arXiv subjects

Di Wu

Publications and source records attributed to Di Wu.

At least 235 records · Page 13Linked to original sources

arXiv2025

Trustworthy Summarization via Uncertainty Quantification and Risk Awareness in Large Language Models

This study addresses the reliability of automatic summarization in high-risk scenarios and proposes a large language model framework that integrates uncertainty quantification and risk-aware mechanisms. Starting from the demands of information overload and high-risk decision-making, a conditional generation-based summarization model is constructed, and Bayesian inference is introduced during generation to model uncertainty in the parameter space, which helps avoid overconfident predictions. The uncertainty level of the generated content is measured using predictive distribution entropy, and a joint optimization of entropy regularization and risk-aware loss is applied to ensure that key information is preserved and risk attributes are explicitly expressed during information compression. On this basis, the model incorporates risk scoring and regulation modules, allowing summaries to cover the core content accurately while enhancing trustworthiness through explicit risk-level prompts. Comparative experiments and sensitivity analyses verify that the proposed method significantly improves the robustness and reliability of summarization in high-risk applications while maintaining fluency and semantic integrity. This research provides a systematic solution for trustworthy summarization and demonstrates both scalability and practical value at the methodological level.

cs.CL↗

arXiv2025

Please Translate Again: Two Simple Experiments on Whether Human-Like Reasoning Helps Translation

Large Language Models (LLMs) demonstrate strong reasoning capabilities for many tasks, often by explicitly decomposing the task via Chain-of-Thought (CoT) reasoning. Recent work on LLM-based translation designs hand-crafted prompts to decompose translation, or trains models to incorporate intermediate steps. Translating Step-by-step (Briakou et al., 2024), for instance, introduces a multi-step prompt with decomposition and refinement of translation with LLMs, which achieved state-of-the-art results on WMT24 test data. In this work, we scrutinise this strategy's effectiveness. Empirically, we find no clear evidence that performance gains stem from explicitly decomposing the translation process via CoT, at least for the models on test; and we show prompting LLMs to 'translate again' and self-refine yields even better results than human-like step-by-step prompting. While the decomposition influences translation behaviour, faithfulness to the decomposition has both positive and negative effects on translation. Our analysis therefore suggests a divergence between the optimal translation strategies for humans and LLMs.

cs.CL↗

arXiv2025

CSDformer: A Conversion Method for Fully Spike-Driven Transformer

Spike-based transformer is a novel architecture aiming to enhance the performance of spiking neural networks while mitigating the energy overhead inherent to transformers. However, methods for generating these models suffer from critical limitations: excessive training costs introduced by direct training methods, or unavoidably hardware-unfriendly operations in existing conversion methods. In this paper, we propose CSDformer, a novel conversion method for fully spike-driven transformers. We tailor a conversion-oriented transformer-based architecture and propose a new function NReLU to replace softmax in self-attention. Subsequently, this model is quantized and trained, and converted into a fully spike-driven model with temporal decomposition technique. Also, we propose delayed Integrate-andFire neurons to reduce conversion errors and improve the performance of spiking models. We evaluate CSDformer on ImageNet, CIFAR-10 and CIFAR-100 datasets and achieve 76.36% top-1 accuracy under 7 time-steps on ImageNet, demonstrating superiority over state-of-the-art models. Furthermore, CSDformer eliminates the need for training SNNs, thereby reducing training costs (reducing computational resource by 75% and accelerating training speed by 2-3$\times$). To the best of our knowledge, this is the first fully spike-driven transformer-based model developed via conversion method, achieving high performance under ultra-low latency, while dramatically reducing both computational complexity and training overhead.

