arXiv subjects

Wei Li

Publications and source records attributed to Wei Li.

At least 379 records · Page 21Linked to original sources

arXiv2025

Learning Arbitrary-Scale RAW Image Downscaling with Wavelet-based Recurrent Reconstruction

Image downscaling is critical for efficient storage and transmission of high-resolution (HR) images. Existing learning-based methods focus on performing downscaling within the sRGB domain, which typically suffers from blurred details and unexpected artifacts. RAW images, with their unprocessed photonic information, offer greater flexibility but lack specialized downscaling frameworks. In this paper, we propose a wavelet-based recurrent reconstruction framework that leverages the information lossless attribute of wavelet transformation to fulfill the arbitrary-scale RAW image downscaling in a coarse-to-fine manner, in which the Low-Frequency Arbitrary-Scale Downscaling Module (LASDM) and the High-Frequency Prediction Module (HFPM) are proposed to preserve structural and textural integrity of the reconstructed low-resolution (LR) RAW images, alongside an energy-maximization loss to align high-frequency energy between HR and LR domain. Furthermore, we introduce the Realistic Non-Integer RAW Downscaling (Real-NIRD) dataset, featuring a non-integer downscaling factor of 1.3$\times$, and incorporate it with publicly available datasets with integer factors (2$\times$, 3$\times$, 4$\times$) for comprehensive benchmarking arbitrary-scale image downscaling purposes. Extensive experiments demonstrate that our method outperforms existing state-of-the-art competitors both quantitatively and visually. The code and dataset will be released at https://github.com/RenYangSCU/ASRD.

eess.IV↗

arXiv2025

AGA: An adaptive group alignment framework for structured medical cross-modal representation learning

Learning medical visual representations from paired images and reports is a promising direction in representation learning. However, current vision-language pretraining methods in the medical domain often simplify clinical reports into single entities or fragmented tokens, ignoring their inherent structure. In addition, contrastive learning frameworks typically depend on large quantities of hard negative samples, which is impractical for small-scale medical datasets. To tackle these challenges, we propose Adaptive Grouped Alignment (AGA), a new framework that captures structured semantics from paired medical images and reports. AGA introduces a bidirectional grouping mechanism based on a sparse similarity matrix. For each image-report pair, we compute fine-grained similarities between text tokens and image patches. Each token selects its top-matching patches to form a visual group, and each patch selects its most related tokens to form a language group. To enable adaptive grouping, we design two threshold gating modules, called Language Grouped Threshold Gate and Vision Grouped Threshold Gate, which learn grouping thresholds dynamically. Group representations are computed as weighted averages based on similarity scores. To align each token with its group representation, we introduce an Instance Aware Group Alignment loss that operates within each image-text pair, removing the need for external negatives. Finally, a Bidirectional Cross-modal Grouped Alignment module is applied to enhance fine-grained alignment between visual and linguistic group representations. Extensive experiments on public and private datasets show that our method achieves strong performance on image-text retrieval and classification tasks under both fine-tuning and zero-shot settings.

cs.CV↗

arXiv2025

Low-Communication Resilient Distributed Estimation Algorithm Based on Memory Mechanism

In multi-task adversarial networks, the accurate estimation of unknown parameters in a distributed algorithm is hindered by attacked nodes or links. To tackle this challenge, this brief proposes a low-communication resilient distributed estimation algorithm. First, a node selection strategy based on reputation is introduced that allows nodes to communicate with more reliable subset of neighbors. Subsequently, to discern trustworthy intermediate estimates, the Weighted Support Vector Data Description (W-SVDD) model is employed to train the memory data. This trained model contributes to reinforce the resilience of the distributed estimation process against the impact of attacked nodes or links. Additionally, an event-triggered mechanism is introduced to minimize ineffective updates to the W-SVDD model, and a suitable threshold is derived based on assumptions. The convergence of the algorithm is analyzed. Finally, simulation results demonstrate that the proposed algorithm achieves superior performance with less communication cost compared to other algorithms.

cs.DC↗

arXiv2025

Come Together, But Not Right Now: A Progressive Strategy to Boost Low-Rank Adaptation

Low-rank adaptation (LoRA) has emerged as a leading parameter-efficient fine-tuning technique for adapting large foundation models, yet it often locks adapters into suboptimal minima near their initialization. This hampers model generalization and limits downstream operators such as adapter merging and pruning. Here, we propose CoTo, a progressive training strategy that gradually increases adapters' activation probability over the course of fine-tuning. By stochastically deactivating adapters, CoTo encourages more balanced optimization and broader exploration of the loss landscape. We provide a theoretical analysis showing that CoTo promotes layer-wise dropout stability and linear mode connectivity, and we adopt a cooperative-game approach to quantify each adapter's marginal contribution. Extensive experiments demonstrate that CoTo consistently boosts single-task performance, enhances multi-task merging accuracy, improves pruning robustness, and reduces training overhead, all while remaining compatible with diverse LoRA variants. Code is available at https://github.com/zwebzone/coto.

