Searcharxiv⌕ Search

arXiv subjects

Di Wu

Publications and source records attributed to Di Wu.

At least 91 records · Page 5Linked to original sources
arXiv2026

Implicit Fine-tuning via Context Engineering: A Curriculum Learning Framework for Multimodal Entity Alignment

Multimodal Entity Alignment (MMEA) aims to identify equivalent entities across different modalities. While existing methods enhance MMEA performance through black-box context engineering strategies, their reliance on LLM parameter capacity and lack of theoretical interpretability remain unresolved. To this end, we first theoretically validate the mathematical equivalence between context engineering and model fine-tuning in MMEA tasks, demonstrating that prompt components simulate contrastive learning-based sequential fine-tuning in MMEA. Building on this foundation, we then propose PTFEA, a curriculum-learning-inspired framework that translates fine-tuning strategies into interpretable context engineering. Specifically, adaptive difficulty modulation dynamically adjusts information injection stages using confidence thresholds, establishing mathematical equivalence between curriculum learning weights and context sample selection; and three-stage progressive inference incorporates entity information from simple to complex cases, mirroring the gradient descent process in fine-tuning. Experiments on five public datasets demonstrate that PTFEA consistently outperforms strong baselines. In particular, on the ICWIKI dataset, PTFEA narrows the H@1 gap between Qwen2.5-72B and 14B to 0.6%. Moreover, compared with the representative context-engineering-based MMEA method MM-ChatAlign, PTFEA reduces the runtime of Qwen2.5-72B from 21 hours to 1 hour and lowers token consumption from 2200-3000 to 200-400, achieving over 80% reduction on the ICWIKI dataset. This work provides the first theoretical framework unifying context engineering and fine-tuning in MMEA, paving the way for future research that seeks to translate additional fine-tuning strategies into context engineering paradigms. Our code is available at https://github.com/DMiC-Lab-HFUT/PTFEA.

cs.IR↗
arXiv2026

Study of exotic hadron states in the $DD^{*}$ system via the complex momentum representation and Green's function method

In this paper, we propose a novel approach to investigate exotic hadronic states. For the $DD^{*}$ system, we employ the projection operator method to derive the momentum-space interaction potential. Subsequently, the complex momentum representation (CMR) method is adopted to realize a unified description of bound states, resonant states, and the continuum. By combining the Green's function and the CMR, the scattering phase shifts and cross sections are determined. This integrated approach provides a comprehensive framework for analyzing the scattering dynamics of the $DD^{*}$ system. In the hadronic molecular state framework, the $X(3872)$, $T_{cc}^+$, and $Z_c(3900)$ states can be consistently explained as bound states, while the $G(3900)$ can be interpreted as a $P$-wave resonant state. The decomposition of the scattering phase shifts and cross sections facilitates understanding the roles of resonant and continuum spectrum.

hep-ph↗
arXiv2026

TacReasoner: A Dynamic Tactile-Language Framework for Interactive Reasoning in Real-World Scenarios

Among the five primary human senses, tactile is arguably the most fundamental to survival, as it enables the perception of physical contact and interaction in real-world environments. In this paper, we explore two key challenges of integrating tactile sensing into intelligent systems for multimodal reasoning: (i) insufficient modeling of dynamic tactile signals, which restricts reasoning over temporally evolving properties, and (ii) hallucination in tactile foundation models caused by the absence of explicit reasoning mechanisms, leading to unstable real-world inference. To address these challenges, we propose TacReasoner, a dynamic tactile-language framework for interactive reasoning in real-world scenarios. First, TacReasoner incorporates a Dynamic-aware Tactile Encoder to enhance the perception and representation of dynamic tactile signals. More importantly, we introduce TouchCoT-10k, the first tactile chain-of-thought dataset for structured reasoning over tactile inputs. Upon it, we establish DynTac-Bench to systematically evaluate dynamic tactile perception and real-world commonsense reasoning. Experimental results demonstrate that TacReasoner achieves competitive performance against state-of-the-art models across multiple datasets. Notably, despite using only 7B parameters, TacReasoner outperforms the 14B VTV-LLM model on most subtasks, highlighting its effectiveness and efficiency in tactile commonsense reasoning.

