arXiv subjects

Li Li

Publications and source records attributed to Li Li.

At least 217 records · Page 12Linked to original sources

arXiv2025

Generative AI in Transportation Planning: A Survey

The integration of generative artificial intelligence (GenAI) into transportation planning has the potential to revolutionize tasks such as demand forecasting, infrastructure design, policy evaluation, and traffic simulation. However, there is a critical need for a systematic framework to guide the adoption of GenAI in this interdisciplinary domain. In this survey, we, a multidisciplinary team of researchers spanning computer science and transportation engineering, present the first comprehensive framework for leveraging GenAI in transportation planning. Specifically, we introduce a new taxonomy that categorizes existing applications and methodologies into two perspectives: transportation planning tasks and computational techniques. From the transportation planning perspective, we examine the role of GenAI in automating descriptive, predictive, generative, simulation, and explainable tasks to enhance mobility systems. From the computational perspective, we detail advancements in data preparation, domain-specific fine-tuning, and inference strategies, such as retrieval-augmented generation and zero-shot learning tailored to transportation applications. Additionally, we address critical challenges, including data scarcity, explainability, bias mitigation, and the development of domain-specific evaluation frameworks that align with transportation goals like sustainability, equity, and system efficiency. This survey aims to bridge the gap between traditional transportation planning methodologies and modern AI techniques, fostering collaboration and innovation. By addressing these challenges and opportunities, we seek to inspire future research that ensures ethical, equitable, and impactful use of generative AI in transportation planning.

cs.AI↗

arXiv2025

Neural Video Compression with Context Modulation

Efficient video coding is highly dependent on exploiting the temporal redundancy, which is usually achieved by extracting and leveraging the temporal context in the emerging conditional coding-based neural video codec (NVC). Although the latest NVC has achieved remarkable progress in improving the compression performance, the inherent temporal context propagation mechanism lacks the ability to sufficiently leverage the reference information, limiting further improvement. In this paper, we address the limitation by modulating the temporal context with the reference frame in two steps. Specifically, we first propose the flow orientation to mine the inter-correlation between the reference frame and prediction frame for generating the additional oriented temporal context. Moreover, we introduce the context compensation to leverage the oriented context to modulate the propagated temporal context generated from the propagated reference feature. Through the synergy mechanism and decoupling loss supervision, the irrelevant propagated information can be effectively eliminated to ensure better context modeling. Experimental results demonstrate that our codec achieves on average 22.7% bitrate reduction over the advanced traditional video codec H.266/VVC, and offers an average 10.1% bitrate saving over the previous state-of-the-art NVC DCVC-FM. The code is available at https://github.com/Austin4USTC/DCMVC.

eess.IV↗

arXiv2025

Disentangling Length Bias In Preference Learning Via Response-Conditioned Modeling

Reinforcement Learning from Human Feedback (RLHF) has achieved considerable success in aligning large language models (LLMs) by modeling human preferences with a learnable reward model and employing a reinforcement learning algorithm to maximize the reward model's scores. However, these reward models are susceptible to exploitation through various superficial confounding factors, with length bias emerging as a particularly significant concern. Moreover, while the pronounced impact of length bias on preference modeling suggests that LLMs possess an inherent sensitivity to length perception, our preliminary investigations reveal that fine-tuned LLMs consistently struggle to adhere to explicit length instructions. To address these two limitations, we propose a novel framework wherein the reward model explicitly differentiates between human semantic preferences and response length requirements. Specifically, we introduce a $\textbf{R}$esponse-$\textbf{c}$onditioned $\textbf{B}$radley-$\textbf{T}$erry (Rc-BT) model that enhances the model's capability in length bias mitigating and length instruction following, through training on our augmented dataset. Furthermore, we propose the Rc-RM and Rc-DPO algorithm to leverage the Rc-BT model for reward modeling and direct policy optimization (DPO) of LLMs, simultaneously mitigating length bias and promoting adherence to length instructions. Extensive experiments across various foundational models and datasets demonstrate the effectiveness and generalizability of our approach.

cs.LG↗

arXiv2025

Multi-Level Aware Preference Learning: Enhancing RLHF for Complex Multi-Instruction Tasks

