enhanced Website Fingerprinting Attack: Against Backdoor Poisoning in Anonymous Networks

Website Fingerprinting (WF) is an effective tool for regulating and governing the dark web. However, its performance can be significantly degraded by backdoor poisoning attacks in practical deployments. This paper aims to address the problem of hidden backdoor poisoning attacks faced by Website Fingerprinting attack, and designs a feasible mothed that integrates unlearning technology to realize detection of automatic poisoned points and complete removal of its destructive effects, requiring only a small number of known poisoned test points. Taking Tor onion routing as an example, our method evaluates the influence value of each training sample on these known poisoned test points as the basis for judgment. We optimize the use of influence scores to identify poisoned samples within the training dataset. Furthermore, by quantifying the difference between the contribution of model parameters on the taining data and the clean data, the target parameters are dynamically adjusted to eliminate the impact of the backdoor attacks. Experiments on public datasets under the assumptions of closed-world (CW) and open-world (OW) verify the effectiveness of the proposed method. In complex scenes containing both clean website fingerprinting features and backdoor triggers, the accuracy of the model on the poisoned dataset and the test dataset is stable at about 80%, significantly outperforming the traditional WF attack models. In addition, the proposed method achieves a 2-3 times speedup in runtime efficiency compared to baseline methods. By incorporating machine unlearning, we realize a WF attack model that exhibits enhanced resistance to backdoor poisoning and faster execution speeds in adversarial settings.

cs.CR↗

arXiv2025

DISCO: Efficient Diffusion Solver for Large-Scale Combinatorial Optimization Problems

Combinatorial Optimization (CO) problems are fundamentally important in numerous real-world applications across diverse industries, characterized by entailing enormous solution space and demanding time-sensitive response. Despite recent advancements in neural solvers, their limited expressiveness struggles to capture the multi-modal nature of CO landscapes. While some research has shifted towards diffusion models, these models still sample solutions indiscriminately from the entire NP-complete solution space with time-consuming denoising processes, which limit their practicality for large problem scales. We propose DISCO, an efficient DIffusion Solver for large-scale Combinatorial Optimization problems that excels in both solution quality and inference speed. DISCO's efficacy is twofold: First, it enhances solution quality by constraining the sampling space to a more meaningful domain guided by solution residues, while preserving the multi-modal properties of the output distributions. Second, it accelerates the denoising process through an analytically solvable approach, enabling solution sampling with minimal reverse-time steps and significantly reducing inference time. DISCO delivers strong performance on large-scale Traveling Salesman Problems and challenging Maximal Independent Set benchmarks, with inference time up to 5.28 times faster than other diffusion alternatives. By incorporating a divide-and-conquer strategy, DISCO can well generalize to solve unseen-scale problem instances, even surpassing models specifically trained for those scales.

cs.AI↗

arXiv2025

Scalar curvature and volume entropy of hyperbolic 3-manifolds

We show that any closed hyperbolic 3-manifold M admits a Riemannian metric with scalar curvature at least -6, but with volume entropy strictly larger than 2. In particular, this construction gives counterexamples to a conjecture of I. Agol, P. Storm and W. Thurston.

math.DG↗

arXiv2025

Designing Pin-pression Gripper and Learning its Dexterous Grasping with Online In-hand Adjustment

We introduce a novel design of parallel-jaw grippers drawing inspiration from pin-pression toys. The proposed pin-pression gripper features a distinctive mechanism in which each finger integrates a 2D array of pins capable of independent extension and retraction. This unique design allows the gripper to instantaneously customize its finger's shape to conform to the object being grasped by dynamically adjusting the extension/retraction of the pins. In addition, the gripper excels in in-hand re-orientation of objects for enhanced grasping stability again via dynamically adjusting the pins. To learn the dynamic grasping skills of pin-pression grippers, we devise a dedicated reinforcement learning algorithm with careful designs of state representation and reward shaping. To achieve a more efficient grasp-while-lift grasping mode, we propose a curriculum learning scheme. Extensive evaluations demonstrate that our design, together with the learned skills, leads to highly flexible and robust grasping with much stronger generality to unseen objects than alternatives. We also highlight encouraging physical results of sim-to-real transfer on a physically manufactured pin-pression gripper, demonstrating the practical significance of our novel gripper design and grasping skill. Demonstration videos for this paper are available at https://github.com/siggraph-pin-pression-gripper/pin-pression-gripper-video.

