arXiv subjects

Lu Liu

Publications and source records attributed to Lu Liu.

At least 91 records · Page 5Linked to original sources

arXiv2025

Control of Marine Robots in the Era of Data-Driven Intelligence

The control of marine robots has long relied on model-based methods grounded in classical and modern control theory. However, the nonlinearity and uncertainties inherent in robot dynamics, coupled with the complexity of marine environments, have revealed the limitations of conventional control methods. The rapid evolution of machine learning has opened new avenues for incorporating data-driven intelligence into control strategies, prompting a paradigm shift in the control of marine robots. This paper provides a review of recent progress in marine robot control through the lens of this emerging paradigm. The review covers both individual and cooperative marine robotic systems, highlighting notable achievements in data-driven control of marine robots and summarizing open-source resources that support the development and validation of advanced control methods. Finally, several future perspectives are outlined to guide research toward achieving high-level autonomy for marine robots in real-world applications. This paper aims to serve as a roadmap toward the next-generation control framework of marine robots in the era of data-driven intelligence.

cs.RO↗

arXiv2025

NTIRE 2025 XGC Quality Assessment Challenge: Methods and Results

This paper reports on the NTIRE 2025 XGC Quality Assessment Challenge, which will be held in conjunction with the New Trends in Image Restoration and Enhancement Workshop (NTIRE) at CVPR 2025. This challenge is to address a major challenge in the field of video and talking head processing. The challenge is divided into three tracks, including user generated video, AI generated video and talking head. The user-generated video track uses the FineVD-GC, which contains 6,284 user generated videos. The user-generated video track has a total of 125 registered participants. A total of 242 submissions are received in the development phase, and 136 submissions are received in the test phase. Finally, 5 participating teams submitted their models and fact sheets. The AI generated video track uses the Q-Eval-Video, which contains 34,029 AI-Generated Videos (AIGVs) generated by 11 popular Text-to-Video (T2V) models. A total of 133 participants have registered in this track. A total of 396 submissions are received in the development phase, and 226 submissions are received in the test phase. Finally, 6 participating teams submitted their models and fact sheets. The talking head track uses the THQA-NTIRE, which contains 12,247 2D and 3D talking heads. A total of 89 participants have registered in this track. A total of 225 submissions are received in the development phase, and 118 submissions are received in the test phase. Finally, 8 participating teams submitted their models and fact sheets. Each participating team in every track has proposed a method that outperforms the baseline, which has contributed to the development of fields in three tracks.

cs.CV↗

arXiv2025

NTIRE 2025 challenge on Text to Image Generation Model Quality Assessment

This paper reports on the NTIRE 2025 challenge on Text to Image (T2I) generation model quality assessment, which will be held in conjunction with the New Trends in Image Restoration and Enhancement Workshop (NTIRE) at CVPR 2025. The aim of this challenge is to address the fine-grained quality assessment of text-to-image generation models. This challenge evaluates text-to-image models from two aspects: image-text alignment and image structural distortion detection, and is divided into the alignment track and the structural track. The alignment track uses the EvalMuse-40K, which contains around 40K AI-Generated Images (AIGIs) generated by 20 popular generative models. The alignment track has a total of 371 registered participants. A total of 1,883 submissions are received in the development phase, and 507 submissions are received in the test phase. Finally, 12 participating teams submitted their models and fact sheets. The structure track uses the EvalMuse-Structure, which contains 10,000 AI-Generated Images (AIGIs) with corresponding structural distortion mask. A total of 211 participants have registered in the structure track. A total of 1155 submissions are received in the development phase, and 487 submissions are received in the test phase. Finally, 8 participating teams submitted their models and fact sheets. Almost all methods have achieved better results than baseline methods, and the winning methods in both tracks have demonstrated superior prediction performance on T2I model quality assessment.

