Searcharxiv⌕ Search

arXiv subjects

Bo Zhou

Publications and source records attributed to Bo Zhou.

At least 37 records · Page 2Linked to original sources
arXiv2026

Learning Topology-Aware Implicit Field for Unified Pulmonary Tree Modeling with Incomplete Topological Supervision

Pulmonary trees extracted from CT images frequently exhibit topological incompleteness, such as missing or disconnected branches, which substantially degrades downstream anatomical analysis and limits the applicability of existing pulmonary tree modeling pipelines. Current approaches typically rely on dense volumetric processing, explicit graph reasoning, or generic point cloud completion priors, leading to limited efficiency, weak structural awareness, and reduced robustness under realistic structural corruption. We propose TopoField, a topology-aware implicit modeling framework that treats topology repair as a first-class modeling problem and enables unified multi-task inference for pulmonary tree analysis. TopoField represents pulmonary anatomy using sparse surface and skeleton point clouds and learns a continuous implicit field that supports topology repair without relying on complete or explicit disconnection annotations, by training on synthetically introduced structural disruptions over \textit{already} incomplete trees. Building upon the repaired implicit representation, anatomical labeling and lung segment reconstruction are jointly inferred through task-specific implicit functions within a single forward pass. Extensive experiments on the Lung3D+ dataset demonstrate that TopoField consistently improves topological completeness and achieves accurate anatomical labeling and lung segment reconstruction under challenging incomplete scenarios. We further validate TopoField on real incomplete outputs from an external segmentation model, demonstrating its applicability to realistic segmentation pipelines. Owing to its implicit formulation, TopoField attains high computational efficiency, completing all tasks in just over one second per case, highlighting its practicality for large-scale and time-sensitive clinical applications.

cs.CV↗
arXiv2026

The number of cycles of a given length in dense hamiltonian graphs: proving Hilton's conjecture

A classical theorem of Sheehan in 1977 states that every hamiltonian graph $G$ of order $n$ satisfying $e(G)>\left\lfloor \frac{n^2}{4}\right\rfloor+1$ contains at least two cycles of every length $\ell$, $3\le \ell\le n$. In the same paper, Sheehan recorded a conjecture of Hilton, which strengthens this conclusion by asserting that such a graph contains at least $n-\ell+2$ cycles of length $\ell$ for each $3\le \ell\le n$. We prove Hilton's conjecture for all hamiltonian graphs of order at least $440$.

math.CO↗
arXiv2026

PPDM: Pixel Puzzling Diffusion Model for Speed and Memory Efficient Volumetric Medical Image Translation

Diffusion models have demonstrated superior fidelity for medical image-to-image translation, but their extension to high-resolution 3D volumes is severely constrained by prohibitive computational cost and GPU memory requirements. Existing memory-efficient strategies often compromise global volumetric consistency or fine anatomical detail. In this work, we propose the Pixel Puzzling Diffusion Model (PPDM), a simple and effective framework for memory- and speed-efficient 3D medical image translation. PPDM introduces a reversible pixel puzzle-unpuzzle operator that trades spatial resolution for channel dimensionality, substantially reducing activation memory while preserving global context. To further improve efficiency and stability, we adopt a direct bridge diffusion formulation that starts from the conditional input rather than pure noise, enabling the model to focus on task-relevant residuals. In addition, a puzzle-gradient loss is incorporated to enforce spatial coherence and suppress grid-like artifacts introduced by spatial rearrangement. We evaluate PPDM on multiple challenging 3D medical image translation tasks, including low-count PET denoising, joint PET denoising and attenuation correction, and cross-modal MRI translation. Across all tasks, PPDM consistently matches or outperforms full 3D diffusion models while reducing training GPU memory usage by up to an order of magnitude and significantly accelerating inference, and it outperforms existing memory-efficient diffusion approaches based on latent compression or frequency decomposition. These results demonstrate that PPDM provides a practical and scalable solution for high-fidelity 3D diffusion-based medical image translation under limited computational resources.

cs.CV↗
arXiv2026

KAN-MLP-Mixer: A comprehensive investigation of the usage of Kolmogorov-Arnold Networks (KANs) for improving IMU-based Human Activity Recognition