cs.AI↗
arXiv2026

CoFEND: A Cross-Modal Fusion End-to-End Network for Cold-Start Drug-Drug Interaction Prediction

Cold-start drug-drug interaction (DDI) prediction for new drugs is critical for minimizing unexpected adverse drug reactions. The key challenge is to capture similarity between new and known drugs. However, such similarity is closely associated with complex relationships and mechanisms among drugs, enzymes, transporters, molecular structures, and other biomedical entities. Existing methods have three limitations in capturing such similarity: (1) only partial relationships and mechanisms are considered, which overlooks cross-modal information and yields incomplete or biased similarity modeling; (2) similarity computation between new and known drugs is conducted separately across modalities and performed offline for cold-start DDI prediction, leading to misalignment between similarity computation and DDI prediction; and (3) existing interpretability analyses are typically single-modality and focus primarily on key determinants of the perpetrator drug, while the underlying causes of susceptibility for the victim drug are seldom investigated. To address these issues, this paper proposes a novel Cross-Modal-Fused End-to-End Learning Network (CMF-ELN) with three components. First, diverse multimodal information is leveraged to construct four types of drug-centered knowledge graphs, enabling comprehensive similarity modeling under reconstruction-based supervision. Second, a four-channel graph autoencoder is designed to fuse cross-modal similarity within an end-to-end learning framework. Finally, a two-stage interpretability scheme is devised to precisely localize key factors for both perpetrator and victim drugs. Extensive experiments on two real datasets demonstrate that CMF-ELN achieves significantly higher prediction accuracy and more comprehensive interpretability of mechanisms than its peers.

cs.LG↗
arXiv2026

Dynamic Neural Graph Encoding of Inference Processes in Deep Weight Space

The rapid advancements in using neural networks as implicit data representations have attracted significant interest in developing machine learning methods that analyze and process the weight spaces of other neural networks. However, efficiently handling these highdimensional weight spaces remains challenging. Existing methods often overlook the sequential nature of layer-by-layer processing in neural network inference. In this work, we propose a novel approach using dynamic graphs to represent neural network parameters, capturing the temporal dynamics of inference. Our Dynamic Neural Graph Encoder (DNG-Encoder) processes these graphs, preserving the sequential nature of neural processing. Additionally, we also leverage DNG-Encoder to develop INR2JLS (Implicit Neural Representation to Joint Latent Space) for facilitate downstream applications, such as classifying Implicit Neural Representations (INRs). Our approach demonstrates significant improvements across multiple tasks, surpassing the state-of-the-art INR classification accuracy by approximately 10% on the CIFAR-100-INR.

cs.LG↗
arXiv2026

Mitigating Batch Effects in Histopathology via Language-Mediated Robust Embedding Generation

Pathology foundation models (PFMs) have demonstrated strong potential across clinical and scientific applications, yet their performance is often hindered by batch effects, which are non-biological variations across tissue source institutions (TSIs) that distort learned feature representations and impair generalization. Conventional mitigation strategies, such as stain normalization, offer limited success in addressing these high-dimensional, complex artifacts. We present GLMP (General-purpose LLM-Mediated Pathology model), a novel framework that generates robust numerical embeddings from histology image patches through an intermediate textual representation. By leveraging pretrained general-purpose multimodal large language models (MLLMs) and text encoders, GLMP effectively prioritizes biologically meaningful signals over TSI-specific artifacts, thereby improving cross-institutional generalization. To our knowledge, GLMP is the first pathology model to use text descriptions of histological features as an intermediate representation for generating numerical embeddings from histology images. Our results highlight the untapped potential of broad-domain, non-specialized MLLMs in computational pathology and introduce a new paradigm for building versatile, generalizable, and robust pathology models.

