arXiv subjects

Zhijie Zhang

Publications and source records attributed to Zhijie Zhang.

At least 19 recordsLinked to original sources

arXiv2026

Linear-Query Deterministic Approximation for Non-monotone Submodular Maximization under a Knapsack Constraint

Submodular maximization under a knapsack constraint (SMK) is a fundamental combinatorial optimization problem with broad applications across machine learning and data mining. Motivated by large-scale applications where query efficiency is paramount, we study non-monotone SMK and focus on deterministic algorithms with linear query complexity. Prior deterministic linear-query algorithms achieve at best a $1/5-\varepsilon$ approximation, falling short of the $1/4-\varepsilon$ ratio attainable by randomized algorithms. We close this gap by presenting a deterministic $(1/4-\varepsilon)$-approximation with $O(n\log^2(1/\varepsilon)/\varepsilon^2)$ queries. Our approach partitions the analysis based on the cost of the largest optimal element $r$: when the cost of $r$ is moderate, we refine the threshold-twin-greedy framework via residual-budget enumeration to tighten the analysis; when the cost of $r$ is large, we reduce the problem to bicriteria submodular maximization. As a secondary contribution, we obtain a $(1/2-\varepsilon, O(1/\varepsilon))$-bicriteria approximation with $O(n\log(1/\varepsilon)/\varepsilon^2)$ queries, improving over the previous $O(n^2/\varepsilon)$ query bound.

cs.DS↗

arXiv2026

Budget-Independent Influence Maximization in Nearly Linear Time

Influence maximization asks for $k$ seed vertices that maximize the expected spread of a diffusion process in a network. Standard near-optimal-time algorithms based on reverse-reachable sampling achieve a $(1-1/e-\varepsilon)$ approximation, but their worst-case running-time bounds grow linearly with the seed budget $k$. We remove this multiplicative dependence: for the independent cascade model, our algorithm succeeds with probability at least $1-δ$ in $O((m+n)\varepsilon^{-3}\log(2n/δ))$ expected time. The result extends to triggering models with explicitly charged local sampling costs. We reserve $O(\varepsilon k)$ seed positions for cost-weighted random vertices, allowing reverse-reachable searches to stop as soon as they encounter a reserved seed. An independent sample-count estimation phase uses a statistic that also controls the expected search cost. Matching these quantities eliminates the multiplicative dependence on $k$ while preserving the approximation guarantee.

cs.DS↗

arXiv2026

Bandit Submodular Maximization under Matroid Constraints: Learning Compressed Exchange Policy

We study adversarial bandit maximization of monotone submodular functions under a matroid constraint. For a rank-$k$ matroid on $n$ elements, we give a randomized oracle-polynomial algorithm that makes one feasible value query per round and has expected $(1-1/e)$-regret $\widetilde O(n^{1/3}k^{2/3}T^{2/3})$. This is the first sublinear-regret algorithm for adversarial bandit submodular maximization under general matroid constraints. Technically, we view the problem as learning an exchange policy for the Poisson base walk. This connects the problem to contextual bandits and gives an information-theoretic sublinear-regret guarantee, but directly learning the exponentially many policies requires exponential time and space. We therefore introduce \emph{balanced fractional exchanges}, which compress the policy mixture into a single fractional base while retaining the exchange information needed by the Poisson analysis. This leads to an polynomial time algorithm with the same regret guarantee.

cs.LG↗

arXiv2026

Urban Flood Observations: A hand-labeled training and validation dataset of post-flood inundation

Urban flooding affects lives and infrastructure worldwide. Mapping inundation in complex urban environments from satellite imagery remains challenging due to limited spatial resolution, infrequent acquisitions, and cloud cover. We present Urban Flood Observations (UFO), a global, hand-labeled dataset of post-flood inundation in diverse urban settings. UFO comprises 215 image chips (1024 by 1024 pixels) from 14 flood events between 2017 and 2021, derived from 3 m PlanetScope imagery. Each chip is annotated with two classes: 'inundated' (all visible surface water, including floodwater and pre-existing water bodies (permanent or seasonal)) and 'non-inundated'. To demonstrate the dataset's utility, we trained a segmentation model using leave-one-event-out cross-validation, achieving a mean Intersection over Union (IoU) of 77.3. We also used UFO to evaluate two widely used surface water products, the Sentinel-1-based NASA IMPACT model and Google's 10 m Dynamic World water class, which yielded IoUs of 44.1 and 48.1, respectively. UFO is publicly available to support the development and validation of urban inundation mapping methods.