cs.CV↗

arXiv2025

DRDT3: Diffusion-Refined Decision Test-Time Training Model

Decision Transformer (DT), a trajectory modelling method, has shown competitive performance compared to traditional offline reinforcement learning (RL) approaches on various classic control tasks. However, it struggles to learn optimal policies from suboptimal, reward-labelled trajectories. In this study, we explore the use of conditional generative modelling to facilitate trajectory stitching given its high-quality data generation ability. Additionally, recent advancements in Recurrent Neural Networks (RNNs) have shown their linear complexity and competitive sequence modelling performance over Transformers. We leverage the Test-Time Training (TTT) layer, an RNN that updates hidden states during testing, to model trajectories in the form of DT. We introduce a unified framework, called Diffusion-Refined Decision TTT (DRDT3), to achieve performance beyond DT models. Specifically, we propose the Decision TTT (DT3) module, which harnesses the sequence modelling strengths of both self-attention and the TTT layer to capture recent contextual information and make coarse action predictions. DRDT3 iteratively refines the coarse action predictions through the generative diffusion model, progressively moving closer to the optimal actions. We further integrate DT3 with the diffusion model using a unified optimization objective. With experiments on multiple tasks in the D4RL benchmark, our DT3 model without diffusion refinement demonstrates improved performance over standard DT, while DRDT3 further achieves superior results compared to state-of-the-art DT-based and offline RL methods.

cs.LG↗

arXiv2025

USEANet: Ultrasound-Specific Edge-Aware Multi-Branch Network for Lightweight Medical Image Segmentation

Ultrasound image segmentation faces unique challenges including speckle noise, low contrast, and ambiguous boundaries, while clinical deployment demands computationally efficient models. We propose USEANet, an ultrasound-specific edge-aware multi-branch network that achieves optimal performance-efficiency balance through four key innovations: (1) ultrasound-specific multi-branch processing with specialized modules for noise reduction, edge enhancement, and contrast improvement; (2) edge-aware attention mechanisms that focus on boundary information with minimal computational overhead; (3) hierarchical feature aggregation with adaptive weight learning; and (4) ultrasound-aware decoder enhancement for optimal segmentation refinement. Built on an ultra-lightweight PVT-B0 backbone, USEANet significantly outperforms existing methods across five ultrasound datasets while using only 3.64M parameters and 0.79G FLOPs. Experimental results demonstrate superior segmentation accuracy with 67.01 IoU on BUSI dataset, representing substantial improvements over traditional approaches while maintaining exceptional computational efficiency suitable for real-time clinical applications. Code is available at https://github.com/chouheiwa/USEANet.

eess.IV↗

arXiv2025

Unstable mode around the 3D boundary layer flow

We study the stability properties of boundary layer-type shear flows for the three-dimensional Navier-Stokes equations in the limit of small viscosity $0<ν\ll 1$. When the streamwise and spanwise velocity profiles are linearly independent near the boundary, we construct an unstable mode that exhibits rapid growth at the rate of $e^{t/\sqrtν}$. Our results reveal an analytic instability in the three-dimensional Navier-Stokes equations around generic boundary layer profiles. This instability arises from the interplay between spanwise flow and three-dimensional perturbations, and does not occur in purely two-dimensional flows.

math.AP↗

arXiv2025

Unlock giant nonreciprocity via multi-valued behavior of non-Hermitian zero-index materials

Although Einstein's field equations are time-independent, the multivalued feature of the horizon of a blackhole naturally enables the one-way transmission, leading to the strong arrow of time from the time-independent gravitational interaction. Here we experimentally demonstrate a photonic analogue of this principle and reveal the infinite nonreciprocity of the time-reversal-symmetric Maxwell equations. By designing a non-Hermitian zero-index magneto-optical metawaveguide, we introduce multivalued feature to this metawaveguide's complex eigenspace via an exceptional point with non-zero residue, bringing nonlocal, path-dependent historical memory to the system. Hence, a weak magneto-optical response can direct forward and backward waves to two photonic branches with largely distinct momenta and losses, leading to the optical nonreciprocity far beyond the limitation imposed by the magneto-optical material. We fabricated an a-Si/Ce:YIG metawaveguide, achieving nonreciprocal phase shift of 47.78 rad/mm and nonreciprocal loss of 53.9 dB/mm near 1575 nm, exceeding state-of-the-art nonreciprocal devices by an order of magnitude. Our principle universally applies from microwave to visible frequencies, leading to compact isolators, circulators, and sensors. Our principle can also be extended to nonreciprocal acoustic, elastic, and thermal systems. The proposed new paradigm -- geometry-based strong arrow of time in covariant and reversible physical systems -- has broad implications in many disciplines including string theory, cosmology, and astronomy.