cs.CV↗
arXiv2026

Reflective-Sail Weak Stability Boundary Structure with the Locally Optimal Control Law

Escaping from the Earth is the first step of interplanetary transfers. Traditional ballistic escape trajectories in the Sun-Earth circular restricted three-body problem face limitations in relatively long time of flight and low hyperbolic excess velocity. To augment the construction of escape trajectories from the Earth, this Note proposes the concept of reflective-sail weak stability boundary structures and accordingly constructs and analyzes escape trajectories from the Earth in the context of the Sun-Earth planar circular restricted three-body problem with a reflective sail. Using an ideal reflective sail, the locally optimal control law to maximize the time derivative of the Keplerian energy with respect to the Earth is adopted. Levi-Civita regularization about the Earth is derived to address the singularity caused by the Earth. The configurations of reflective-sail weak stability boundary structures are calculated to provide initial states for constructing escape trajectories and information about regions where escape is facilitated. Then, the escape trajectories using a reflective sail are constructed based on the proposed weak stability boundary structures. The escape performance, including time of flight and estimated hyperbolic excess velocity, is analyzed. Comparison with ballistic escape trajectories in the Sun-Earth PCR3BP is also performed, indicating improved escape performance characterized by shorter time of flight and higher hyperbolic excess velocity.

astro-ph.EP↗
arXiv2026

Full spectrum Unlearnable Examples via Spectral Equalization

Unlearnable examples (UEs) protect training data by injecting imperceptible perturbations so that models fail to extract exploitable representations. In this paper, we reveal that existing UEs exhibit a critical failure once low-pass filtering is applied, indicating that the effective perturbation signals for unlearnability concentrate predominantly in high frequencies. Hence, we argue that reliable UEs should remain effective across the full spectrum. To this end, we propose Full-spectrum Unlearnable examples via Spectral Equalization (FUSE), which aims to generate spectrum-agnostic perturbations by equalizing the contributions from different bands and enforcing cross-band consistency. Specifically, FUSE adopts a Random Spectral Masking (RSM) strategy during generator training, which randomly removes a contiguous frequency band, forcing the remaining bands to maintain unlearnability. In addition, FUSE further integrates Cross-Band Guidance (CBG), which enforces mutual consistency between high- and low-frequency components, thereby further enhancing low-frequency unlearnability and regulating high-frequency perturbations to preserve the semantic fidelity of images. Extensive experiments across multiple datasets, architectures, and spectral filtering demonstrate the strong protection achieved by FUSE.

cs.CV↗
arXiv2026

DT-GOL: Dual-Track Geometric Online Learning in Nonstationary Environment with Label Delay

Online learning is crucial for handling complex data streams in big data applications. Recent research has begun to focus on dynamic scenarios, i.e., non-stationary environments. However, a crucial yet often overlooked aspect is label latency, where new data may not receive labels in time due to the slow and expensive labeling process, thus hindering rapid adaptation to dynamic environments. To resolve this impasse, we propose Dual-Track Geometry Online Learning (DT-GOL), a novel framework that shifts from temporal compensation to spatial reasoning to bridge the supervised latency gap. By modeling the delay challenge as a semi-supervised task, we leverage real-time topological evolution of features as a reliable geometric surrogate for unobservable conceptual changes to achieve proactive supervised adaptation within the delay window. Unlike rigid self-training, we introduce a dynamic evidence calibration mechanism that distills geometric information into soft labels that perceive uncertainty, effectively mitigating the confirmation bias inherent in hard pseudo-labels. Furthermore, to resolve the stability-plasticity dilemma, we design a decoupled dual-track architecture in which a master learner serves as a stable anchor, updated strictly from delayed ground truth, while a transient branch leverages soft geometric knowledge for low-risk forward adaptation. Extensive experiments on real and synthetic datasets demonstrate that DT-GOL significantly outperforms existing state-of-the-art baseline methods, especially in scenarios with concept drift.

cs.LG↗
arXiv2026

FLFL: Federated Latent Factor Learning for Private Recovery of Spatio-Temporal Signals