Kolmogorov-Arnold Networks (KANs) have demonstrated an exceptional ability to learn complex functions on clean, low-dimensional data but struggle to maintain performance on noisy and imperfect real-world datasets. In contrast, conventional multi-layer perceptrons (MLPs) are far more tolerant to noise and computationally efficient. Replacing all MLP components with KANs in HAR models often degrades accuracy and computation efficiency, highlighting an open challenge: how to combine KANs' precision with MLPs' noise robustness and efficiency. To address this, we systematically explore various placements of KAN modules within deep HAR networks and propose a hybrid architecture that strategically synergizes the strengths of both paradigms, which uses a KAN-based input embedding layer, retains MLP layers for intermediate feature mixing, and introduces a specialized LarctanKAN module for final activity classification. Across eight public HAR datasets, the hybrid KAN-MLP model achieves an average macro F1 score relative improvement of 5.33\% compared pure-MLP model, significantly outperforming standalone KAN and MLP baselines. Furthermore, integrating this hybrid strategy into other state-of-the-art HAR architectures consistently boosts their performance. Our findings demonstrate that a carefully orchestrated combination of KAN, MLP, or other conventional neural components yields more robust and accurate HAR models for real-world wearable sensing environments.

cs.AI↗
arXiv2026

Supermodularity and Submodularity in Network Interdiction

We study a bilevel network interdiction problem, with an attacker interdicting (attacking) certain components of a network and a defender optimizing operations over the ensuing network. We study when the defender's optimal objective is submodular or supermodular with respect to the attacker's interdiction decisions, for optimizing the bilevel integer program more efficiently. We first consider the min-cost flow (MinCF) interdiction problem and derive necessary and sufficient conditions for the supermodularity or submodularity to hold under three types of attacks, respectively on supplies/demands, flow capacities, and cost coefficients. We extend to other variants, including capacitated facility location, maximum flow (MaxF), and shortest path (SP) interdiction. The conditions hold under general network topologies and parameter settings, and depend solely on the locations of the attacks. We further incorporate additional network information (e.g., detailed parameters and special topologies) to establish less restrictive conditions. We also derive necessary and sufficient conditions for supermodularity or submodularity in SP and MaxF interdiction in series-parallel networks. Furthermore, we explore more challenging interdiction problems where the defender may make additional binary decisions (e.g., repairing or reinforcing the network) and identify conditions that preserve submodularity or recover supermodularity. Via extensive numerical studies with diverse types of attacks, we demonstrate an order-of-magnitude computational speedup achieved by exploiting these properties and generating valid inequalities, for solving network interdiction at scale.

math.OC↗
arXiv2026

SNR-ST-Mix: Sample-specific Neighborhood Regression Mixup for Augmented Spatial Transcriptomics Imputation with Deep Neural Network

Purpose: Spatial transcriptomics (ST) enables gene expression measurements within the tissue context. However, these measurements are often noisy, low-resolution, and sparsely sampled, which limits the recovery of fine spatial structure. Deep neural networks have become powerful tools for expression imputation from histology, but their performance remains constrained by limited sample sizes and a lack of biologically informed augmentation. Most of the existing augmentation strategies for learning are designed for classification tasks rather than regression, which neglect spatial and transcriptomic relationships, leading to biologically implausible interpolations that hinder prediction performance. Approach: To address these limitations, we propose SNR-ST-Mix, a geometry- and expression-aware data augmentation framework designed specifically for ST data. It constrains mixing to a spot's k-nearest spatial neighbors and adaptively weights interpolation coefficients based on expression similarity, generating augmented samples that preserve local biological structure while ensuring spatial smoothness. This dual conditioning yields synthetic examples that expand the effective training manifold, promote generalization, and enhance prediction stability under sample-specific training. Results: Extensive experiments with various tissue types demonstrate that SNR-ST-Mix consistently outperforms conventional augmentation methods without requiring architectural changes or additional computation. Conclusions: SNR-ST-Mix provides an effective and biologically principled augmentation strategy for spatial transcriptomics regression tasks. By explicitly leveraging spatial geometry and transcriptomic similarity, it expands the effective training manifold and improves predictive performance without increasing model complexity.

cs.LG↗
arXiv2026

Less Is More: Training-Free Acceleration Framework of 3D Diffusion Models for Low-Count PET Denoising via Global-Local Trajectory Reduction