cs.LG↗

arXiv2025

MIGE: Mutually Enhanced Multimodal Instruction-Based Image Generation and Editing

Despite significant progress in diffusion-based image generation, subject-driven generation and instruction-based editing remain challenging. Existing methods typically treat them separately, struggling with limited high-quality data and poor generalization. However, both tasks require capturing complex visual variations while maintaining consistency between inputs and outputs. Inspired by this, we propose MIGE, a unified framework that standardizes task representations using multimodal instructions. It first treats subject-driven generation as creation on a blank canvas and instruction-based editing as modification of an existing image, establishing a shared input-output formulation, then introduces a novel multimodal encoder that maps free-form multimodal instructions into a unified vision-language space, integrating visual and semantic features through a feature fusion mechanism. This unification enables joint training of both tasks, providing two key advantages: (1) Cross-Task Enhancement: by leveraging shared visual and semantic representations, joint training improves instruction adherence and visual consistency in both subject-driven generation and instruction-based editing. (2) Generalization: learning in a unified format facilitates cross-task knowledge transfer, enabling MIGE to generalize to novel compositional tasks, including instruction-based subject-driven editing. Experiments show that MIGE excels in both subject-driven generation and instruction-based editing while setting a SOTA in the new task of instruction-based subject-driven editing. Code and model have been publicly available at https://github.com/Eureka-Maggie/MIGE.

cs.CV↗

arXiv2025

RailX: A Flexible, Scalable, and Low-Cost Network Architecture for Hyper-Scale LLM Training Systems

Increasingly large AI workloads are calling for hyper-scale infrastructure; however, traditional interconnection network architecture is neither scalable nor cost-effective enough. Tree-based topologies such as the \textit{Rail-optimized} network are extremely expensive, while direct topologies such as \textit{Torus} have insufficient bisection bandwidth and flexibility. In this paper, we propose \textit{RailX}, a reconfigurable network architecture based on intra-node direct connectivity and inter-node circuit switching. Nodes and optical switches are physically 2D-organized, achieving better scalability than existing centralized circuit switching networks. We propose a novel interconnection method based on \textit{Hamiltonian Decomposition} theory to organize separate rail-based rings into \textit{all-to-all} topology, simultaneously optimizing ring-collective and all-to-all communication. More than $100$K chips with hyper bandwidth can be interconnected with a flat switching layer, and the diameter is only $2\sim4$ inter-node hops. The network cost per injection/All-Reduce bandwidth of \textit{RailX} is less than $10\%$ of the Fat-Tree, and the cost per bisection/All-to-All bandwidth is less than $50\%$ of the Fat-Tree. Specifically, only $\sim$\$$1.3$B is required to interconnect 200K chips with 1.8TB bandwidth. \textit{RailX} can also be used in the ML-as-a-service (MLaaS) scenario, where single or multiple training workloads with various shapes, scales, and parallelism strategies can be flexibly mapped, and failures can be worked around.

cs.AR↗

arXiv2025

Results of 15-Year Pulsar Timing of PSR J0007+7303 with Fermi-LAT

The study of pulsar glitches provides a unique window into the internal structure and dynamic processes of neutron stars. PSR J0007+7303, a very bright gamma-ray pulsar, is the first pulsar discovered by the Fermi-LAT telescope. In this paper, we present the 15 years of timing results of this pulsar using the Fermi-LAT data. We identified nine glitches, five of which are newly discovered. Among these, two are small glitches, occurring between the three previously reported ones, while the other four are large glitches. The glitches exhibit fractional frequency changes ranging from 15 x 10^-9 to 1238 x 10^-9, with intervals of approximately 1-2 years between events. Uniquely, this pulsar shows no exponential recovery behavior following any glitch, setting it apart from most glitching pulsars. Furthermore, no significant changes were observed in the gamma-ray pulse profile, flux, or phase-averaged spectra before and after glitches, indicating the stability of the pulsar's emission properties despite internal changes. A parametric analysis of the glitches yielded a fractional moment of inertia of the crustal superfluid involved in glitches as 1.06 percent, which matches extremely well with previous statistical work if the non-dissipative entrainment effect is not considered and strongly supports the internal origin of these glitches. These results highlight the distinct glitch behavior of PSR J0007+7303 and offer valuable insights into the crust-superfluid interaction in neutron stars. The physical origin of no exponential recovery is also discussed.