RLHF has emerged as a predominant approach for aligning artificial intelligence systems with human preferences, demonstrating exceptional and measurable efficacy in instruction following tasks; however, it exhibits insufficient compliance capabilities when confronted with complex multi-instruction tasks. Conventional approaches rely heavily on human annotation or more sophisticated large language models, thereby introducing substantial resource expenditure or potential bias concerns. Meanwhile, alternative synthetic methods that augment standard preference datasets often compromise the model's semantic quality. Our research identifies a critical oversight in existing techniques, which predominantly focus on comparing responses while neglecting valuable latent signals embedded within prompt inputs, and which only focus on preference disparities at the intra-sample level, while neglecting to account for the inter-sample level preference differentials that exist among preference data. To leverage these previously neglected indicators, we propose a novel Multi-level Aware Preference Learning (MAPL) framework, capable of enhancing multi-instruction capabilities. Specifically, for any given response in original preference data pairs, we construct varied prompts with a preference relation under different conditions, in order to learn intra-sample level preference disparities. Furthermore, for any given original preference pair, we synthesize multi-instruction preference pairs to capture preference discrepancies at the inter-sample level. Building on the two datasets constructed above, we consequently devise two sophisticated training objective functions. Subsequently, our framework integrates seamlessly into both Reward Modeling and Direct Preference Optimization paradigms. Through rigorous evaluation across multiple benchmarks, we empirically validate the efficacy of our framework.

cs.AI↗

arXiv2025

A Survey on Data-Driven Modeling of Human Drivers' Lane-Changing Decisions

Lane-changing (LC) behavior, a critical yet complex driving maneuver, significantly influences driving safety and traffic dynamics. Traditional analytical LC decision (LCD) models, while effective in specific environments, often oversimplify behavioral heterogeneity and complex interactions, limiting their capacity to capture real LCD. Data-driven approaches address these gaps by leveraging rich empirical data and machine learning to decode latent decision-making patterns, enabling adaptive LCD modeling in dynamic environments. In light of the rapid development of artificial intelligence and the demand for data-driven models oriented towards connected vehicles and autonomous vehicles, this paper presents a comprehensive survey of data-driven LCD models, with a particular focus on human drivers LC decision-making. It systematically reviews the modeling framework, covering data sources and preprocessing, model inputs and outputs, objectives, structures, and validation methods. This survey further discusses the opportunities and challenges faced by data-driven LCD models, including driving safety, uncertainty, as well as the integration and improvement of technical frameworks.

cs.AI↗

arXiv2025

Correctness Coverage Evaluation for Medical Multiple-Choice Question Answering Based on the Enhanced Conformal Prediction Framework

Large language models (LLMs) are increasingly adopted in medical question-answering (QA) scenarios. However, LLMs can generate hallucinations and nonfactual information, undermining their trustworthiness in high-stakes medical tasks. Conformal Prediction (CP) provides a statistically rigorous framework for marginal (average) coverage guarantees but has limited exploration in medical QA. This paper proposes an enhanced CP framework for medical multiple-choice question-answering (MCQA) tasks. By associating the non-conformance score with the frequency score of correct options and leveraging self-consistency, the framework addresses internal model opacity and incorporates a risk control strategy with a monotonic loss function. Evaluated on MedMCQA, MedQA, and MMLU datasets using four off-the-shelf LLMs, the proposed method meets specified error rate guarantees while reducing average prediction set size with increased risk level, offering a promising uncertainty evaluation metric for LLMs.

cs.CL↗

arXiv2025

Augmented Deep Contexts for Spatially Embedded Video Coding

Most Neural Video Codecs (NVCs) only employ temporal references to generate temporal-only contexts and latent prior. These temporal-only NVCs fail to handle large motions or emerging objects due to limited contexts and misaligned latent prior. To relieve the limitations, we propose a Spatially Embedded Video Codec (SEVC), in which the low-resolution video is compressed for spatial references. Firstly, our SEVC leverages both spatial and temporal references to generate augmented motion vectors and hybrid spatial-temporal contexts. Secondly, to address the misalignment issue in latent prior and enrich the prior information, we introduce a spatial-guided latent prior augmented by multiple temporal latent representations. At last, we design a joint spatial-temporal optimization to learn quality-adaptive bit allocation for spatial references, further boosting rate-distortion performance. Experimental results show that our SEVC effectively alleviates the limitations in handling large motions or emerging objects, and also reduces 11.9% more bitrate than the previous state-of-the-art NVC while providing an additional low-resolution bitstream. Our code and model are available at https://github.com/EsakaK/SEVC.