cs.CV↗

arXiv2025

ReCopilot: Reverse Engineering Copilot in Binary Analysis

Binary analysis plays a pivotal role in security domains such as malware detection and vulnerability discovery, yet it remains labor-intensive and heavily reliant on expert knowledge. General-purpose large language models (LLMs) perform well in programming analysis on source code, while binaryspecific LLMs are underexplored. In this work, we present ReCopilot, an expert LLM designed for binary analysis tasks. ReCopilot integrates binary code knowledge through a meticulously constructed dataset, encompassing continue pretraining (CPT), supervised fine-tuning (SFT), and direct preference optimization (DPO) stages. It leverages variable data flow and call graph to enhance context awareness and employs test-time scaling to improve reasoning capabilities. Evaluations on a comprehensive binary analysis benchmark demonstrate that ReCopilot achieves state-of-the-art performance in tasks such as function name recovery and variable type inference on the decompiled pseudo code, outperforming both existing tools and LLMs by 13%. Our findings highlight the effectiveness of domain-specific training and context enhancement, while also revealing challenges in building super long chain-of-thought. ReCopilot represents a significant step toward automating binary analysis with interpretable and scalable AI assistance in this domain.

cs.CR↗

arXiv2025

Reflected stochastic recursive control problems with jumps: dynamic programming and stochastic verification theorems

This paper mainly investigates reflected stochastic recursive control problems governed by jump-diffusion dynamics. The system's state evolution is described by a stochastic differential equation driven by both Brownian motion and Poisson random measures, while the recursive cost functional is formulated via the solution process Y of a reflected backward stochastic differential equation driven by the same dual stochastic sources. By establishing the dynamic programming principle, we provide the probabilistic interpretation of an obstacle problem for partial integro-differential equations of Hamilton-Jacobi-Bellman type in the viscosity solution sense through our control problem's value function. Furthermore, the value function is proved to inherit the semi-concavity and joint Lipschitz continuity in state and time coordinates, which play key roles in deriving stochastic verification theorems of control problem within the framework of viscosity solutions. We remark that some restrictions in previous study are eliminated, such as the frozen of the reflected processes in time and state, and the independence of the driver from diffusion variables.

math.OC↗

arXiv2025

A Multi-Agent Rollout Approach for Highway Bottleneck Decongestion in Mixed Autonomy

The integration of autonomous vehicles (AVs) into the existing transportation infrastructure offers a promising solution to alleviate congestion and enhance mobility. This research explores a novel approach to traffic optimization by employing a multi-agent rollout approach within a mixed autonomy environment. The study concentrates on coordinating the speed of human-driven vehicles by longitudinally controlling AVs, aiming to dynamically optimize traffic flow and alleviate congestion at highway bottlenecks in real-time. We model the problem as a decentralized partially observable Markov decision process (Dec-POMDP) and propose an improved multi-agent rollout algorithm. By employing agent-by-agent policy iterations, our approach implicitly considers cooperation among multiple agents and seamlessly adapts to complex scenarios where the number of agents dynamically varies. Validated in a real-world network with varying AV penetration rates and traffic flow, the simulations demonstrate that the multi-agent rollout algorithm significantly enhances performance, reducing average travel time on bottleneck segments by 9.42% with a 10% AV penetration rate.

cs.MA↗

arXiv2025

FineVQ: Fine-Grained User Generated Content Video Quality Assessment

The rapid growth of user-generated content (UGC) videos has produced an urgent need for effective video quality assessment (VQA) algorithms to monitor video quality and guide optimization and recommendation procedures. However, current VQA models generally only give an overall rating for a UGC video, which lacks fine-grained labels for serving video processing and recommendation applications. To address the challenges and promote the development of UGC videos, we establish the first large-scale Fine-grained Video quality assessment Database, termed FineVD, which comprises 6104 UGC videos with fine-grained quality scores and descriptions across multiple dimensions. Based on this database, we propose a Fine-grained Video Quality assessment (FineVQ) model to learn the fine-grained quality of UGC videos, with the capabilities of quality rating, quality scoring, and quality attribution. Extensive experimental results demonstrate that our proposed FineVQ can produce fine-grained video-quality results and achieve state-of-the-art performance on FineVD and other commonly used UGC-VQA datasets.

cs.CV↗

arXiv2025

Facial Foundational Model Advances Early Warning of Coronary Artery Disease from Live Videos with DigitalShadow

