Searcharxiv⌕ Search

arXiv subjects

Wenjuan Li

Publications and source records attributed to Wenjuan Li.

At least 19 recordsLinked to original sources

$L^p(\mathbb{R}^3)$-estimates for maximal averages along mixed homogeneous hypersurfaces with vanishing Hessian

We study maximal averages over the surfaces parametrized by $c+Φ$ in $\mathbb{R}^3$, where $c$ is a constant and $Φ$ is mixed homogeneous and real analytic away from the origin. Under the assumption that the Hessian determinant of $Φ$ vanishes identically, we classify the possible graphing functions for all positive weights. For surfaces in each resulting class, we establish sharp $L^{p}$-estimates for the corresponding maximal averages.

math.CA↗

Endpoint weighted Fourier estimate with vanishing spherical trace

We establish an endpoint weighted Fourier estimate under a vanishing restriction condition on the unit sphere. Let $n \geq 2$ and $p_c = 2(n+1)/(n+3)$. We prove that every $f \in L^{p_c}(\mathbb{R}^n)$ with zero spherical Fourier restriction satisfies $$ \left\| \bigl|1-|ξ|^2\bigr|^{-1/2}\widehat{f}(ξ) \right\|_{L^2(\mathbb{R}^n)} \leq C_n \|f\|_{L^{p_c}(\mathbb{R}^n)}, $$ where the restriction condition is understood through the continuous Tomas--Stein restriction operator. This result gives a negative answer to Goldberg's counterexample-existence question and supplies a missing endpoint.

math.CA↗

Stability of Fourier Restriction for a Class of Finite Type Surfaces in $\mathbb R^3$

We establish the stability of the optimal non-endpoint Fourier restriction range under smooth flat perturbations of curved-root surfaces in $\mathbb R^3$. Specifically, we consider graphs of $$ϕ(x_1,x_2)=(x_2-x_1^m)^n+R(x_1,x_2),$$ where $m,n\ge2$ are integers and $R$ is smooth and flat at the origin. On a sufficiently small neighborhood depending on the perturbation, we prove the local $L^p(\mathbb R^3)\to L^2(S,dσ)$ restriction estimate for $1\le p p_c$. Thus arbitrary smooth flat perturbations preserve the optimal restriction range away from the critical endpoint. For $n\ge3$, the main local estimate combines planar curve decoupling with a one-dimensional finite-type extension estimate, whose principal scale factors cancel exactly. For $n=2$, we prove a uniform $C^4$ perturbation estimate using a weighted convolution bound and an anisotropic Whitney decomposition. Anisotropic rescaling and summation complete the proof.

math.CA↗

Endpoint maximal estimates for the half-wave propagator

We present a proof of the strong maximal estimate for the Euclidean half-wave propagator at the critical pair $s_d=d/(d+1)$ and $q_d=2(d+1)/(d-1)$, in every dimension $d\ge2$, i.e. \begin{equation*} \biggl\|\sup_{0<t<1}|e^{it\sqrt{-Δ}}f(x)|\biggl\|_{L^{q_d}({\mathbb{R}}^d)} \le C_d\|f\|_{ H^{s_d}({\mathbb{R}}^d)}. \end{equation*}

math.CA↗

Event-Centric Memory with Query-Aware Graph Augmentation for Long-Term Conversational Agents

For persistent and personalized conversational agents, memory systems can enable them to remember, update, and reason over long histories by storing past interactions and retrieving relevant information. Existing memory systems typically follow two paradigms: flat-structured memory and graph-based memory. The former is lightweight but leaves event relations and state updates implicit, while the latter explicitly models memory structure but incurs additional construction cost and introduces irrelevant relations over long histories. To address these limitations, we propose QGMem, a novel memory construction and activation framework motivated by human memory, in which experience is organized into events and query-relevant events are modeled by graph as working memory. QGMem converts long dialogue histories into event-indexed atomic memory units that preserve individual experiences and consolidates related units into dynamic memory traces that retain state trajectories and current states. When a query arrives, hybrid memory retrieval gathers complementary candidate memories, and query-aware reranking activates the most relevant units as a compact working memory. To expose relational dependencies in the working memory and support conflict-aware reasoning, QGMem organizes the working memory as a local graph, which is then encoded as a graph token and provided to the LLM together with the textual working memory to improve evidence utilization during answer generation. Experiments across six benchmarks validate the framework and show consistent gains in retrieval, multi-hop evidence composition, conflict resolution, and ultra-long dialogue reasoning with compact contexts and moderate inference cost.