eess.IV↗

arXiv2025

Quantum Acoustics with Superconducting Qubits in the Multimode Transition-Coupling Regime

Hybrid mechanical-superconducting systems for quantum information processing have attracted significant attention due to their potential applications. In such systems, the weak coupling regime, dominated by dissipation, has been extensively studied. The strong coupling regime, where coherent energy exchange exceeds losses, has also been widely explored. However, the transition-coupling regime, which lies between the above two and exhibits rich, unique physics, remains underexplored. In this study, we fabricate a tunable coupling device to investigate the coupling of a superconducting transmon qubit to a seven-mode surface acoustic wave resonator (SAWR), with a particular focus on the transition-coupling regime. Through a series of phonon oscillation experiments and studies in the dispersive regime, we systematically characterize the performance of the SAWR. We then explore the complex dynamics of energy exchange between the qubit and the mechanical modes, highlighting the interplay between dissipation and coherence. Finally, we propose a protocol for qubit readout and fast reset with a multimode mechanical cavity using one mode for readout and another mode for reset. We have demonstrated in simulation that the qubit achieves both fast reset and high coherence performance when the qubit is coupled to the reset mode in the transition-coupling regime.

quant-ph↗

arXiv2025

LoRATK: LoRA Once, Backdoor Everywhere in the Share-and-Play Ecosystem

Finetuning LLMs with LoRA has gained significant popularity due to its simplicity and effectiveness. Often, users may even find pluggable, community-shared LoRAs to enhance their base models for a specific downstream task of interest; enjoying a powerful, efficient, yet customized LLM experience with negligible investment. However, this convenient share-and-play ecosystem also introduces a new attack surface, where attackers can distribute malicious LoRAs to a community eager to try out shared assets. Despite the high-risk potential, no prior art has comprehensively explored LoRA's attack surface under the downstream-enhancing share-and-play context. In this paper, we investigate how backdoors can be injected into task-enhancing LoRAs and examine the mechanisms of such infections. We find that with a simple, efficient, yet specific recipe, a backdoor LoRA can be trained once and then seamlessly merged (in a training-free fashion) with multiple task-enhancing LoRAs, retaining both its malicious backdoor and benign downstream capabilities. This allows attackers to scale the distribution of compromised LoRAs with minimal effort by leveraging the rich pool of existing shared LoRA assets. We note that such merged LoRAs are particularly infectious -- because their malicious intent is cleverly concealed behind improved downstream capabilities, creating a strong incentive for voluntary download -- and dangerous -- because under local deployment, no safety measures exist to intervene when things go wrong. Our work is among the first to study this new threat model of training-free distribution of downstream-capable-yet-backdoor-injected LoRAs, highlighting the urgent need for heightened security awareness in the LoRA ecosystem. Warning: This paper contains offensive content and involves a real-life tragedy.

cs.CR↗

arXiv2025

Extended convexity and smoothness and their applications in deep learning

Classical assumptions like strong convexity and Lipschitz smoothness often fail to capture the nature of deep learning optimization problems, which are typically non-convex and non-smooth, making traditional analyses less applicable. This study aims to elucidate the mechanisms of non-convex optimization in deep learning by extending the conventional notions of strong convexity and Lipschitz smoothness. By leveraging these concepts, we prove that, under the established constraints, the empirical risk minimization problem is equivalent to optimizing the local gradient norm and structural error, which together constitute the upper and lower bounds of the empirical risk. Furthermore, our analysis demonstrates that the stochastic gradient descent (SGD) algorithm can effectively minimize the local gradient norm. Additionally, techniques like skip connections, over-parameterization, and random parameter initialization are shown to help control the structural error. Ultimately, we validate the core conclusions of this paper through extensive experiments. Theoretical analysis and experimental results indicate that our findings provide new insights into the mechanisms of non-convex optimization in deep learning.