Global population aging presents increasing challenges to healthcare systems, with coronary artery disease (CAD) responsible for approximately 17.8 million deaths annually, making it a leading cause of global mortality. As CAD is largely preventable, early detection and proactive management are essential. In this work, we introduce DigitalShadow, an advanced early warning system for CAD, powered by a fine-tuned facial foundation model. The system is pre-trained on 21 million facial images and subsequently fine-tuned into LiveCAD, a specialized CAD risk assessment model trained on 7,004 facial images from 1,751 subjects across four hospitals in China. DigitalShadow functions passively and contactlessly, extracting facial features from live video streams without requiring active user engagement. Integrated with a personalized database, it generates natural language risk reports and individualized health recommendations. With privacy as a core design principle, DigitalShadow supports local deployment to ensure secure handling of user data.

cs.CV↗

arXiv2025

Coplanar order induced by emergent frustration

Traditional frustration arises from the conflict between the spin alignments due to the geometry or the nature of the interactions. Here, we demonstrate a novel form of frustration, dubbed ``emergent frustration'', which is induced by the symmetry that emerges at the phase transition point of a quantum spin model devoid of geometric frustration. We study the two-dimensional bipartite chequerboard $J$-$Q$ model, which hosts the antiferromagnetic (AFM) state to the plaquette-singlet solid state (PSS) phase transition detected in the Shastry-Sutherland compound SrCu$_2({\rm BO}_3)_2$. By analyzing the scaling behavior of the Rényi entanglement entropy with smooth boundaries at the transition point, we observe an unexpected scaling behavior, which indicates that the number of Goldstone modes is five. We explain this by proposing a novel scenario in which the system is described by an effective quantum rotor Hamiltonian with a three-sublattice geometry that frustrates collinear order while supporting coplanar order. Such a three-sublattice geometry arises from the emergent symmetry of coexisting orders, which may also occur at the AFM-PSS transition point of SrCu$_2({\rm BO}_3)_2$. Therefore, experimental investigations are warranted.

cond-mat.str-el↗

arXiv2025

DropletVideo: A Dataset and Approach to Explore Integral Spatio-Temporal Consistent Video Generation

Spatio-temporal consistency is a critical research topic in video generation. A qualified generated video segment must ensure plot plausibility and coherence while maintaining visual consistency of objects and scenes across varying viewpoints. Prior research, especially in open-source projects, primarily focuses on either temporal or spatial consistency, or their basic combination, such as appending a description of a camera movement after a prompt without constraining the outcomes of this movement. However, camera movement may introduce new objects to the scene or eliminate existing ones, thereby overlaying and affecting the preceding narrative. Especially in videos with numerous camera movements, the interplay between multiple plots becomes increasingly complex. This paper introduces and examines integral spatio-temporal consistency, considering the synergy between plot progression and camera techniques, and the long-term impact of prior content on subsequent generation. Our research encompasses dataset construction through to the development of the model. Initially, we constructed a DropletVideo-10M dataset, which comprises 10 million videos featuring dynamic camera motion and object actions. Each video is annotated with an average caption of 206 words, detailing various camera movements and plot developments. Following this, we developed and trained the DropletVideo model, which excels in preserving spatio-temporal coherence during video generation. The DropletVideo dataset and model are accessible at https://dropletx.github.io.

cs.CV↗

arXiv2025

SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training

Large Language Models (LLMs) have demonstrated exceptional performance across diverse tasks, yet their training remains highly resource-intensive and susceptible to critical challenges such as training instability. A predominant source of this instability stems from gradient and loss spikes, which disrupt the learning process, often leading to costly interventions like checkpoint recovery and experiment restarts, further amplifying inefficiencies. This paper presents a comprehensive investigation into gradient spikes observed during LLM training, revealing their prevalence across multiple architectures and datasets. Our analysis shows that these spikes can be up to $1000\times$ larger than typical gradients, substantially deteriorating model performance. To address this issue, we propose Spike-Aware Adam with Momentum Reset SPAM, a novel optimizer designed to counteract gradient spikes through momentum reset and spike-aware gradient clipping. Extensive experiments, including both pre-training and fine-tuning, demonstrate that SPAM consistently surpasses Adam and its variants across various tasks, including (1) LLM pre-training from 60M to 1B, (2) 4-bit LLM pre-training,(3) reinforcement learning, and (4) Time Series Forecasting. Additionally, SPAM facilitates memory-efficient training by enabling sparse momentum, where only a subset of momentum terms are maintained and updated. When operating under memory constraints, SPAM outperforms state-of-the-art memory-efficient optimizers such as GaLore and Adam-Mini. Our work underscores the importance of mitigating gradient spikes in LLM training and introduces an effective optimization strategy that enhances both training stability and resource efficiency at scale. Code is available at https://github.com/TianjinYellow/SPAM-Optimizer.git

cs.LG↗

arXiv2025

Natural van der Waals canalization lens for non-destructive nanoelectronic circuit imaging and inspection