Accurate quantification and uptake measurement in PET are critical for assessing disease progression and supporting clinical decision-making. While high-count PET provides reliable image quality, the associated radiation dose and prolonged acquisition remain significant clinical concerns, motivating the adoption of low-count protocols. Diffusion-model-based methods have demonstrated strong potential for restoring low-count PET to near high-count quality, but their iterative sampling procedure becomes prohibitively expensive when applied to high-resolution 3D PET volumes, introducing substantial inference latency that limits practical clinical deployment. To address these challenges, we propose a training-free Global-Local Skipping Strategy that accelerates diffusion model-based 3D PET denoising while simultaneously improving reconstruction quality. The proposed method is plug-and-play and directly applicable to pre-trained diffusion models without retraining or architectural modification. Specifically, we introduce: (i) a global denoising step skipping strategy that initializes the reverse diffusion process from an intermediate denoising step using a noise-consistent transformation of the low-count input, substantially reducing the number of required denoising steps; and (ii) a local feature reuse shortcut that reuses slowly-varying high-level U-Net features across neighboring denoising steps, further reducing per-step computation while preserving image fidelity. We evaluate the proposed approach on multiple PET tracers from in-house and public datasets, including 18F-FDG PET, 68Ga-DOTATATE PET, and 18F-PSMA PET, demonstrating consistent acceleration of over an order of magnitude alongside improved or comparable reconstruction performance relative to the full-step baseline. Blinded reader studies further confirm enhanced clinical confidence and perceived diagnostic quality.

cs.CV↗
arXiv2026

On $k$-connected vertex-pancyclic graphs without pancyclic edges

An edge of a graph of order $n$ is pancyclic if it lies in a cycle of every length $3,\ldots,n$. A graph of order $n$ is vertex-pancyclic if every vertex lies in a cycle of every length $3,\ldots,n$. Recently, Li and Zhan proved that every $2$-connected $[4,2]$-graph of order at least seven contains a pancyclic edge. Zhan asked whether there exists a positive integer $k$ such that every $k$-connected vertex-pancyclic graph contains a pancyclic edge. We answer this question by showing that for every positive integer $k$, there is a $k$-connected vertex-pancyclic graph containing no pancyclic edge.

math.CO↗
arXiv2026

Minimal Wigner-$SU(4)$ Interaction in Microscopic Cluster Models for $α$-Conjugate Nuclei

We present a minimalist, symmetry-guided interaction for microscopic cluster models based on Wigner-$SU(4)$ symmetry. Retaining only an $SU(4)$-invariant two-body attraction and a local three-body repulsion, this framework is implemented via the generator coordinate method (GCM) to describe $α$--$α$ scattering phase shifts, the low-lying spectrum and transition properties of $^{12}\mathrm{C}$, and the cluster spectrum of $^{16}\mathrm{O}$. We show that the long-standing structural tension between the $^{12}\mathrm{C}$ and $^{16}\mathrm{O}$ ground states can be mitigated within this restricted $SU(4)$ operator space without introducing additional phenomenological complexity. These results indicate that Wigner-$SU(4)$ symmetry provides an effective organizing principle for $Nα$ clustering, offering a more fundamental baseline for understanding complex cluster structures.

nucl-th↗
arXiv2026

A Case Study on Energy-Efficient Edge AI Crack Segmentation

Crack segmentation on edge devices can support continuous infrastructure monitoring and maintenance and thereby help to preserve public safety. Furthermore, autonomous infrastructure monitoring by using Unmanned Aerial Vehicles (UAVs) can reduce inspection risks, as human operators no longer need to enter hazardous areas. Edge processing reduces the cost of inspection by eliminating the need for high resolution image storage for offline processing and mitigates the security risks and bandwidth requirements of streaming to cloud servers. Edge inference is difficult due to the limited memory and computational capabilities of edge devices, which can affect both accuracy and latency. Furthermore, battery-powered devices are subject to strict power and energy constraints. Together, these limitations impose restrictions on the model size and computational complexity that can be deployed close to the sensor. In recent years, Transformers have achieved state-of-the-art accuracy in a variety of applications, including semantic segmentation. However, Transformer-based models are typically large and computationally intensive, making efficient edge deployment difficult. To address this, we first apply knowledge distillation to enhance the performance of the base models. We then use PTQ to compress the models further. Additionally, we consider the deployment of these models across multiple edge platforms. To maximize energy efficiency, we design and implement a custom hardware architecture for the models on an FPGA. Our results show that Knowledge Distillation (KD) improves all tested U-Net variants. Among the evaluated platforms, the selected FPGA implementation achieves 398 FPS at 204.99 Frames/J while maintaining a mean IoU of 69.42%. In addition, our best model reaches 71.92% mean IoU, which is 8.82 percentage points (pps) higher than the previously reported result on the CrackVision12K dataset.