cs.CV↗

arXiv2026

Dynamic Spectral Denoising with Global-Context Attention for Multi-Behavior Recommendation

Multi-behavior recommendation improves target-behavior prediction by exploiting heterogeneous auxiliary feedback (e.g., view, collect, and cart), yet its robustness is undermined by behavior-dependent noise and inconsistency. We argue that the key bottleneck is a representation-level failure caused by two coupled heterogeneities. First, intra-behavior representation entanglement arises when multi-hop propagation blends incidental signals with true preferences in the embedding space, making coarse spatial denoising unable to suppress noise without sacrificing informative niche signals. Second, inter-behavior reliability heterogeneity complicates cross-behavior fusion because the predictive value of auxiliary behaviors varies across users and contexts. Without reliability calibration, frequent yet unreliable signals may dominate aggregation and cause target-intent drift. To address this bottleneck, we propose Dynamic Spectral Denoising with Global-Context Attention for Multi-Behavior Recommendation (SpectraMB), a target-oriented model that performs representation purification before reliability-aware fusion. SpectraMB introduces Dynamic Feature-Level Spectral Filtering, which re-parameterizes embeddings along the feature dimension into a feature-frequency space and learns view-adaptive spectral modulation under target supervision, enabling component-wise purification without hand-crafted frequency assumptions. It further proposes Global-Context Attention Fusion, which uses a purified global representation as a context anchor to assess view compatibility and perform reliability-aware aggregation, while a residual global backbone preserves collaborative structure. Extensive experiments on three real-world datasets show that SpectraMB achieves the best results in most evaluation settings and exhibits improved robustness under noisy interactions.

cs.IR↗

arXiv2026

Probing the Hot Gaseous Halos of Milky Way-like Galaxies in the TNG50 simulation

The origin and structure of the hot ($T\gtrsim10^6$K) gaseous halo around Milky Way (MW)-mass galaxies provide a critical test for galaxy formation models. We perform a comprehensive comparison for a sample of MW analogues from the TNG50 cosmological simulation by generating synthetic soft X-ray emission and O VII/O VIII absorption lines, viewed from both internal (Solar) and external perspectives. The simulated halos successfully reproduce the observed global soft X-ray luminosity, inner-halo X-ray surface brightness, emission measure, and O VII absorption strength. However, two interconnected discrepancies are identified. First, the azimuthally averaged X-ray surface brightness profile from external viewpoints declines too steeply with radius compared to the extended emission detected in eROSITA stacking of SDSS galaxies, falling below the observations by up to $\sim 1$ dex at $R \gtrsim 100$ kpc. Second, the halos systematically underproduce O VIII absorption, with a median equivalent width $\sim 65\%$ lower than that observed in the Galactic halo, pointing to a deficit of hotter-phase gas at $T\sim(1.6-3.2)\times10^6$ K. These findings indicate that the simulated hot halos are too spatially compact and lack a hotter gas phase, suggesting that the TNG50 feedback model, while generating hot gas, deposits energy too centrally and too vigorously to sustain a gently extended, multi-phase corona.

astro-ph.GA↗

arXiv2026

Revisiting Fair and Efficient Allocations for Bivalued Goods

This paper re-examines the problem of fairly and efficiently allocating indivisible goods among agents with additive bivalued valuations. Garg and Murhekar (2021) proposed a polynomial-time algorithm that purported to find an EFX and fPO allocation. However, we provide a counterexample demonstrating that their algorithm may fail to terminate. To address this issue, we propose a new polynomial-time algorithm that computes a WEFX (Weighted Envy-Free up to any good) and fPO allocation, thereby correcting the prior approach and offering a more general solution. Furthermore, we show that our algorithm can be adapted to compute a WEQX (Weighted Equitable up to any good) and fPO allocation.

cs.GT↗

arXiv2026

Modeling Stage-wise Evolution of User Interests for News Recommendation

Personalized news recommendation is highly time-sensitive, as user interests are often driven by emerging events, trending topics, and shifting real-world contexts. These dynamics make it essential to model not only users' long-term preferences, which reflect stable reading habits and high-order collaborative patterns, but also their short-term, context-dependent interests that change rapidly over time. However, most existing approaches rely on a single static interaction graph, which struggles to capture both long-term preference patterns and short-term interest changes as user behavior evolves. To address this challenge, we propose a unified framework that learns user preferences from both global and local temporal perspectives. A global preference modeling component captures long-term collaborative signals from the overall interaction graph, while a local preference modeling component partitions historical interactions into stage-wise temporal subgraphs to represent short-term dynamics. Within this module, an LSTM branch models the progressive evolution of recent interests, and a self-attention branch captures long-range temporal dependencies. Extensive experiments on two large-scale real-world datasets show that our approach consistently outperforms strong baselines and delivers fresher and more relevant recommendations across diverse user behaviors and temporal settings.