astro-ph.HE↗

arXiv2025

An Empirical Study on Embodied Artificial Intelligence Robot (EAIR) Software Bugs

Embodied Artificial Intelligence Robots (EAIR) is an emerging and rapidly evolving technological domain. Ensuring their program correctness is fundamental to their successful deployment. However, a general and in-depth understanding of EAIR system bugs remains lacking, which hinders the development of practices and techniques to tackle EAIR system bugs. To bridge this gap, we conducted the first systematic study of 885 EAIR system bugs collected from 80 EAIR system projects to investigate their symptoms, underlying causes, and module distribution. Our analysis takes considerable effort, which classifies these bugs into 18 underlying causes, 15 distinct symptoms, and identifies 13 affected modules. It reveals several new interesting findings and implications which help shed light on future research on tackling or repairing EAIR system bugs. First, among the 15 identified symptoms, our findings highlight 8 symptoms specific to EAIR systems, which is characterized by severe functional failures and potential physical hazards. Second, within the 18 underlying causes, we define 8 EAIR-specific causes, the majority of which stem from the intricate issues of AI- agent reasoning and decision making. Finally, to facilitate precise and efficient bug prediction, detection, and repair, we constructed a mapping between underlying causes and the modules in which they most frequently occur, which enables researchers to focus diagnostic efforts on the modules most susceptible to specific bug types.

cs.SE↗

arXiv2025

Hybrid Boundary Physics-Informed Neural Networks for Solving Navier-Stokes Equations with Complex Boundary

Physics-informed neural networks (PINN) have achieved notable success in solving partial differential equations (PDE), yet solving the Navier-Stokes equations (NSE) with complex boundary conditions remains a challenging task. In this paper, we introduce a novel Hybrid Boundary PINN (HB-PINN) method that combines a pretrained network for efficient initialization with a boundary-constrained mechanism. The HB-PINN method features a primary network focused on inner domain points and a distance metric network that enhances predictions at the boundaries, ensuring accurate solutions for both boundary and interior regions. Comprehensive experiments have been conducted on the NSE under complex boundary conditions, including the 2D cylinder wake flow and the 2D blocked cavity flow with a segmented inlet. The proposed method achieves state-of-the-art (SOTA) performance on these benchmark scenarios, demonstrating significantly improved accuracy over existing PINN-based approaches.

physics.comp-ph↗

arXiv2025

Livatar-1: Real-Time Talking Heads Generation with Tailored Flow Matching

We present Livatar, a real-time audio-driven talking heads videos generation framework. Existing baselines suffer from limited lip-sync accuracy and long-term pose drift. We address these limitations with a flow matching based framework. Coupled with system optimizations, Livatar achieves competitive lip-sync quality with a 8.50 LipSync Confidence on the HDTF dataset, and reaches a throughput of 141 FPS with an end-to-end latency of 0.17s on a single A10 GPU. This makes high-fidelity avatars accessible to broader applications. Our project is available at https://www.hedra.com/ with with examples at https://h-liu1997.github.io/Livatar-1/

cs.CV↗

arXiv2025

RetinaLogos: Fine-Grained Synthesis of High-Resolution Retinal Images Through Captions

The scarcity of high-quality, labelled retinal imaging data, which presents a significant challenge in the development of machine learning models for ophthalmology, hinders progress in the field. Existing methods for synthesising Colour Fundus Photographs (CFPs) largely rely on predefined disease labels, which restricts their ability to generate images that reflect fine-grained anatomical variations, subtle disease stages, and diverse pathological features beyond coarse class categories. To overcome these challenges, we first introduce an innovative pipeline that creates a large-scale, captioned retinal dataset comprising 1.4 million entries, called RetinaLogos-1400k. Specifically, RetinaLogos-1400k uses the visual language model(VLM) to describe retinal conditions and key structures, such as optic disc configuration, vascular distribution, nerve fibre layers, and pathological features. Building on this dataset, we employ a novel three-step training framework, RetinaLogos, which enables fine-grained semantic control over retinal images and accurately captures different stages of disease progression, subtle anatomical variations, and specific lesion types. Through extensive experiments, our method demonstrates superior performance across multiple datasets, with 62.07% of text-driven synthetic CFPs indistinguishable from real ones by ophthalmologists. Moreover, the synthetic data improves accuracy by 5%-10% in diabetic retinopathy grading and glaucoma detection. Codes are available at https://github.com/uni-medical/retina-text2cfp.