cs.CL↗

Schema-Anchored Latent Reasoning for Semantic Parsing-Based Knowledge Base Question Answering

Semantic parsing (SP)-based knowledge base question answering aims to answer natural language questions by generating executable logical forms (LFs) over knowledge bases (KBs). When applying Large Language Models (LLMs) to this task, a key challenge over large, heterogeneous KBs is selecting question-related schema elements (i.e., relations and classes) and composing them into complex LFs. Recent LLM-based methods often make early discrete commitments to schema elements during intermediate reasoning, allowing incorrect intermediate schema decisions to propagate and finally result in incorrect LFs. To overcome this limitation, we propose SALR, a schema-anchored latent reasoning method for LF construction. It performs multi-step reasoning by generating continuous thoughts in the model's hidden states, thereby delaying the explicit commitment to LF decisions. To ground this latent reasoning process in the corresponding KB schema, SALR aligns continuous thoughts with a codebook of KB schema elements through an alignment objective supervised by schema traces deterministically derived from gold LFs. It then incorporates the aligned schema codes into inputs for subsequent reasoning steps. This schema-mediated feedback guides LF generation without requiring the model to emit an explicit textual reasoning trajectory. Experiments on GrailQA and WebQSP show that SALR achieves consistent overall gains over strong baselines. Notably, on compositional questions from GrailQA, SALR outperforms TIARA, a strong SP-based baseline, by 2.86 F1 points. Further analyses show that schema-mediated feedback affects LF generation and that schema information is recoverable from the latent states.

cs.CL↗

$L^p$-Estimates for maximal averages along mixed homogeneous hypersurfaces in $\mathbb{R}^{3}$

In this paper, we study $L^p$-estimates for maximal averaging operators $\mathcal M$ along hypersurfaces $S$ in $\mathbb{R}^{3}$ which are the graph of a mixed homogeneous function $Φ$ which is analytic away from the origin. The closure of such a surface will pass through the origin, so that the usual transversality condition that had been imposed in many previous works on maximal averages along hypersurfaces will not hold even when $Φ$ is analytic at the origin. As our main result, under mild assumptions which are satisfied for instance for every mixed homogeneous polynomial $Φ,$ we determine the critical Lebesgue exponent $p_c$ for which $\mathcal M$ is $L^p$-bounded for every $p>p_c,$ but unbounded for $p<p_c,$ in terms of multiplicities of the real roots of the Hessian determinant of $Φ.$ It turns out that the study of the contributions by neighborhoods of a certain type of roots is closely related to recent work by Dendrinos, Ikromov and the first and third author on sharp estimates for a maximal averaging operator along a transversal hypersurface of an ``exceptional'' class, whose $L^p$-boundedness had been an open problem for a long time and which has recently been established by means of their new theory of FIO-cone multipliers.

math.CA↗

A Study on Kakeya Needle Problem for $(n-1)$-Rectifiable Sets

In this article we study the analog of Kakeya needle problem for $(n-1)$-rectifiable sets in $\mathbb{R}^n$ and construct the related Nikodym type sets. The novelty of our approach lies in combining three ingredients: the two-dimensional Venetian blind-type construction for isometries in $\mathbb{R}^n$; the normal geometry of a $(n-1)$-rectifiable set viewed in the projective setting; and measure estimates of moving $(n-1)$-rectifiable sets by isometries in $\mathbb{R}^n$. Together, these ingredients enable us to move $(n-1)$-rectifiable sets along paths of isometries in $\mathbb{R}^n$ and cover a Lebesgue null set.

math.CA↗

Security in the Fine-Tuning Lifecycle of Large Language Models: Threats, Defenses,Evaluation, and Future Directions