Wireless sensor network (WSNs) stands out as a burgeoning and promising domain in intelligent sensing. Owing to various factors such as sudden sensor malfunctions or deliberate shutdown of partial nodes to save energy, the collected sensing signals from WSNs commonly have massive missing data, leading to adverse effects on subsequent analysis or decision-making. Latent factor learning (LFL) has proven to be highly effective in recovering the missing data for WSNs. However, the existing LFL models require the collected sensing signals to be maintained in one central place like a central server, which is becoming unacceptable for data owners who are getting increasingly privacy-sensitive. To address this issue, this paper innovatively proposes a federated latent factor learning (FLFL) model for privacy-preserving spatio-temporal signal recovery. Its main idea is two-fold: 1) it designs a sensor-level federated learning framework based on LFL, where each sensor only needs to upload gradient information rather than raw data for training a privacy-preserving recovery model, and 2) it incorporates the spatio-temporal correlation into the designed federated learning framework as the regularization constraint to improve its recovery accuracy. With such designs, FLFL can not only accurately recover the missing data of WSNs but also ensure data owners' privacy-preserving of raw data. To evaluate the proposed FLFL model, extensive experiments have been conducted on four real-world WSN datasets. The results demonstrate that FLFL significantly outperforms eight state-of-the-art federated and non-federated signal recovery models in terms of recovery accuracy with privacy-preserving.

cs.LG↗
arXiv2026

Suppression of p-Wave Altermagnetism by Localized 4f Electrons in CeNiAsO

Altermagnetism, characterized by momentum-dependent spin splitting and zero net magnetization, has so far been explored mainly in weakly or moderately correlated d-electron systems. How symmetry-allowed altermagnetic band splitting manifests in heavy-fermion materials, where magnetic exchange competes with Kondo correlations, remains unclear. Here we use high-resolution angle-resolved photoemission spectroscopy (ARPES) to investigate CeNiAsO, a Kondo-lattice system that was predicted to be a candidate for p-wave altermagnetism. Fermi surface mapping and polarization-dependent ARPES show that the experimentally observed itinerant bands are mainly derived from Ni 3d orbitals, while resonant photoemission reveals that the Ce 4f states remain predominantly localized with residual c-f hybridization. Ultra-low-temperature measurements reveal no resolvable near-Fermi-level p-wave-like exchange splitting on the Ni 3d-derived conduction bands across the successive antiferromagnetic transitions. These experimental observations cannot be captured by an itinerant-4f band-structure description, which predicts a sizable p-wave splitting in the itinerant bands. When the localized Ce 4f character is incorporated, our band structure calculations indicate that the itinerant Ce 4f band weight is shifted away from the Fermi level and the p-wave-like splitting on the Ni 3d-derived bands is reduced to the few-meV scale. These results establish CeNiAsO as a strongly correlated f-electron setting in which the magnetic symmetry allows p-wave-like band splitting, but localized 4f electrons strongly suppress its observable itinerant single-particle signature.

cond-mat.str-el↗
arXiv2026

Dimensional structure of thermodynamic topology in ultraspinning Kerr-AdS black holes

In this paper, we apply the thermodynamic topology framework to ultraspinning Kerr-AdS black holes in arbitrary spacetime dimensions. By constructing the off-shell Helmholtz free energy and the associated vector field, black hole states are characterized as topological defects, and their phase structures are described through zero points, winding numbers, and asymptotic thermodynamic behavior. Analyses of the four- and five-dimensional cases highlight the differences between even- and odd-dimensional configurations, while the endpoint behavior of the inverse-temperature curve, together with representative higher-dimensional cases, supports the absence of additional topological classes or subclasses. We find that only two thermodynamic topological structures appear: the standard class $W^{1+}$ for most configurations, and the distinct subclass $\tilde{W}^{1+}$ for odd-dimensional black holes with maximal rotations. These results support a unified classification scheme valid across dimensions for ultraspinning Kerr-AdS black holes.