eess.IV↗

arXiv2025

Interplay of short-range bond order and A-type antiferromagnetic order in metallic triangular lattice GdZn$_3$P$_3$

We investigate a hexagonal ScAl$_3$C$_3$-type antiferromagnet GdZn$_3$P$_3$ single crystal. Compared with antiferromagnetic topological material EuM$_2$X$_2$ (M=Zn, Cd; X=P, As), the GdZn$_3$P$_3$ features an additional ZnP$_3$ trigonal planar units. Notably, single-crystal X-ray diffraction analysis reveals that Zn and P atoms within trigonal planar layer exhibit significant anisotropic displacement parameters with a space group of P63/mmc. Meanwhile, scanning transmission electron microscopy experiment demonstrates the presence of interstitial P atoms above and below the ZnP honeycomb lattice, suggesting potential ZnP bond instability within the ZnP$_3$ trigonal layers. Concerning the triangular Gd$^{3+}$ layer, the magnetic susceptibility $χ$$(T)$ and heat capacity measurements reveal long-range antiferromagnetic order at T$_N$ = 4.5 K. Below T$_N$, the in-plane $χ$$(T)$ is nearly 4 times the $χ$$(T)$ along $c$ axis, indicative of strong magnetic anisotropy. The Curie Weiss fitting to the low temperature $χ$$(T)$ data reveals ferromagnetic interaction ($θ$$_{CW}$ = 5.2 K) in ab-plane, and antiferromagnetic interaction ($θ$$_{CW}$ = -1 K) along c axis, suggesting the ground state as an A-type antiferromagnetic order. Correspondingly, the density function theory calculation shows that GdZn$_3$P$_3$ is an indirect semiconductor with a band gap 0.27 eV, supported by the resistivity measurement on polycrystal sample. Interestingly, the GdZn$_3$P$_3$ single crystal exhibits metallic conductivity with an anomaly at T$_N$, likely associated with the observation of interstitial P atoms mentioned above. Therefore, our results establish GdZn$_3$P$_3$ system as a concrete example for investigating the coupling between charge carrier and triangular lattice magnetism in the two-dimensional lattice framework, on the background of short-range bond order.

cond-mat.str-el↗

arXiv2025

Hund's Rule, Interorbital Hybridization, and High-$T_c$ Superconductivity in the Bilayer Nickelate

Understanding the pairing mechanism in bilayer nickelate superconductors constitutes a fascinating quest. Here we investigate the intriguing interplay between Hund's rule coupling and interorbital hybridization in a two-orbital model for bilayer nickelates, using a comprehensive tensor network approach: density matrix renormalization group for finite-size systems, infinite projected entangled-pair states in the thermodynamic limit, and thermal tensor networks for finite-temperature properties. We explain the pressure-dependent high-$T_c$ superconductivity observed in experiment, by identifying three distinct superconductive (SC) regimes: hybridization dominant, Hund's rule dominant, and the hybrid-Hund synergistic SC regimes. In these SC regimes, both $d_{x^2-y^2}$ and $d_{z^2}$ orbitals exhibit algebraic pairing correlations with similar Luttinger parameters $K_{\mathrm{SC}}$. However, the former exhibits a much stronger amplitude than the latter, with a distinctly higher SC characteristic temperature $T_c^*$, below which the pairing susceptibility diverges as $χ_{\mathrm{SC}}(T) \sim 1/T^{2-K_{\mathrm{SC}}}$. With realistic model parameters, we find the pressurized La$_3$Ni$_2$O$_7$ falls into the Hund's rule dominated SC regime. As hybridization further enhances with pressure, it leads to significant interorbital frustration and in turn suppresses the SC correlations, explaining the rise and fall of high-$T_c$ superconductivity under high pressure. Our results offer a comprehensive understanding of the interlayer pairing in superconducting La$_3$Ni$_2$O$_7$.

cond-mat.str-el↗

arXiv2025

All-optical Fourier neural network using partially coherent light

Optical neural networks present distinct advantages over traditional electrical counterparts, such as accelerated data processing and reduced energy consumption. While coherent light is conventionally employed in optical neural networks, our study proposes harnessing spatially incoherent light in all-optical Fourier neural networks. Contrary to numerical predictions of declining target recognition accuracy with increased incoherence, our experimental results demonstrate a surprising outcome: improved accuracy with incoherent light. We attribute this unexpected enhancement to spatially incoherent light's ability to alleviate experimental errors like diffraction rings, laser speckle, and edge effects. Our controlled experiments introduced spatial incoherence by passing monochromatic light through a spatial light modulator featuring a dynamically changing random phase array. These findings underscore partially coherent light's potential to optimize optical neural networks, delivering dependable and efficient solutions for applications demanding consistent accuracy and robustness across diverse conditions.