eess.SP↗
arXiv2026

Tree-based Credit Assignment for Multi-Agent Memory System

Memory systems are widely adopted to enhance LLMs for long-horizon tasks, and are commonly organized as multi-agent pipelines with memory building, summarizing, and retrieval agents. To empower this system, existing RL-based methods either apply final downstream task rewards (e.g., QA accuracy) for all agents uniformly, which are coarse and ambiguous, or design task-specific rewards for agents on different subtasks, which require costly annotations (e.g., key evidence) and are difficult to define reliably. To address these limitations, we propose Tree-based Credit Assignment for Multi-Agent Memory Systems (TreeMem), which derives agent-specific credit from the final reward without task-specific annotations. Specifically, TreeMem extends the multi-agent pipeline (builder--summarizer--retrieval) into a tree structure, where each agent's outputs are expanded into multiple subsequent branches. The contribution of each agent is estimated via Monte Carlo averaging over its subsequent branches, capturing how intermediate agent actions may influence the final reward. This converts the coarse final reward into agent-specific optimization signals. These signals are then used to update all agent policies simultaneously, helping heterogeneous agents specialize effectively. Experiments on long-horizon benchmarks show that TreeMem improves memory system performance over strong baselines, validating the effectiveness of tree-structured credit assignment for the multi-agent memory system.

cs.MA↗
arXiv2026

Dual-domain Multi-path Self-supervised Diffusion Model for Accelerated MRI Reconstruction

Magnetic resonance imaging (MRI) is a vital diagnostic tool, but its inherently long acquisition times reduce clinical efficiency and patient comfort. Recent advancements in deep learning, particularly diffusion models, have improved accelerated MRI reconstruction. However, existing diffusion models' training often relies on fully sampled data, models incur high computational costs, and often lack uncertainty estimation, limiting their clinical applicability. To overcome these challenges, we propose a novel framework, called Dual-domain Multi-path Self-supervised Diffusion Model (DMSM), that integrates a self-supervised dual-domain diffusion model training scheme, a lightweight hybrid attention network for the reconstruction diffusion model, and a multi-path inference strategy, to enhance reconstruction accuracy, efficiency, and explainability. Unlike traditional diffusion-based models, DMSM eliminates the dependency on training from fully sampled data, making it more practical for real-world clinical settings. We evaluated DMSM on two human MRI datasets, demonstrating that it achieves favorable performance over several supervised and self-supervised baselines, particularly in preserving fine anatomical structures and suppressing artifacts under high acceleration factors. Additionally, our model generates uncertainty maps that correlate reasonably well with reconstruction errors, offering valuable clinically interpretable guidance and potentially enhancing diagnostic confidence.

eess.IV↗
arXiv2026

Unbalanced signed bipartite graphs containing no negative $C_4$ with maximum spectral radius

A signed graph $(G,σ)$ is a graph $G$ together with an assignment $σ$ of either a positive sign or a negative sign to each edge. A signed graph is unbalanced if it contains a cycle with odd number of negative edges. The spectral radius of a signed graph is the spectral radius of its adjacency matrix, in which for vertices $u,v$, the $(u,v)$-entry is $0$, $-1$, or $1$ depending on whether $uv$ represents no edge, a negative edge, or a positive edge, respectively. Recently, Conde, Dratman and Grippo [Discrete Math. 349 (2026) 114942] proved that there is only one unbalanced signed bipartite graph with maximum spectral radius, up to switching isomorphism. In this paper, we establish a spectral Turán type results for signed bipartite graphs. More precisely, we determine the unique graphs containing no negative cycles of length four with maximum spectral radius, up to switching isomorphism, among unbalanced signed bipartite graphs with fixed bipartite sizes and order, respectively.

math.CO↗
arXiv2026

Tight spectral conditions for the Hamiltonicity of $K_{1,r}$-free split graphs

The Hamiltonicity and related subjects of split graphs, and in particular $K_{1,r}$-free split graphs with $r\ge 3$ received much attention. Dai et al. [Discrete Math. 345 (2022) 112826] conjectured that every $(r-1)$-connected $K_{1,r}$-free split graph is Hamiltonian. They proved the case when $r=4$, and earlier Renjith and Sadagopan [Int. J. Found. Comput. Sci. 33 (2022) 1--32] proved the case when $r=3$. Recently, Liu, Song, Zhang and Lai [Discrete Math. 346 (2023) 113402] proved that a split graph is Hamiltonian if and only if it is fully cycle extendable. So for $r=3,4$ every $(r-1)$-connected $K_{1,r}$-free split graph is fully cycle extendable. We give tight spectral sufficient conditions for a $K_{1,r}$-free split graph to be Hamiltonian for $r=3,4$.