cs.IR↗

arXiv2026

RMBRec: Robust Multi-Behavior Recommendation towards Target Behaviors

Multi-behavior recommendation faces a critical challenge in practice: auxiliary behaviors (e.g., clicks, carts) are often noisy, weakly correlated, or semantically misaligned with the target behavior (e.g., purchase), which leads to biased preference learning and suboptimal performance. While existing methods attempt to fuse these heterogeneous signals, they inherently lack a principled mechanism to ensure robustness against such behavioral inconsistency. In this work, we propose Robust Multi-Behavior Recommendation towards Target Behaviors (RMBRec), a robust multi-behavior recommendation framework grounded in an information-theoretic robustness principle. We interpret robustness as a joint process of maximizing predictive information while minimizing its variance across heterogeneous behavioral environments. Under this perspective, the Representation Robustness Module (RRM) enhances local semantic consistency by maximizing the mutual information between users' auxiliary and target representations, whereas the Optimization Robustness Module (ORM) enforces global stability by minimizing the variance of predictive risks across behaviors, which is an efficient approximation to invariant risk minimization. This local-global collaboration bridges representation purification and optimization invariance in a theoretically coherent way. Extensive experiments on three real-world datasets demonstrate that RMBRec not only outperforms state-of-the-art methods in accuracy but also maintains remarkable stability under various noise perturbations. For reproducibility, our code is available at https://github.com/miaomiao-cai2/RMBRec/.

cs.IR↗

arXiv2025

Learning Disentangled Speech- and Expression-Driven Blendshapes for 3D Talking Face Animation

Expressions are fundamental to conveying human emotions. With the rapid advancement of AI-generated content (AIGC), realistic and expressive 3D facial animation has become increasingly crucial. Despite recent progress in speech-driven lip-sync for talking-face animation, generating emotionally expressive talking faces remains underexplored. A major obstacle is the scarcity of real emotional 3D talking-face datasets due to the high cost of data capture. To address this, we model facial animation driven by both speech and emotion as a linear additive problem. Leveraging a 3D talking-face dataset with neutral expressions (VOCAset) and a dataset of 3D expression sequences (Florence4D), we jointly learn a set of blendshapes driven by speech and emotion. We introduce a sparsity constraint loss to encourage disentanglement between the two types of blendshapes while allowing the model to capture inherent secondary cross-domain deformations present in the training data. The learned blendshapes can be further mapped to the expression and jaw pose parameters of the FLAME model, enabling the animation of 3D Gaussian avatars. Qualitative and quantitative experiments demonstrate that our method naturally generates talking faces with specified expressions while maintaining accurate lip synchronization. Perceptual studies further show that our approach achieves superior emotional expressivity compared to existing methods, without compromising lip-sync quality.

cs.CV↗

arXiv2025

Document Intelligence in the Era of Large Language Models: A Survey

Document AI (DAI) has emerged as a vital application area, and is significantly transformed by the advent of large language models (LLMs). While earlier approaches relied on encoder-decoder architectures, decoder-only LLMs have revolutionized DAI, bringing remarkable advancements in understanding and generation. This survey provides a comprehensive overview of DAI's evolution, highlighting current research attempts and future prospects of LLMs in this field. We explore key advancements and challenges in multimodal, multilingual, and retrieval-augmented DAI, while also suggesting future research directions, including agent-based approaches and document-specific foundation models. This paper aims to provide a structured analysis of the state-of-the-art in DAI and its implications for both academic and practical applications.

cs.CL↗

arXiv2025

LangGrasp: Leveraging Fine-Tuned LLMs for Language Interactive Robot Grasping with Ambiguous Instructions

The existing language-driven grasping methods struggle to fully handle ambiguous instructions containing implicit intents. To tackle this challenge, we propose LangGrasp, a novel language-interactive robotic grasping framework. The framework integrates fine-tuned large language models (LLMs) to leverage their robust commonsense understanding and environmental perception capabilities, thereby deducing implicit intents from linguistic instructions and clarifying task requirements along with target manipulation objects. Furthermore, our designed point cloud localization module, guided by 2D part segmentation, enables partial point cloud localization in scenes, thereby extending grasping operations from coarse-grained object-level to fine-grained part-level manipulation. Experimental results show that the LangGrasp framework accurately resolves implicit intents in ambiguous instructions, identifying critical operations and target information that are unstated yet essential for task completion. Additionally, it dynamically selects optimal grasping poses by integrating environmental information. This enables high-precision grasping from object-level to part-level manipulation, significantly enhancing the adaptability and task execution efficiency of robots in unstructured environments. More information and code are available here: https://github.com/wu467/LangGrasp.