Background: Fine-tuning is central to adapting pre-trained Large Language Models (LLMs) to downstream tasks, but its reliance on training data, parameter updates, and reusable components opens entry points for attackers. Threats have evolved from data poisoning and weight tampering to agent manipulation and interface exploitation, yet existing reviews lack a unified framework spanning the full fine-tuning lifecycle. Objective: This paper presents a systematic survey of LLM fine-tuning security and establishes a lifecycle-based framework for comparing attacks and defenses, complemented by unified empirical evaluation. Methods: We divide attack and defense mechanisms into three phases by intervention timing: pre-tuning, during-tuning, and post-tuning. Within each phase, strategies are reviewed and contrasted to expose their evolution and limitations. Representative methods are then evaluated under a unified model, hardware, and protocol setup, with cross-phase experiments pairing attacks and defenses from different phases. Results: Attack effectiveness is highly model-dependent and non-monotonic with scale: weight-editing attacks effective on earlier models lose impact on modern open-source LLMs; cross-lingual backdoor transfer, reported as near-perfect at larger scales, fails entirely on tested 1B-4B models; and purely benign samples can compromise safety alignment in instruction-tuned models. Single-phase defenses rarely generalize across phases, and defense effectiveness depends jointly on model architecture and alignment state. Conclusion: We identify key open problems (configuration-robust defense, cross-phase defense composition, and embedding-space attacks beyond behavioral assumptions) and propose concrete future research directions.

cs.CR↗

Maximal functions related to homogeneous hypersurfaces in $\mathbb{R}^3$

We study maximal functions related to homogeneous polynomial hypersurfaces in $\mathbb{R}^3$. In a sense made precise in this paper, the region of $(p,q)$ for which we obtain $L^p\rightarrow L^q$ boundedness is optimal up to the endpoints for the corresponding local maximal operators. The boundedness exponents depend explicitly on both the height of the hypersurface and the type of the curve determined by the level set. As a corollary, we obtain $L^p$-estimates and weighted norm inequalities for the associated global maximal functions. Moreover, we also obtain optimal $L^{p}$-estimates for the global maximal operators associated with homogeneous polynomial hypersurfaces without transversality condition in $\mathbb{R}^{3}$.

math.CA↗

Stabilizing correlated pair tunneling of spin-orbit-coupled bosons in a non-Hermitian driven double well

We present an analytical framework for stabilizing second-order correlated tunneling of two spin-orbit-coupled bosons in a periodically driven non-Hermitian double-well potential. By combining Floquet theory with multiple-scale asymptotic analysis, we derive effective second-order dynamics and exact quasienergy spectra in the strongly interacting regime. Our analysis reveals distinct stability mechanisms for three fundamental tunneling channels: interwell spin-conserving, interwell spin-flipping, and intrawell spin-flipping. For balanced gain and loss, we identify discrete, well-defined parameter regions where stable pair tunneling emerges, with the spin-flipping channel exhibiting a characteristic symmetry absent in its spin-conserving counterpart. Under unbalanced gain-loss conditions, stability is achieved only when the gain and loss coefficients satisfy specific parametric relations, enabling dissipation-controlled tunneling. Most notably, stable intrawell spin-flipping, while inherently unstable for an initial Fock state, becomes accessible when the system is prepared in a coherent superposition state, thereby revealing that initial-state coherence can serve as a control parameter for dynamical stability in non-Hermitian systems. These results expand the possibilities for controlling correlated tunneling in many-body systems with engineered dissipation.

quant-ph↗

Endpoint estimates for maximal operators associated to the wave equation

We consider the $H^{s}$--$L^q$ maximal estimates associated to the wave operator \begin{equation*} e^{ it\sqrt{-Δ}}f(x) = \frac{1}{(2π)^d}\int_{\mathbb{R}^d} e^{i(x \cdot ξ\, + t|ξ|)} \widehat{f}(ξ\,) dξ. \end{equation*} Rogers--Villarroya proved $H^{s}$--$L^q$ estimates for the maximal operator $f\mapsto$ $\sup_{t} |e^{ it\sqrt{-Δ}}f|$ up to the critical Sobolev exponents $s_c(q,d)$. However, the endpoint case estimates for the critical exponent $s=s_c(q,d)$ have remained open so far. We obtain the endpoint $H^{s_c(q,d)}$--$L^q$ bounds on the maximal operator $f\mapsto \sup_{t} |e^{ it\sqrt{-Δ}}f|$. We also prove that several different forms of the maximal estimates considered by Rogers--Villarroya are basically equivalent to each other.