Optical inspection has long served as a cornerstone non-destructive method in semiconductor wafer manufacturing, particularly for surface and defect analysis. However, conventional techniques such as bright-field and dark-field scattering optics face significant limitations, including insufficient resolution and the inability to penetrate and detect buried structures. Atomic force microscopy (AFM), while offering higher resolution and precise surface characterization, is constrained by slow speed, limited to surface-level imaging, and incapable of resolving subsurface features. Here, we propose an approach that integrates the strengths of dark-field scattering optics and AFM by leveraging a van der Waals (vdW) canalization lens based on natural biaxial α-MoO3 crystals. This method enables ultrahigh-resolution subwavelength imaging with the ability to visualize both surface and buried structures, achieving a spatial resolution of 15 nm and grating pitch detection down to 100 nm. The underlying mechanism relies on the unique anisotropic properties of α-MoO3, where its atomic-scale unit cells and biaxial symmetry facilitate the diffraction-free propagation of both evanescent and propagating waves via a flat-band canalization regime. Unlike metamaterial-based superlenses and hyperlenses, which suffer from high plasmonic losses, fabrication imperfections, and uniaxial constraints, α-MoO3 provides robust and aberration-free imaging in multiple directions. We successfully applied this approach to high-resolution inspection of buried nanoscale electronic circuits, offering unprecedented capabilities essential for next-generation semiconductor manufacturing.

physics.optics↗

arXiv2025

Causal Learning for Heterogeneous Subgroups Based on Nonlinear Causal Kernel Clustering

Due to the challenge posed by multi-source and heterogeneous data collected from diverse environments, causal relationships among features can exhibit variations influenced by different time spans, regions, or strategies. This diversity makes a single causal model inadequate for accurately representing complex causal relationships in all observational data, a crucial consideration in causal learning. To address this challenge, the nonlinear Causal Kernel Clustering method is introduced for heterogeneous subgroup causal learning, highlighting variations in causal relationships across diverse subgroups. The main component for clustering heterogeneous subgroups lies in the construction of the $u$-centered sample mapping function with the property of unbiased estimation, which assesses the differences in potential nonlinear causal relationships in various samples and supported by causal identifiability theory. Experimental results indicate that the method performs well in identifying heterogeneous subgroups and enhancing causal learning, leading to a reduction in prediction error.

cs.LG↗

arXiv2024

Vision-based Tactile Image Generation via Contact Condition-guided Diffusion Model

Vision-based tactile sensors, through high-resolution optical measurements, can effectively perceive the geometric shape of objects and the force information during the contact process, thus helping robots acquire higher-dimensional tactile data. Vision-based tactile sensor simulation supports the acquisition and understanding of tactile information without physical sensors by accurately capturing and analyzing contact behavior and physical properties. However, the complexity of contact dynamics and lighting modeling limits the accurate reproduction of real sensor responses in simulations, making it difficult to meet the needs of different sensor setups and affecting the reliability and effectiveness of strategy transfer to practical applications. In this letter, we propose a contact-condition guided diffusion model that maps RGB images of objects and contact force data to high-fidelity, detail-rich vision-based tactile sensor images. Evaluations show that the three-channel tactile images generated by this method achieve a 60.58% reduction in mean squared error and a 38.1% reduction in marker displacement error compared to existing approaches based on lighting model and mechanical model, validating the effectiveness of our approach. The method is successfully applied to various types of tactile vision sensors and can effectively generate corresponding tactile images under complex loads. Additionally, it demonstrates outstanding reconstruction of fine texture features of objects in a Montessori tactile board texture generation task.

cs.RO↗

arXiv2024

Observation of quantum information collapse-and-revival in a strongly-interacting Rydberg atom array