cs.RO↗

arXiv2025

Statistical Mechanics and Categorical Entropy

This paper investigates the relationship between categorical entropy and von Neumann entropy of quantum lattices. We begin by studying the von Neumann entropy, proving that the average von Neumann entropy per site converges to the logarithm of an algebraic integer in the low-temperature and thermodynamic limits. Next, we turn to categorical entropy. Given an endofunctor of a saturated A-infinity-category, we construct a corresponding lattice model, through which the categorical entropy can be understood in terms of the information encoded in the model. Finally, by introducing a gauged lattice framework, we unify these two notions of entropy. This unification leads naturally to a sufficient condition for a conjectural algebraicity property of categorical entropy, suggesting a deeper structural connection between A-infinity-categories and statistical mechanics.

cond-mat.stat-mech↗

arXiv2025

CityEQA: A Hierarchical LLM Agent on Embodied Question Answering Benchmark in City Space

Embodied Question Answering (EQA) has primarily focused on indoor environments, leaving the complexities of urban settings-spanning environment, action, and perception-largely unexplored. To bridge this gap, we introduce CityEQA, a new task where an embodied agent answers open-vocabulary questions through active exploration in dynamic city spaces. To support this task, we present CityEQA-EC, the first benchmark dataset featuring 1,412 human-annotated tasks across six categories, grounded in a realistic 3D urban simulator. Moreover, we propose Planner-Manager-Actor (PMA), a novel agent tailored for CityEQA. PMA enables long-horizon planning and hierarchical task execution: the Planner breaks down the question answering into sub-tasks, the Manager maintains an object-centric cognitive map for spatial reasoning during the process control, and the specialized Actors handle navigation, exploration, and collection sub-tasks. Experiments demonstrate that PMA achieves 60.7% of human-level answering accuracy, significantly outperforming competitive baselines. While promising, the performance gap compared to humans highlights the need for enhanced visual reasoning in CityEQA. This work paves the way for future advancements in urban spatial intelligence. Dataset and code are available at https://github.com/BiluYong/CityEQA.git.

cs.AI↗

arXiv2025

Interplay between disorder and topology in Thouless pumping on a superconducting quantum processor

Topological phases are robust against weak perturbations, but break down when disorder becomes sufficiently strong. However, moderate disorder can also induce topologically nontrivial phases. Thouless pumping, as a (1+1)D counterpart of the integer quantum Hall effect, is one of the simplest manifestations of topology. Here, we report experimental observations of the competition and interplay between Thouless pumping and disorder on a 41-qubit superconducting quantum processor. We improve a Floquet engineering technique to realize cycles of adiabatic pumping by simultaneously varying the on-site potentials and the hopping couplings. We demonstrate Thouless pumping in the presence of disorder and show its breakdown as the strength of disorder increases. Moreover, we observe two types of topological pumping that are induced by on-site potential disorder and hopping disorder, respectively. In particular, an intrinsic topological pump that is induced by quasi-periodic hopping disorder has never been experimentally realized before. Our highly controllable system provides a valuable quantum simulating platform for studying various aspects of topological physics in the presence of disorder.

quant-ph↗

arXiv2025

Finiteness and the Emergence of Dualities

We argue that the finiteness of quantum gravity amplitudes in fully compactified theories (at least in supersymmetric cases) leads to a bottom-up prediction for the existence of non-trivial dualities. In particular, finiteness requires the moduli space of massless fields to be compactifiable, meaning that its volume must be finite or at least grow no faster than that of Euclidean space. Moreover, we relate the compactifiability of moduli spaces to the condition that the lattice of charged objects transform in a semisimple representation under the action of the duality group. These ideas are supported by a wide variety of string theory examples.