hep-th↗
arXiv2026

Model-agnostic search of gravitational wave echoes in LVK data

Gravitational wave echoes offer a unique probe of the near-horizon structure of astrophysical black holes, beyond the standard "black hole spectroscopy." Theoretical waveform predictions, however, remain uncertain, motivating robust searches that avoid specific echo modeling. We present a model-agnostic search framework targeting long-lived quasinormal modes (QNMs) expected from strong interior reflection. By employing a generalized phase-marginalized likelihood that coherently combines data for each QNM across a detector network, our method enhances sensitivity to the signals. To handle real detector noise, we implement an optimized notching procedure to suppress instrumental spectral lines and refine the Bayesian parameter settings. We validate the performance of this framework using injection studies on O1 background data, demonstrating reliable signal recovery in realistic noise conditions. We then apply this method to three binary black hole merger events with high ringdown signal-to-noise ratios (SNRs): GW150914 from O1, GW231226 from O4a, and the recently reported O4 event GW250114. No statistically significant evidence for postmerger echoes is found. Consequently, we derive 90% upper limits on the network SNR and the average initial strain amplitude of the long-lived QNMs. These results provide model-agnostic constraints on late-time echoes from LVK data, complementing existing searches for other echo signatures.

gr-qc↗
arXiv2026

UMI-Bench 1.0: An Open and Reproducible Real-World Benchmark for Tabletop Robotic Manipulation with UMI Data

Real-robot evaluation is essential for understanding whether learned manipulation policies can operate reliably outside curated demonstrations. This need is particularly pressing for Universal Manipulation Interface (UMI)-style policies, whose performance depends on the coupling between wrist-view observations, action representation, data collection, and physical deployment. Existing real-world benchmarks have made important progress, but they are not designed around this UMI data-to-deployment setting. We present UMI-Bench 1.0, a local-first real-robot benchmark for standardized evaluation of UMI-style manipulation policies. To the best of our knowledge, this is the first benchmark dedicated to real-world evaluation of UMI-based manipulation models. UMI-Bench aligns data collection, scene reset, policy execution, result logging, and task-factor analysis within a unified protocol. By making the full evaluation process reproducible and auditable, UMI-Bench provides a practical testbed for measuring how UMI-trained policies generalize to real physical manipulation.

cs.RO↗
arXiv2026

Perfect divisibility and perfect-Pollyanna in bull-free graphs

A graph $G$ is {\em perfectly divisible} if, for each induced subgraph $H$ of $G$, $V(H)$ can be partitioned into $A$ and $B$ such that $H[A]$ is perfect and $ω(H[B])<ω(H)$. A {\em bull} is a graph consisting of a triangle with two disjoint pendant edges. Hoàng [Discrete Math. 349 (2026) 114809] proposed four conjectures: 1. $P_5$-free graphs are perfectly divisible; 2. Odd hole-free graphs are perfectly divisible; 3. Even hole-free graphs are perfectly divisible; and 4. $4K_1$-free graphs are perfectly divisible. Karthick et al. [Electron. J. Combin. 29 (2022) P3.19] proposed a conjecture: Fork-free graphs are perfectly divisible. In this paper, we prove that all of five conjectures above hold for bull-free graphs. Our results also generalize some results of Chudnovsky and Sivaraman [J. Graph Theory 90 (2019) 54--60] and Karthick et al. [Electron. J. Combin. 29 (2022) P3.19]. We say that a class ${\cal C}$ is {\em perfect-Pollyanna} if ${\cal C}\cap {\cal G}$ is perfectly divisible for any hereditary class ${\cal G}$ in which each triangle-free graph is 3-colorable. Let $H\in\{\text{house, hammer, diamond}\}$. In this paper, we prove that the class of $(\text{bull}, H)$-free graphs is perfect-Pollyanna. Let ${\cal C}$ be the class of $(\text{bull}, H)$-free graphs. This implies that ${\cal C}\cap {\cal G}$ is perfectly divisible if and only if all of triangle-free graphs in ${\cal G}$ are perfectly divisible. As corollaries, we show that $(\text{bull},{\cal H})$-free graphs are perfectly divisible, where ${\cal H}$ is one of $\{P_{11},C_4\},\{P_{14},C_5,C_4\}$, and $\{P_{17},C_6,C_5,C_4\}$.