Interactions of isolated quantum many-body systems typically scramble local information into the entire system and make it unrecoverable. Ergodicity-breaking systems possess the potential to exhibit fundamentally different information scrambling dynamics beyond this paradigm. For many-body localized systems with strong ergodicity breaking, local transport vanishes and information scrambles logarithmically slowly. Whereas in Rydberg atom arrays, local qubit flips induce dynamical retardation on surrounding qubits through the Rydberg blockade effect, giving rise to quantum many-body scars that weakly break ergodicity, and resulting in the predicted unconventional quantum information spreading behaviours. Here, we present the first measurements of out-of-time-ordered correlators and Holevo information in a Rydberg atom array, enabling us to precisely track quantum information scrambling and transport dynamics. By leveraging these tools, we observe a novel spatio-temporal collapse-and-revival behaviour of quantum information, which differs from both typical chaotic and many-body localized systems. Our experiment sheds light on the unique information dynamics in many-body systems with kinetic constraints, and demonstrates an effective digital-analogue approach to coherently reverse time evolution and steer information propagation in near-term quantum devices.

quant-ph↗

arXiv2024

Quantum spin Hall effect protected by spin U(1) quasisymmetry

Quantum spin Hall (QSH) effect, where electrons with opposite spin channels are deflected to opposite sides of a two-dimensional system with a quantized conductance, was believed to be characterized by a nontrivial topological index $Z_{2}$. However, spin mixing effects in realistic materials often lead to deviation of the spin Hall conductance from exact quantization. In this Letter, we present a universal symmetry indicator for diagnosing QSH effect in realistic materials, termed spin U(1) quasisymmetry. Such a symmetry eliminates the first-order spin-mixing perturbation and thus protects the near-quantization of SHC, applicable to time-reversal-preserved cases with either $Z_{2}=1$ or $Z_{2}=0$, as well as time-reversal-broken scenarios. We propose that spin U(1) quasisymmetry is hidden in the subspace spanned by the doublets with unquenched orbital momentum and emerges when SOC is present, which can be realized in 19 crystallographic point groups. Particularly, we identify a previous overlooked even spin Chern phase with a trivial $Z_{2}$ index as an ideal platform for achieving a near-double-quantized SHC, as exemplified by twisted bilayer transition metal dichalcogenides and monolayer RuBr$_{3}$. Our work offers a new perspective for understanding QSH effect and significantly expands the material pool for the screening of exemplary material candidates.

cond-mat.mtrl-sci↗

arXiv2024

Symbol Level Precoding for Systems with Improper Gaussian Interference

This paper focuses on precoding design in multi-antenna systems with improper Gaussian interference (IGI), characterized by correlated real and imaginary parts. We first study block level precoding (BLP) and symbol level precoding (SLP) assuming the receivers apply a pre-whitening filter to decorrelate and normalize the IGI. We then shift to the scenario where the base station (BS) incorporates the IGI statistics in the SLP design, which allows the receivers to employ a standard detection algorithm without pre-whitenting. Finally we address the case where the channel and statistics of the IGI are unknown, and we formulate robust BLP and SLP designs that minimize the worst case performance in such settings. Interestingly, we show that for BLP, the worst-case IGI is in fact proper, while for SLP the worst case occurs when the interference signal is maximally improper, with fully correlated real and imaginary parts. Numerical results reveal the superior performance of SLP in terms of symbol error rate (SER) and energy efficiency (EE), especially for the case where there is uncertainty in the non-circularity of the jammer.

eess.SP↗

arXiv2024

An Empirical Study on Information Extraction using Large Language Models

Human-like large language models (LLMs), especially the most powerful and popular ones in OpenAI's GPT family, have proven to be very helpful for many natural language processing (NLP) related tasks. Therefore, various attempts have been made to apply LLMs to information extraction (IE), which is a fundamental NLP task that involves extracting information from unstructured plain text. To demonstrate the latest representative progress in LLMs' information extraction ability, we assess the information extraction ability of GPT-4 (the latest version of GPT at the time of writing this paper) from four perspectives: Performance, Evaluation Criteria, Robustness, and Error Types. Our results suggest a visible performance gap between GPT-4 and state-of-the-art (SOTA) IE methods. To alleviate this problem, considering the LLMs' human-like characteristics, we propose and analyze the effects of a series of simple prompt-based methods, which can be generalized to other LLMs and NLP tasks. Rich experiments show our methods' effectiveness and some of their remaining issues in improving GPT-4's information extraction ability.

cs.CL↗