math.CA↗

FoMo4Wheat: Toward reliable crop vision foundation models with globally curated data

Vision-driven field monitoring is central to digital agriculture, yet models built on general-domain pretrained backbones often fail to generalize across tasks, owing to the interaction of fine, variable canopy structures with fluctuating field conditions. We present FoMo4Wheat, one of the first crop-domain vision foundation model pretrained with self-supervision on ImAg4Wheat, the largest and most diverse wheat image dataset to date (2.5 million high-resolution images collected over a decade at 30 global sites, spanning >2,000 genotypes and >500 environmental conditions). This wheat-specific pretraining yields representations that are robust for wheat and transferable to other crops and weeds. Across ten in-field vision tasks at canopy and organ levels, FoMo4Wheat models consistently outperform state-of-the-art models pretrained on general-domain dataset. These results demonstrate the value of crop-specific foundation models for reliable in-field perception and chart a path toward a universal crop foundation model with cross-species and cross-task capabilities. FoMo4Wheat models and the ImAg4Wheat dataset are publicly available online: https://github.com/PheniX-Lab/FoMo4Wheat and https://huggingface.co/PheniX-Lab/FoMo4Wheat. The demonstration website is: https://fomo4wheat.phenix-lab.com/.

cs.CV↗

Stability of spin dynamics for a spin-orbit coupled boson in a driven non-Hermitian double well

We study the stability of spin dynamics for a spin-orbit (SO) coupled boson held in a driven non-Hermitian double-well potential. Under high-frequency approximation, we analytically derive the Floquet states and complex Floquet quasienergies of the system and reveal a striking parity-dependent stability criterion: when the ratio of the Zeeman field strength to the driving frequency $Ω/ω$ is even, stable spin dynamics can be achieved for \emph{arbitrary} SO coupling strength. However, when $Ω/ω$ is odd, stability requires the SO coupling strength to be integer or half-integer values. Particularly, we find four types of stability boundary lines for non-zero bias field strength, in sharp contrast to the commonly observed stability regions. These results establish a tunable parity-governed mechanism for stabilizing spin dynamics in non-Hermitian cold atomic systems.

cond-mat.quant-gas↗

Integer Binary-Range Alignment Neuron for Spiking Neural Networks

Spiking Neural Networks (SNNs) are noted for their brain-like computation and energy efficiency, but their performance lags behind Artificial Neural Networks (ANNs) in tasks like image classification and object detection due to the limited representational capacity. To address this, we propose a novel spiking neuron, Integer Binary-Range Alignment Leaky Integrate-and-Fire to exponentially expand the information expression capacity of spiking neurons with only a slight energy increase. This is achieved through Integer Binary Leaky Integrate-and-Fire and range alignment strategy. The Integer Binary Leaky Integrate-and-Fire allows integer value activation during training and maintains spike-driven dynamics with binary conversion expands virtual timesteps during inference. The range alignment strategy is designed to solve the spike activation limitation problem where neurons fail to activate high integer values. Experiments show our method outperforms previous SNNs, achieving 74.19% accuracy on ImageNet and 66.2% mAP@50 and 49.1% mAP@50:95 on COCO, surpassing previous bests with the same architecture by +3.45% and +1.6% and +1.8%, respectively. Notably, our SNNs match or exceed ANNs' performance with the same architecture, and the energy efficiency is improved by 6.3${\times}$.

cs.NE↗

Global Rice Multi-Class Segmentation Dataset (RiceSEG): A Comprehensive and Diverse High-Resolution RGB-Annotated Images for the Development and Benchmarking of Rice Segmentation Algorithms