physics.optics↗

arXiv2025

Your Trust, Your Terms: A General Paradigm for Near-Instant Cross-Chain Transfer

Cross-chain transactions today remain slow, costly, and fragmented. Existing custodial exchanges expose users to counterparty and centralization risks, while non-custodial liquidity bridges suffer from capital inefficiency and slow settlement; critically, neither approach guarantees users a unilateral path to recover assets if the infrastructure fails. We introduce the Delegated Ownership Transfer (DOT) paradigm, which decouples key ownership from value ownership to enable secure, high-performance cross-chain payments. In DOT, a user deposits funds into a sandboxed on-chain Temporary Account (TA) (value ownership) while delegating its private key (key ownership) to an abstract Trusted Entity (TE). Payments and swaps are thus reframed as near-instant, off-chain ownership handoffs. Security follows from dual guarantees: the TE's exclusive control prevents double-spending, while a pre-signed, unilateral recovery transaction ensures users retain ultimate authority over their assets. Building on this foundation, we design a novel off-chain atomic swap that executes optimistically in near real time and remains fair even if the TE fails. We formalize the security of DOT in the Universal Composability framework and present two concrete instantiations: a high-performance design based on Trusted Execution Environments (TEEs) and a cryptographically robust variant leveraging threshold cryptography. Our geo-distributed prototype shows that cross-chain payments complete in under 16.70 ms and atomic swaps in under 33.09 ms, with costs fully decoupled from Layer-1 gas fees. These results provide a practical blueprint for building secure, efficient, and interoperable cross-chain payment systems.

cs.CR↗

arXiv2025

Goal-Conditioned Data Augmentation for Offline Reinforcement Learning

Offline reinforcement learning (RL) enables policy learning from pre-collected offline datasets, relaxing the need to interact directly with the environment. However, limited by the quality of offline datasets, it generally fails to learn well-qualified policies in suboptimal datasets. To address datasets with insufficient optimal demonstrations, we introduce Goal-cOnditioned Data Augmentation (GODA), a novel goal-conditioned diffusion-based method for augmenting samples with higher quality. Leveraging recent advancements in generative modelling, GODA incorporates a novel return-oriented goal condition with various selection mechanisms. Specifically, we introduce a controllable scaling technique to provide enhanced return-based guidance during data sampling. GODA learns a comprehensive distribution representation of the original offline datasets while generating new data with selectively higher-return goals, thereby maximizing the utility of limited optimal demonstrations. Furthermore, we propose a novel adaptive gated conditioning method for processing noisy inputs and conditions, enhancing the capture of goal-oriented guidance. We conduct experiments on the D4RL benchmark and real-world challenges, specifically traffic signal control (TSC) tasks, to demonstrate GODA's effectiveness in enhancing data quality and superior performance compared to state-of-the-art data augmentation methods across various offline RL algorithms.

cs.LG↗

arXiv2025

End to End Autoencoder MLP Framework for Sepsis Prediction

Sepsis is a life threatening condition that requires timely detection in intensive care settings. Traditional machine learning approaches, including Naive Bayes, Support Vector Machine (SVM), Random Forest, and XGBoost, often rely on manual feature engineering and struggle with irregular, incomplete time-series data commonly present in electronic health records. We introduce an end-to-end deep learning framework integrating an unsupervised autoencoder for automatic feature extraction with a multilayer perceptron classifier for binary sepsis risk prediction. To enhance clinical applicability, we implement a customized down sampling strategy that extracts high information density segments during training and a non-overlapping dynamic sliding window mechanism for real-time inference. Preprocessed time series data are represented as fixed dimension vectors with explicit missingness indicators, mitigating bias and noise. We validate our approach on three ICU cohorts. Our end-to-end model achieves accuracies of 74.6 percent, 80.6 percent, and 93.5 percent, respectively, consistently outperforming traditional machine learning baselines. These results demonstrate the framework's superior robustness, generalizability, and clinical utility for early sepsis detection across heterogeneous ICU environments.