hep-th↗

arXiv2025

Tuning the Quantum Mpemba Effect in Isolated System by Initial State Engineering

We investigate the quantum Mpemba effect (QME) in isolated, non-integrable quantum systems, where relaxation dynamics depend on structure of the initial states. By analyzing the distribution of initial states across symmetrical subspaces, we identify a tunable mechanism that influences the emergence of QME, showing faster relaxation from certain out-of-equilibrium states. Additionally, we propose an experimentally realizable quantum circuit, which requires no complex controls on quantum simulator platforms and serves to verify our theoretical predictions. These results establish symmetry-resolved state engineering as a practical tool for manipulating non-equilibrium quantum dynamics.

quant-ph↗

arXiv2025

Web-Bench: A LLM Code Benchmark Based on Web Standards and Frameworks

The application of large language models (LLMs) in the field of coding is evolving rapidly: from code assistants, to autonomous coding agents, and then to generating complete projects through natural language. Early LLM code benchmarks primarily focused on code generation accuracy, but these benchmarks have gradually become saturated. Benchmark saturation weakens their guiding role for LLMs. For example, HumanEval Pass@1 has reached 99.4% and MBPP 94.2%. Among various attempts to address benchmark saturation, approaches based on software engineering have stood out, but the saturation of existing software engineering benchmarks is rapidly increasing. To address this, we propose a new benchmark, Web-Bench, which contains 50 projects, each consisting of 20 tasks with sequential dependencies. The tasks implement project features in sequence, simulating real-world human development workflows. When designing Web-Bench, we aim to cover the foundational elements of Web development: Web Standards and Web Frameworks. Given the scale and complexity of these projects, which were designed by engineers with 5 to 10 years of experience, each presents a significant challenge. On average, a single project takes 4 to 8 hours for a senior engineer to complete. On our given benchmark agent (Web-Agent), SOTA (Claude 3.7 Sonnet) achieves only 25.1% Pass@1, significantly lower (better) than SWE-Bench's Verified (65.4%) and Full (33.8%) scores. Finally, we discuss that in any development field, Standards and Frameworks represent foundational knowledge and efficiency tools, respectively, and LLMs require optimization tailored to them.

cs.AI↗

arXiv2025

Quantum Acoustics with Superconducting Qubits in the Multimode Transition-Coupling Regime

Hybrid mechanical-superconducting systems for quantum information processing have attracted significant attention due to their potential applications. In such systems, the weak coupling regime, dominated by dissipation, has been extensively studied. The strong coupling regime, where coherent energy exchange exceeds losses, has also been widely explored. However, the transition-coupling regime, which lies between the above two and exhibits rich, unique physics, remains underexplored. In this study, we fabricate a tunable coupling device to investigate the coupling of a superconducting transmon qubit to a seven-mode surface acoustic wave resonator (SAWR), with a particular focus on the transition-coupling regime. Through a series of phonon oscillation experiments and studies in the dispersive regime, we systematically characterize the performance of the SAWR. We then explore the complex dynamics of energy exchange between the qubit and the mechanical modes, highlighting the interplay between dissipation and coherence. Finally, we propose a protocol for qubit readout and fast reset with a multimode mechanical cavity using one mode for readout and another mode for reset. We have demonstrated in simulation that the qubit achieves both fast reset and high coherence performance when the qubit is coupled to the reset mode in the transition-coupling regime.

quant-ph↗

arXiv2025

CAD-NeRF: Learning NeRFs from Uncalibrated Few-view Images by CAD Model Retrieval