cs.RO↗

arXiv2025

Tracing the Origins of Hot Halo Gas in Milky Way-Type Galaxies with SMUGGLE

Current galaxy formation models predict the existence of X-ray-emitting gaseous halos around Milky Way (MW)-type galaxies. To investigate properties of this coronal gas in MW-like galaxies, we analyze a suite of high-resolution simulations based on the SMUGGLE framework and compare the results with X-ray observations of both the MW and external galaxies. We find that for subgrid models incorporating any form of stellar feedback, e.g., early feedback (including stellar winds and radiation) and/or supernova (SN) explosions, the total 0.5-2 keV luminosity is consistent within uncertainties with X-ray observations of the MW and with scaling relations derived for external disk galaxies. However, all models exhibit an X-ray surface brightness profile that declines too steeply beyond $\sim5$ kpc, underpredicting the extended emission seen in recent eROSITA stacking results. Across all subgrid prescriptions, the simulated surface brightness and emission measure fall below MW observations by at least 1-2 orders of magnitude, with the most severe discrepancy occurring in the no-feedback model. Our results suggest that (i) stellar feedback primarily shapes the innermost hot atmosphere (central $\sim5$ kpc), with comparable contributions from early feedback and SNe to the resulting X-ray luminosity; (ii) additional mechanisms such as gravitational heating, active galactic nuclei feedback, and/or Compton effects of GeV cosmic ray are necessary to generate the extended, volume-filling hot gaseous halo of MW-mass galaxies; (iii) the origins of hot corona in MW-like galaxies are partially distinct from those of the warm ($\sim10^5$ K) gas, by combining our previous finding that the SMUGGLE model successfully reproduces the kinematics and spatial distribution of MW O VI absorbers.

astro-ph.GA↗

arXiv2025

ALWNN Empowered Automatic Modulation Classification: Conquering Complexity and Scarce Sample Conditions

In Automatic Modulation Classification (AMC), deep learning methods have shown remarkable performance, offering significant advantages over traditional approaches and demonstrating their vast potential. Nevertheless, notable drawbacks, particularly in their high demands for storage, computational resources, and large-scale labeled data, which limit their practical application in real-world scenarios. To tackle this issue, this paper innovatively proposes an automatic modulation classification model based on the Adaptive Lightweight Wavelet Neural Network (ALWNN) and the few-shot framework (MALWNN). The ALWNN model, by integrating the adaptive wavelet neural network and depth separable convolution, reduces the number of model parameters and computational complexity. The MALWNN framework, using ALWNN as an encoder and incorporating prototype network technology, decreases the model's dependence on the quantity of samples. Simulation results indicate that this model performs remarkably well on mainstream datasets. Moreover, in terms of Floating Point Operations Per Second (FLOPS) and Normalized Multiply - Accumulate Complexity (NMACC), ALWNN significantly reduces computational complexity compared to existing methods. This is further validated by real-world system tests on USRP and Raspberry Pi platforms. Experiments with MALWNN show its superior performance in few-shot learning scenarios compared to other algorithms.

cs.LG↗

arXiv2025

Pseudocode-Injection Magic: Enabling LLMs to Tackle Graph Computational Tasks

Graph computational tasks are inherently challenging and often demand the development of advanced algorithms for effective solutions. With the emergence of large language models (LLMs), researchers have begun investigating their potential to address these tasks. However, existing approaches are constrained by LLMs' limited capability to comprehend complex graph structures and their high inference costs, rendering them impractical for handling large-scale graphs. Inspired by human approaches to graph problems, we introduce a novel framework, PIE (Pseudocode-Injection-Enhanced LLM Reasoning for Graph Computational Tasks), which consists of three key steps: problem understanding, prompt design, and code generation. In this framework, LLMs are tasked with understanding the problem and extracting relevant information to generate correct code. The responsibility for analyzing the graph structure and executing the code is delegated to the interpreter. We inject task-related pseudocodes into the prompts to further assist the LLMs in generating efficient code. We also employ cost-effective trial-and-error techniques to ensure that the LLM-generated code executes correctly. Unlike other methods that require invoking LLMs for each individual test case, PIE only calls the LLM during the code generation phase, allowing the generated code to be reused and significantly reducing inference costs. Extensive experiments demonstrate that PIE outperforms existing baselines in terms of both accuracy and computational efficiency.