math.CO↗
arXiv2026

F3-Tokenizer: Taming Audio Autoencoder Latents for Understanding and Generation

Continuous audio autoencoders reconstruct waveforms well but often produce latents with weak structure for understanding, while self-supervised audio encoders capture semantics but are not directly decodable. This mismatch complicates a single audio tokenizer that must support both understanding and generation. We adapt continuous autoencoder latents to this setting with two components: a noise-regularized autoencoder bottleneck and a latent-side representation encoder. The bottleneck uses channel normalization and stochastic perturbation instead of KL-based variational training, yielding scale-controlled continuous latents for reconstruction and autoregressive generation. The representation encoder is trained on frozen autoencoder latents with RQ-MTP and frozen-LLM supervision. The resulting tokenizer provides high-dimensional representations for understanding while preserving normalized continuous latents as generation targets

cs.SD↗
arXiv2026

Federated Learning for Multi-Center Sepsis Early Prediction with Privacy-Preserving

Privacy-sensitive and distributed characteristics of multi-center medical data bring severe obstacles to centralized modeling for accurate early prediction of sepsis. Federated learning (FL) has attracted growing attention as a promising framework for collaborative model development, as it allows multiple institutions to jointly train predictive models without directly sharing or centralizing raw data. Nevertheless, its practical performance, robustness, and privacy-preserving benefits remain insufficiently evaluated using real-world clinical datasets. To bridge this gap, this study systematically examines the application of federated learning to multi-center sepsis prediction. The experimental dataset consists of 648 clinically screened samples collected from three tertiary hospitals in China, with rigorous inclusion and exclusion criteria. We establish a centralized training paradigm as the performance baseline, and then implement a horizontal federated learning framework for distributed collaborative modeling. Extensive experimental results demonstrate that the federated learning-based model achieves highly comparable prediction accuracy to the centralized counterpart, while fundamentally avoiding privacy leakage. Further privacy security analysis verifies that malicious attackers cannot reconstruct the original patient data from the transmitted model parameters, indicating strong resistance against data reconstruction attacks. This work not only validates the practicality and security of federated learning in clinical sepsis prediction, but also provides a reliable and feasible solution for privacy-preserving multi-center medical collaboration.

cs.LG↗
arXiv2026

Can AI Review Improve Paper Drafting? An Empirical Study on 20 Computer Architecture Submissions

Research is advancing faster than ever with artificial intelligence (AI); and so are the corresponding research papers. The exploding volume of AI-generated papers have put a strain to peer review, leading to the usage of AI-generated review, potentially wide yet sneaky. However, relevant ethical concerns about confidentiality, quality, and fairness are raised and no consensus has been reached in the broad research community. We expect the debate to continue for a while, but in the meantime, we ask an alternative, practical question: \textit{can AI review improve paper drafting?} We study 20 computer architecture papers, with varying levels of submission lineage, to expose how well AI review aligns with human review, quantified by a set of metrics we define. To conduct the case study, we build a web UI-integrated tool, \emph{AI-Paper-Review}, that generates structured AI review of a draft paper, available at https://github.com/unarylab/ai-paper-review. This tool selects several AI reviewers from a diverse pool of AI reviewers and clusters and ranks their comments based on commonality and importance of review comments. It also allows to align AI comments with human comments to facilitate metric-based validation. The case study shows that AI review can cover a significant fraction of human-raised issues, but also raises issues missing in human review. This paper is not intended to encourage using AI for peer review at the current stage, but to study that (1) how AI review can improve paper drafting and (2) the potential and limitation of AI-based peer review. The release of the tool and the case study data is intended to instigate future research on this topic. Misuse for peer review would violate the ethics policies from major academic venues.

cs.AI↗