math.CO↗
arXiv2026

Learning 3D Representations for Spatial Intelligence from Unposed Multi-View Images

Robust 3D representation learning forms the perceptual foundation of spatial intelligence, enabling downstream tasks in scene understanding and embodied AI. However, learning such representations directly from unposed multi-view images remains challenging. Recent self-supervised methods attempt to unify geometry, appearance, and semantics in a feed-forward manner, but they often suffer from weak geometry induction, limited appearance detail, and inconsistencies between geometry and semantics. We introduce UniSplat, a feed-forward framework designed to address these limitations through three complementary components. First, we propose a dual-masking strategy that strengthens geometry induction in the encoder. By masking both encoder and decoder tokens, and targeting decoder masks toward geometry-rich regions, the model is forced to infer structural information from incomplete visual cues, yielding geometry-aware representations even under unposed inputs. Second, we develop a coarse-to-fine Gaussian splatting strategy that reduces appearance-semantics inconsistencies by progressively refining the radiance field. Finally, to enforce geometric-semantic consistency, we introduce a pose-conditioned recalibration mechanism that interrelates the outputs of multiple heads by re-projecting predicted 3D point and semantic maps into the image plane using estimated camera parameters, and aligning them with corresponding RGB and semantic predictions to ensure cross-task consistency, thereby resolving geometry-semantic mismatches. Together, these components yield unified 3D representations that are robust to unposed, sparse-view inputs and generalize across diverse tasks, laying a perceptual foundation for spatial intelligence.

cs.CV↗
arXiv2026

Foundation Models Defining A New Era In Sensor-based Human Activity Recognition: A Survey And Outlook

Sensor-based Human Activity Recognition (HAR) underpins many ubiquitous and wearable computing applications, yet current models remain limited by scarce labels, sensor heterogeneity, and weak generalization across users, devices, and contexts. Foundation models, which are generally pretrained at scale using self-supervised and multimodal learning, offer a unifying paradigm to address these challenges by learning reusable, adaptable representations for activity understanding. This survey synthesizes emerging foundation models for sensor-based HAR. We first clarify foundational concepts, definitions, and evaluation criteria, then organize existing work using a lifecycle-oriented taxonomy spanning input design, pretraining, adaptation, and utilization. Rather than enumerating individual models, we analyze recurring design patterns and trade-offs across nine technical axes, including modality scope, tokenization, architectures, learning paradigms, adaptation mechanisms, and deployment settings. From this synthesis, we identify three dominant development trajectories: (1) HAR-specific foundation models trained from scratch on large sensor corpora, (2) adaptation of general time-series or multimodal foundation models to sensor-based HAR, and (3) integration of large language models for reasoning, annotation, and human-AI interaction. We conclude by highlighting open challenges in data curation, multimodal alignment, personalization, privacy, and responsible deployment, and outline directions toward general-purpose, interpretable, and human-centered foundation models for activity understanding. A complete, continuously updated index of papers and models is available in our companion repository: https://github.com/zhaxidele/Foundation-Models-Defining-A-New-Era-In-Human-Activity-Recognition.

eess.SP↗
arXiv2026

Accelerating Scientific Discovery with Autonomous Goal-evolving Agents

There has been unprecedented interest in developing agents that expand the boundary of scientific discovery, primarily by optimizing quantitative objective functions specified by scientists. However, for grand challenges in science, these objectives may only be imperfect proxies. We argue that automating objective function design is a central, yet unmet need for scientific discovery agents. In this work, we introduce the Scientific Autonomous Goal-evolving Agent (SAGA) to address this challenge. SAGA employs a bi-level architecture in which an outer loop of LLM agents analyzes optimization outcomes, proposes new objectives, and converts them into computable scoring functions, while an inner loop performs solution optimization under the current objectives. This bi-level design enables systematic exploration of the space of objectives and their trade-offs, rather than treating them as fixed inputs. We demonstrate the framework through a wide range of design applications, including antibiotics, nanobodies, functional DNA sequences, inorganic materials, and chemical processes. Notably, our experimental validation identifies a structurally novel hit with promising potency and safety profiles for E. coli in the antibiotic design task, and three de novo PD-L1 binders in the nanobody design task. These results suggest that automating objective formulation can substantially improve the effectiveness of scientific discovery agents.

cs.AI↗