cs.LG↗

arXiv2025

Learning Switchable Priors for Neural Image Compression

Neural image compression (NIC) usually adopts a predefined family of probabilistic distributions as the prior of the latent variables, and meanwhile relies on entropy models to estimate the parameters for the probabilistic family. More complex probabilistic distributions may fit the latent variables more accurately, but also incur higher complexity of the entropy models, limiting their practical value. To address this dilemma, we propose a solution to decouple the entropy model complexity from the prior distributions. We use a finite set of trainable priors that correspond to samples of the parametric probabilistic distributions. We train the entropy model to predict the index of the appropriate prior within the set, rather than the specific parameters. Switching between the trained priors further enables us to embrace a skip mode into the prior set, which simply omits a latent variable during the entropy coding. To demonstrate the practical value of our solution, we present a lightweight NIC model, namely FastNIC, together with the learning of switchable priors. FastNIC obtains a better trade-off between compression efficiency and computational complexity for neural image compression. We also implanted the switchable priors into state-of-the-art NIC models and observed improved compression efficiency with a significant reduction of entropy coding complexity.

cs.MM↗

arXiv2025

DropoutGS: Dropping Out Gaussians for Better Sparse-view Rendering

Although 3D Gaussian Splatting (3DGS) has demonstrated promising results in novel view synthesis, its performance degrades dramatically with sparse inputs and generates undesirable artifacts. As the number of training views decreases, the novel view synthesis task degrades to a highly under-determined problem such that existing methods suffer from the notorious overfitting issue. Interestingly, we observe that models with fewer Gaussian primitives exhibit less overfitting under sparse inputs. Inspired by this observation, we propose a Random Dropout Regularization (RDR) to exploit the advantages of low-complexity models to alleviate overfitting. In addition, to remedy the lack of high-frequency details for these models, an Edge-guided Splitting Strategy (ESS) is developed. With these two techniques, our method (termed DropoutGS) provides a simple yet effective plug-in approach to improve the generalization performance of existing 3DGS methods. Extensive experiments show that our DropoutGS produces state-of-the-art performance under sparse views on benchmark datasets including Blender, LLFF, and DTU. The project page is at: https://xuyx55.github.io/DropoutGS/.

cs.CV↗

arXiv2025

Entangling two Rydberg Superatoms via Heralded Storage

Heralded storage of photons is crucial for advancing quantum networks. Previous realizations have primarily relied on single atoms strongly coupled to optical cavities. In this work, we present the experimental realization of heralded storage using a Rydberg superatom, a mesoscopic atomic ensemble operating in the strong blockade regime. In our approach, an input photon is initially stored in the superatom via electromagnetically induced transparency. Subsequently, a second photon is emitted conditioned on the success of the first photon's storage. Due to the collectively enhanced interaction, both the storage and the emission of the herald photon can be rather efficient in principle. As a demonstration of this technique, we use it to entangle two remote Rydberg superatoms. This method obviates the need for an intermediate node, which is commonly employed in traditional interference-based remote entanglement schemes. Our results showcase the potential of performing cavity-QED-like experiments with Rydberg superatoms. This work opens pathways for numerous applications in quantum networks and linear optical quantum computing.

quant-ph↗

arXiv2025

LUIEO: A Lightweight Model for Integrating Underwater Image Enhancement and Object Detection

Underwater optical images inevitably suffer from various degradation factors such as blurring, low contrast, and color distortion, which hinder the accuracy of object detection tasks. Due to the lack of paired underwater/clean images, most research methods adopt a strategy of first enhancing and then detecting, resulting in a lack of feature communication between the two learning tasks. On the other hand, due to the contradiction between the diverse degradation factors of underwater images and the limited number of samples, existing underwater enhancement methods are difficult to effectively enhance degraded images of unknown water bodies, thereby limiting the improvement of object detection accuracy. Therefore, most underwater target detection results are still displayed on degraded images, making it difficult to visually judge the correctness of the detection results. To address the above issues, this paper proposes a multi-task learning method that simultaneously enhances underwater images and improves detection accuracy. Compared with single-task learning, the integrated model allows for the dynamic adjustment of information communication and sharing between different tasks. Due to the fact that real underwater images can only provide annotated object labels, this paper introduces physical constraints to ensure that object detection tasks do not interfere with image enhancement tasks. Therefore, this article introduces a physical module to decompose underwater images into clean images, background light, and transmission images and uses a physical model to calculate underwater images for self-supervision. Numerical experiments demonstrate that the proposed model achieves satisfactory results in visual performance, object detection accuracy, and detection efficiency compared to state-of-the-art comparative methods.