Reconstructing from multi-view images is a longstanding problem in 3D vision, where neural radiance fields (NeRFs) have shown great potential and get realistic rendered images of novel views. Currently, most NeRF methods either require accurate camera poses or a large number of input images, or even both. Reconstructing NeRF from few-view images without poses is challenging and highly ill-posed. To address this problem, we propose CAD-NeRF, a method reconstructed from less than 10 images without any known poses. Specifically, we build a mini library of several CAD models from ShapeNet and render them from many random views. Given sparse-view input images, we run a model and pose retrieval from the library, to get a model with similar shapes, serving as the density supervision and pose initializations. Here we propose a multi-view pose retrieval method to avoid pose conflicts among views, which is a new and unseen problem in uncalibrated NeRF methods. Then, the geometry of the object is trained by the CAD guidance. The deformation of the density field and camera poses are optimized jointly. Then texture and density are trained and fine-tuned as well. All training phases are in self-supervised manners. Comprehensive evaluations of synthetic and real images show that CAD-NeRF successfully learns accurate densities with a large deformation from retrieved CAD models, showing the generalization abilities.

cs.CV↗

arXiv2025

PIN-WM: Learning Physics-INformed World Models for Non-Prehensile Manipulation

While non-prehensile manipulation (e.g., controlled pushing/poking) constitutes a foundational robotic skill, its learning remains challenging due to the high sensitivity to complex physical interactions involving friction and restitution. To achieve robust policy learning and generalization, we opt to learn a world model of the 3D rigid body dynamics involved in non-prehensile manipulations and use it for model-based reinforcement learning. We propose PIN-WM, a Physics-INformed World Model that enables efficient end-to-end identification of a 3D rigid body dynamical system from visual observations. Adopting differentiable physics simulation, PIN-WM can be learned with only few-shot and task-agnostic physical interaction trajectories. Further, PIN-WM is learned with observational loss induced by Gaussian Splatting without needing state estimation. To bridge Sim2Real gaps, we turn the learned PIN-WM into a group of Digital Cousins via physics-aware randomizations which perturb physics and rendering parameters to generate diverse and meaningful variations of the PIN-WM. Extensive evaluations on both simulation and real-world tests demonstrate that PIN-WM, enhanced with physics-aware digital cousins, facilitates learning robust non-prehensile manipulation skills with Sim2Real transfer, surpassing the Real2Sim2Real state-of-the-arts.

cs.LG↗

arXiv2025

F2M-Reg: Unsupervised RGB-D Point Cloud Registration with Frame-to-Model Optimization

This work studies the problem of unsupervised RGB-D point cloud registration, which aims at training a robust registration model without ground-truth pose supervision. Existing methods usually leverages unposed RGB-D sequences and adopt a frame-to-frame framework based on differentiable rendering to train the registration model, which enforces the photometric and geometric consistency between the two frames for supervision. However, this frame-to-frame framework is vulnerable to inconsistent factors between different frames, e.g., lighting changes, geometry occlusion, and reflective materials, which leads to suboptimal convergence of the registration model. In this paper, we propose a novel frame-to-model optimization framework named F2M-Reg for unsupervised RGB-D point cloud registration. We leverage the neural implicit field as a global model of the scene and optimize the estimated poses of the frames by registering them to the global model, and the registration model is subsequently trained with the optimized poses. Thanks to the global encoding capability of neural implicit field, our frame-to-model framework is significantly more robust to inconsistent factors between different frames and thus can provide better supervision for the registration model. Besides, we demonstrate that F2M-Reg can be further enhanced by a simplistic synthetic warming-up strategy. To this end, we construct a photorealistic synthetic dataset named Sim-RGBD to initialize the registration model for the frame-to-model optimization on real-world RGB-D sequences. Extensive experiments on four challenging benchmarks have shown that our method surpasses the previous state-of-the-art counterparts by a large margin, especially under scenarios with severe lighting changes and low overlap. Our code and models are available at https://github.com/MrIsland/F2M_Reg.

cs.CV↗