physics.optics↗

arXiv2025

An Empirical Study of Interaction Bugs in ROS-based Software

Modern robotic systems integrate multiple independent software and hardware components, each responsible for distinct functionalities such as perception, decision-making, and execution. These components interact extensively to accomplish complex end-to-end tasks. As a result, the overall system reliability depends not only on the correctness of individual components, but also on the correctness of their interactions. Failures often manifest at the boundaries between components, yet interaction-related reliability issues in robotics--referred to here as interaction bugs (iBugs)--remain underexplored. This work presents an empirical study of iBugs within robotic systems built using the Robot Operating System (ROS), a widely adopted open-source robotics framework. A total of 121 iBugs were analyzed across ten actively maintained and representative ROS projects. The identified iBugs are categorized into three major types: intra-system iBugs, hardware iBugs, and environmental iBugs, covering a broad range of interaction scenarios in robotics. The analysis includes an examination of root causes, fixing strategies, and the impact of these bugs. Several findingsa are derived that shed light on the nature of iBugs and suggest directions for improving their prevention and detection. These insights aim to inform the design of more robust and safer robotic systems.

cs.SE↗

arXiv2025

Continuous variable quantum communication with 40 pairs of entangled sideband

Constructing large-scale quantum resources is an important foundation for further improving the efficiency and scalability of quantum communication. Here, we present an efficient extraction and stable control scheme of 40 pairs of entangled sideband modes from the squeezed light by specially designing optical parametric oscillator. Utilizing the low-loss optical frequency comb control technology and the local cross-correlation algorithm, we model and manage the efficient separation process of the entangled sidebands modes facilitated by the optical filtering cavities, a maximum entanglement level of 6.5 dB is achieved. The feasibility of large-capacity quantum dense coding based on these entangled sideband modes is proved experimentally, which is of great significance for optimizing the utilization of quantum resources, thereby contributing to the advancement of large-capacity quantum communication networks and enabling the realization of more secure and efficient quantum communication systems.

quant-ph↗

arXiv2025

Ophora: A Large-Scale Data-Driven Text-Guided Ophthalmic Surgical Video Generation Model

In ophthalmic surgery, developing an AI system capable of interpreting surgical videos and predicting subsequent operations requires numerous ophthalmic surgical videos with high-quality annotations, which are difficult to collect due to privacy concerns and labor consumption. Text-guided video generation (T2V) emerges as a promising solution to overcome this issue by generating ophthalmic surgical videos based on surgeon instructions. In this paper, we present Ophora, a pioneering model that can generate ophthalmic surgical videos following natural language instructions. To construct Ophora, we first propose a Comprehensive Data Curation pipeline to convert narrative ophthalmic surgical videos into a large-scale, high-quality dataset comprising over 160K video-instruction pairs, Ophora-160K. Then, we propose a Progressive Video-Instruction Tuning scheme to transfer rich spatial-temporal knowledge from a T2V model pre-trained on natural video-text datasets for privacy-preserved ophthalmic surgical video generation based on Ophora-160K. Experiments on video quality evaluation via quantitative analysis and ophthalmologist feedback demonstrate that Ophora can generate realistic and reliable ophthalmic surgical videos based on surgeon instructions. We also validate the capability of Ophora for empowering downstream tasks of ophthalmic surgical workflow understanding. Code is available at https://github.com/uni-medical/Ophora.

eess.IV↗

arXiv2025

DiffNMR: Diffusion Models for Nuclear Magnetic Resonance Spectra Elucidation

Nuclear Magnetic Resonance (NMR) spectroscopy is a central characterization method for molecular structure elucidation, yet interpreting NMR spectra to deduce molecular structures remains challenging due to the complexity of spectral data and the vastness of the chemical space. In this work, we introduce DiffNMR, a novel end-to-end framework that leverages a conditional discrete diffusion model for de novo molecular structure elucidation from NMR spectra. DiffNMR refines molecular graphs iteratively through a diffusion-based generative process, ensuring global consistency and mitigating error accumulation inherent in autoregressive methods. The framework integrates a two-stage pretraining strategy that aligns spectral and molecular representations via diffusion autoencoder (Diff-AE) and contrastive learning, the incorporation of retrieval initialization and similarity filtering during inference, and a specialized NMR encoder with radial basis function (RBF) encoding for chemical shifts, preserving continuity and chemical correlation. Experimental results demonstrate that DiffNMR achieves competitive performance for NMR-based structure elucidation, offering an efficient and robust solution for automated molecular analysis.

physics.chem-ph↗