cs.CV↗

arXiv2025

Driving-RAG: Driving Scenarios Embedding, Search, and RAG Applications

Driving scenario data play an increasingly vital role in the development of intelligent vehicles and autonomous driving. Accurate and efficient scenario data search is critical for both online vehicle decision-making and planning, and offline scenario generation and simulations, as it allows for leveraging the scenario experiences to improve the overall performance. Especially with the application of large language models (LLMs) and Retrieval-Augmented-Generation (RAG) systems in autonomous driving, urgent requirements are put forward. In this paper, we introduce the Driving-RAG framework to address the challenges of efficient scenario data embedding, search, and applications for RAG systems. Our embedding model aligns fundamental scenario information and scenario distance metrics in the vector space. The typical scenario sampling method combined with hierarchical navigable small world can perform efficient scenario vector search to achieve high efficiency without sacrificing accuracy. In addition, the reorganization mechanism by graph knowledge enhances the relevance to the prompt scenarios and augment LLM generation. We demonstrate the effectiveness of the proposed framework on typical trajectory planning task for complex interactive scenarios such as ramps and intersections, showcasing its advantages for RAG applications.

cs.RO↗

arXiv2025

Prethermalization by Random Multipolar Driving on a 78-Qubit Superconducting Processor

Time-dependent drives hold the promise of realizing non-equilibrium many-body phenomena that are absent in undriven systems. Yet, drive-induced heating normally destabilizes the systems, which can be parametrically suppressed in the high-frequency regime by using periodic (Floquet) drives. It remains largely unknown to what extent highly controllable quantum simulators can suppress heating in non-periodically driven systems. Using the 78-qubit superconducting quantum processor, Chuang-tzu 2.0, we report the experimental observation of long-lived prethermal phases in many-body systems with tunable heating rates, driven by structured random protocols, characterized by $n$-multipolar temporal correlations. By measuring both the particle imbalance and subsystem entanglement entropy, we monitor the entire heating process over 1,000 driving cycles and observe the existence of the prethermal plateau. The prethermal lifetime is `doubly tunable': one way by driving frequency, the other by multipolar order; it grows algebraically with the frequency with the universal scaling exponent $2n{+}1$. Using quantum state tomography on different subsystems, we demonstrate a non-uniform spatial entanglement distribution and observe a crossover from area-law to volume-law entanglement scaling. With 78 qubits and 137 couplers in a 2D configuration, the entire far-from-equilibrium heating dynamics are beyond the reach of simulation using tensor-network numerical techniques. Our work highlights superconducting quantum processors as a powerful platform for exploring universal scaling laws and non-equilibrium phases of matter in driven systems in regimes where classical simulation faces formidable challenges.

quant-ph↗

arXiv2025

Is Journal Citation Indicator a good metric for Art & Humanities Journals currently?

Probably Not. Journal Citation Indicator (JCI) was introduced to address the limitations of traditional metrics like the Journal Impact Factor (JIF), particularly its inability to normalize citation impact across different disciplines. This study reveals that JCI faces significant challenges in field normalization for Art & Humanities journals, as evidenced by much lower correlations with a more granular, paper-level metric, CNCI-CT. A detailed analysis of Architecture journals highlights how journal-level misclassification and the interdisciplinary nature of content exacerbate these issues, leading to less reliable evaluations. We recommend improving journal classification systems or adopting paper-level normalization methods, potentially supported by advanced AI techniques, to enhance the accuracy and effectiveness of JCI for Art & Humanities disciplines.

cs.DL↗

arXiv2025

Towards Understanding the Optimization Mechanisms in Deep Learning

In this paper, we adopt a probability distribution estimation perspective to explore the optimization mechanisms of supervised classification using deep neural networks. We demonstrate that, when employing the Fenchel-Young loss, despite the non-convex nature of the fitting error with respect to the model's parameters, global optimal solutions can be approximated by simultaneously minimizing both the gradient norm and the structural error. The former can be controlled through gradient descent algorithms. For the latter, we prove that it can be managed by increasing the number of parameters and ensuring parameter independence, thereby providing theoretical insights into mechanisms such as over-parameterization and random initialization. Ultimately, the paper validates the key conclusions of the proposed method through empirical results, illustrating its practical effectiveness.

cs.LG↗