cs.LG↗

arXiv2025

Auto prompt sql: a resource-efficient architecture for text-to-sql translation in constrained environments

Using the best Text-to-SQL methods in resource-constrained environments is challenging due to their reliance on resource-intensive open-source models. This paper introduces Auto Prompt SQL(AP-SQL), a novel architecture designed to bridge the gap between resource-efficient small open-source models and the powerful capabilities of large closed-source models for Text-to-SQL translation. Our method decomposes the task into schema filtering, retrieval-augmented text-to-SQL generation based on in-context examples, and prompt-driven schema linking and SQL generation. To improve schema selection accuracy, we fine-tune large language models. Crucially, we also explore the impact of prompt engineering throughout the process, leveraging Chain-of-Thought(CoT) and Graph-of-Thought(GoT) templates to significantly enhance the model's reasoning for accurate SQL generation. Comprehensive evaluations on the Spider benchmarks demonstrate the effectiveness of AP-SQL.

cs.CL↗

arXiv2025

Energy Transition Domain and Its Application in Constructing Gravity-Assist Escape Trajectories

This Note proposes the concept and theory of energy transition domain (ETD) defined by the mechanical energy of spacecraft in the Earth-Moon planar circular restricted three-body problem (PCR3BP) inspired by the pioneering work from Ano{è} et al. (2024) on the ETD defined by the two-body energy with respect to the secordary body in the PCR3BP. An effective construction method of gravity-assist escape trajectories is then proposed. Firstly, the concept of the ETD defined by the mechanical energy is presented, and its dependency on the Jacobi energy is analyzed. This dependency may provide prior knowledge about selecting the range of the Jacobi energy in the construction of escape trajectories. Then, gravity-assist escape trajectories departing from the 167 km low Earth orbit and 36000 km geosynchronous Earth orbit are constructed based on the ETD. The initial states are selected in the sphere of influence of the Moon, and the trajectories are searched from the forward and backward integration. Finally, the obtained solutions are presented and analyzed.

astro-ph.EP↗

arXiv2025

Understanding the atomically precise evolution of the miscibility of newly prepared face-centered cubic W-Cu nanoalloys and its asymmetry

According to classical Miedema theory, reducing crystals to the order of nanometer sizes might greatly modulate the mixing enthalpy of elements, thus enabling the invention of a lot of new bulk-immiscible alloys. Although numerous alloys with higher mixing enthalpies remain unexplored, this strategy is approaching its limit, as reflected by the critical diameter of recent alloys of 1.8 nm, which corresponds to ~150 atoms and hardly provides a crystalline order. Future development requires not only even smaller atomic-scale control but also a new surface energy-saving mechanism. Here, we report the formation of W-Cu nanoalloys with a very large miscibility gap in the bulk via the use of an atomically size-selected cluster beam source as an example. The face-centered cubic (FCC) structure was demonstrated through electron diffraction, which indicated a lattice constant of 3.88Å for W0.85Cu0.15 nanoalloys (~2280 atoms). In this comprehensive study that covers a large parameter space of W/Cu compositions and numbers of atoms, an asymmetric miscibility nanophase diagram in which W-rich compositions favor mixing and the critical size is approximately 6000 atoms, which far exceeds the approximately tens of atoms predicted via classical theory, was obtained for the first time. Density functional theory (DFT) calculations revealed a mutual strain-induced mechanism that simultaneously lowers the surface energies while reducing the size to the atomic scale. This approach paves the way for the development of new high-performance nonequilibrium phase alloys.

cond-mat.mtrl-sci↗

arXiv2025

Catwalk: Unary Top-K for Efficient Ramp-No-Leak Neuron Design for Temporal Neural Networks