cs.CL↗

arXiv2024

Efficient Deterministic Algorithms for Maximizing Symmetric Submodular Functions

Symmetric submodular maximization is an important class of combinatorial optimization problems, including MAX-CUT on graphs and hyper-graphs. The state-of-the-art algorithm for the problem over general constraints has an approximation ratio of $0.432$. The algorithm applies the canonical continuous greedy technique that involves a sampling process. It, therefore, suffers from high query complexity and is inherently randomized. In this paper, we present several efficient deterministic algorithms for maximizing a symmetric submodular function under various constraints. Specifically, for the cardinality constraint, we design a deterministic algorithm that attains a $0.432$ ratio and uses $O(kn)$ queries. Previously, the best deterministic algorithm attains a $0.385-ε$ ratio and uses $O\left(kn (\frac{10}{9ε})^{\frac{20}{9ε}-1}\right)$ queries. For the matroid constraint, we design a deterministic algorithm that attains a $1/3-ε$ ratio and uses $O(kn\log ε^{-1})$ queries. Previously, the best deterministic algorithm can also attain $1/3-ε$ ratio but it uses much larger $O(ε^{-1}n^4)$ queries. For the packing constraints with a large width, we design a deterministic algorithm that attains a $0.432-ε$ ratio and uses $O(n^2)$ queries. To the best of our knowledge, there is no deterministic algorithm for the constraint previously. The last algorithm can be adapted to attain a $0.432$ ratio for single knapsack constraint using $O(n^4)$ queries. Previously, the best deterministic algorithm attains a $0.316-ε$ ratio and uses $\widetilde{O}(n^3)$ queries.

cs.DS↗

arXiv2024

A Correction of Pseudo Log-Likelihood Method

Pseudo log-likelihood is a type of maximum likelihood estimation (MLE) method used in various fields including contextual bandits, influence maximization of social networks, and causal bandits. However, in previous literature \citep{li2017provably, zhang2022online, xiong2022combinatorial, feng2023combinatorial1, feng2023combinatorial2}, the log-likelihood function may not be bounded, which may result in the algorithm they proposed not well-defined. In this paper, we give a counterexample that the maximum pseudo log-likelihood estimation fails and then provide a solution to correct the algorithms in \citep{li2017provably, zhang2022online, xiong2022combinatorial, feng2023combinatorial1, feng2023combinatorial2}.

cs.LG↗

arXiv2023

Low- and High-velocity \ion{O}{6} in Milky Way-like Galaxies: the Role of Stellar Feedback

Milky Way-type galaxies are surrounded by a warm-hot gaseous halo containing a considerable amount of baryons and metals. The kinematics and spatial distribution of highly-ionized ion species such as \ion{O}{6} can be significantly affected by supernova (SN) explosions and early (pre-SN) stellar feedback (e.g., stellar winds, radiation pressure). Here, we investigate effects of stellar feedback on \ion{O}{6} absorptions in Milky Way-like galaxies by analyzing the suites of high-resolution hydrodynamical simulations under the framework of {\it SMUGGLE}, a physically motivated subgrid interstellar medium and stellar feedback model for the moving-mesh code {\sc Arepo}. We find that the fiducial run with the full suite of stellar feedback and moderate star formation activities can reasonably reproduce Galactic \ion{O}{6} absorptions observed by space telescopes such as {\it FUSE}, including the scale height of low-velocity ($|v_{\rm LSR}|< 100\, \rm km~s^{-1}$) \ion{O}{6}, the column density $-$ line width relation for high-velocity ($100 \leq |v_{\rm LSR}|< 400\, \rm km~s^{-1}$) \ion{O}{6}, and the cumulative \ion{O}{6} column densities. In contrast, model variations with more intense star formation activities deviate from observations further. Additionally, we find that the run considering only SN feedback is in broad agreement with the observations, whereas in runs without SN feedback this agreement is absent, which indicates a dominant role of SN feedback in heating and accelerating interstellar \ion{O}{6}. This is consistent with the current picture that interstellar \ion{O}{6} is predominantly produced by collisional ionization where mechanical feedback can play a central role. In contrast, photoionization is negligible for \ion{O}{6} production due to the lack of high-energy ($\gtrsim114\ {\rm eV}$) photons required.

astro-ph.GA↗