Developing computer vision-based rice phenotyping techniques is crucial for precision field management and accelerating breeding, thereby continuously advancing rice production. Among phenotyping tasks, distinguishing image components is a key prerequisite for characterizing plant growth and development at the organ scale, enabling deeper insights into eco-physiological processes. However, due to the fine structure of rice organs and complex illumination within the canopy, this task remains highly challenging, underscoring the need for a high-quality training dataset. Such datasets are scarce, both due to a lack of large, representative collections of rice field images and the time-intensive nature of annotation. To address this gap, we established the first comprehensive multi-class rice semantic segmentation dataset, RiceSEG. We gathered nearly 50,000 high-resolution, ground-based images from five major rice-growing countries (China, Japan, India, the Philippines, and Tanzania), encompassing over 6,000 genotypes across all growth stages. From these original images, 3,078 representative samples were selected and annotated with six classes (background, green vegetation, senescent vegetation, panicle, weeds, and duckweed) to form the RiceSEG dataset. Notably, the sub-dataset from China spans all major genotypes and rice-growing environments from the northeast to the south. Both state-of-the-art convolutional neural networks and transformer-based semantic segmentation models were used as baselines. While these models perform reasonably well in segmenting background and green vegetation, they face difficulties during the reproductive stage, when canopy structures are more complex and multiple classes are involved. These findings highlight the importance of our dataset for developing specialized segmentation models for rice and other crops.

eess.IV↗

A General Neural Network Potential for Energetic Materials with C, H, N, and O elements

The discovery and optimization of high-energy materials (HEMs) are constrained by the prohibitive computational expense and prolonged development cycles inherent in conventional approaches. In this work, we develop a general neural network potential (NNP) that efficiently predicts the structural, mechanical, and decomposition properties of HEMs composed of C, H, N, and O. Our framework leverages pre-trained NNP models, fine-tuned using transfer learning on energy and force data derived from density functional theory (DFT) calculations. This strategy enables rapid adaptation across 20 different HEM systems while maintaining DFT-level accuracy, significantly reducing computational costs. A key aspect of this work is the ability of NNP model to capture the chemical activity space of HEMs, accurately describe the key atomic interactions and reaction mechanisms during thermal decomposition. The general NNP model has been applied in molecular dynamics (MD) simulations and validated with experimental data for various HEM structures. Results show that the NNP model accurately predicts the structural, mechanical, and decomposition properties of HEMs by effectively describing their chemical activity space. Compared to traditional force fields, it offers superior DFT-level accuracy and generalization across both microscopic and macroscopic properties, reducing the computational and experimental costs. This work provides an efficient strategy for the design and development of HEMs and proposes a promising framework for integrating DFT, machine learning, and experimental methods in materials research. (To facilitate further research and practical applications, we open-source our NNP model on GitHub: https://github.com/MingjieWen/General-NNP-model-for-C-H-N-O-Energetic-Materials.)

cond-mat.mtrl-sci↗

NFT1000: A Cross-Modal Dataset for Non-Fungible Token Retrieval

With the rise of "Metaverse" and "Web 3.0", Non-Fungible Token (NFT) has emerged as a kind of pivotal digital asset, garnering significant attention. By the end of March 2024, more than 1.7 billion NFTs have been minted across various blockchain platforms. To effectively locate a desired NFT, conducting searches within a vast array of NFTs is essential. The challenge in NFT retrieval is heightened due to the high degree of similarity among different NFTs, regarding regional and semantic aspects. In this paper, we will introduce a benchmark dataset named "NFT Top1000 Visual-Text Dataset" (NFT1000), containing 7.56 million image-text pairs, and being collected from 1000 most famous PFP1 NFT collections2 by sales volume on the Ethereum blockchain. Based on this dataset and leveraging the CLIP series of pre-trained models as our foundation, we propose the dynamic masking fine-tuning scheme. This innovative approach results in a 7.4\% improvement in the top1 accuracy rate, while utilizing merely 13\% of the total training data (0.79 million vs. 6.1 million). We also propose a robust metric Comprehensive Variance Index (CVI) to assess the similarity and retrieval difficulty of visual-text pairs data. The dataset will be released as an open-source resource. For more details, please refer to: https://github.com/ShuxunoO/NFT-Net.git.

cs.IR↗