Temporal neural networks (TNNs) are neuromorphic neural networks that utilize bit-serial temporal coding. TNNs are composed of columns, which in turn employ neurons as their building blocks. Each neuron processes volleys of input spikes, modulated by associated synaptic weights, on its dendritic inputs. Recently proposed neuron implementation in CMOS employs a Spike Response Model (SRM) with a ramp-no-leak (RNL) response function and assumes all the inputs can carry spikes. However, in actual spike volleys, only a small subset of the dendritic inputs actually carry spikes in each compute cycle. This form of sparsity can be exploited to achieve better hardware efficiency. In this paper, we propose a Catwalk neuron implementation by relocating spikes in a spike volley as a sorted subset cluster via unary top-k. Such relocation can significantly reduce the cost of the subsequent parallel counter (PC) for accumulating the response functions from the spiking inputs. This can lead to improvements on area and power efficiency in RNL neuron implementation. Place-and-route results show Catwalk is 1.39x and 1.86x better in area and power, respectively, as compared to existing SRM0-RNL neurons.

cs.AR↗

arXiv2025

Cosmological constraints on small-scale primordial non-Gaussianity

In contrast to the large-scale primordial power spectrum $\mathcal{P}_ζ(k)$ and primordial non-Gaussianity $f_{\mathrm{NL}}$, which are strictly constrained, the small-scale $\mathcal{P}_ζ(k)$ and $f_{\mathrm{NL}}$ remain less restricted. Considering local-type primordial non-Gaussianity, we study the PBH and SIGW caused by large-amplitude small-scale primordial power spectrum. By analyzing current observational data from PTA, CMB, BAO, and abundance of PBH, and combining them with the SNR analysis of LISA, we rigorously constrain the parameter space of $\mathcal{P}_ζ(k)$ and $f_{\mathrm{NL}}$. Furthermore, we examine the effects of different shapes of the primordial power spectrum on these constraints and comprehensively calculate the Bayes factors for various models. Our results indicate that SIGW generated by a monochromatic primordial power spectrum are more likely to dominate current PTA observations, with the corresponding constraint on the primordial non-Gaussian parameter being $-10.0<f_{\mathrm{NL}}<1.2$.

astro-ph.CO↗

arXiv2025

LongRetriever: Towards Ultra-Long Sequence based Candidate Retrieval for Recommendation

Precisely modeling user ultra-long sequences is critical for industrial recommender systems. Current approaches predominantly focus on leveraging ultra-long sequences in the ranking stage, whereas research for the candidate retrieval stage remains under-explored. This paper presents LongRetriever, a practical framework for incorporating ultra-long sequences into the retrieval stage of recommenders. Specifically, we propose in-context training and multi-context retrieval, which enable candidate-specific interaction between user sequence and candidate item, and ensure training-serving consistency under the search-based paradigm. Extensive online A/B testing conducted on a large-scale e-commerce platform demonstrates statistically significant improvements, confirming the framework's effectiveness. Currently, LongRetriever has been fully deployed in the platform, impacting billions of users.

cs.IR↗

arXiv2025

Adaptive Ensemble Learning with Gaussian Copula for Load Forecasting

Machine learning (ML) is capable of accurate Load Forecasting from complete data. However, there are many uncertainties that affect data collection, leading to sparsity. This article proposed a model called Adaptive Ensemble Learning with Gaussian Copula to deal with sparsity, which contains three modules: data complementation, ML construction, and adaptive ensemble. First, it applies Gaussian Copula to eliminate sparsity. Then, we utilise five ML models to make predictions individually. Finally, it employs adaptive ensemble to get final weighted-sum result. Experiments have demonstrated that our model are robust.

cs.LG↗

arXiv2025

Instantaneous optical selection rule for independent control of valley currents

We reveal an instantaneous optical valley selection rule that illuminates the coupling between the instantaneous optical chirality of the driving laser field and the chirality of valley systems. Building on this principle, we propose and demonstrate that a single chirality-separated optical field, in which oppositely signed instantaneous optical chiralities are separated within an optical cycle, enables independent manipulation of currents from K and K' valleys. Based on this scheme, we highlight two key example applications: (1) complete separation of currents from different valleys, yielding 100%-purity valley-polarized currents, and (2) generation of pure valley current with zero net charge flow. Our work offers a robust and highly controllable all-optical strategy for ultrafast engineering valley currents in the optical cycle timescale, paving a new avenue for valleytronics and quantum information technologies.

physics.optics↗