arXiv subjects

Jiaqi Liu

Publications and source records attributed to Jiaqi Liu.

At least 163 records · Page 9Linked to original sources

arXiv2024

MAPPO-PIS: A Multi-Agent Proximal Policy Optimization Method with Prior Intent Sharing for CAVs' Cooperative Decision-Making

Vehicle-to-Vehicle (V2V) technologies have great potential for enhancing traffic flow efficiency and safety. However, cooperative decision-making in multi-agent systems, particularly in complex human-machine mixed merging areas, remains challenging for connected and autonomous vehicles (CAVs). Intent sharing, a key aspect of human coordination, may offer an effective solution to these decision-making problems, but its application in CAVs is under-explored. This paper presents an intent-sharing-based cooperative method, the Multi-Agent Proximal Policy Optimization with Prior Intent Sharing (MAPPO-PIS), which models the CAV cooperative decision-making problem as a Multi-Agent Reinforcement Learning (MARL) problem. It involves training and updating the agents' policies through the integration of two key modules: the Intention Generator Module (IGM) and the Safety Enhanced Module (SEM). The IGM is specifically crafted to generate and disseminate CAVs' intended trajectories spanning multiple future time-steps. On the other hand, the SEM serves a crucial role in assessing the safety of the decisions made and rectifying them if necessary. Merging area with human-machine mixed traffic flow is selected to validate our method. Results show that MAPPO-PIS significantly improves decision-making performance in multi-agent systems, surpassing state-of-the-art baselines in safety, efficiency, and overall traffic system performance. The code and video demo can be found at: \url{https://github.com/CCCC1dhcgd/A-MAPPO-PIS}.

cs.RO↗

arXiv2024

Active Generation for Image Classification

Recently, the growing capabilities of deep generative models have underscored their potential in enhancing image classification accuracy. However, existing methods often demand the generation of a disproportionately large number of images compared to the original dataset, while having only marginal improvements in accuracy. This computationally expensive and time-consuming process hampers the practicality of such approaches. In this paper, we propose to address the efficiency of image generation by focusing on the specific needs and characteristics of the model. With a central tenet of active learning, our method, named ActGen, takes a training-aware approach to image generation. It aims to create images akin to the challenging or misclassified samples encountered by the current model and incorporates these generated images into the training set to augment model performance. ActGen introduces an attentive image guidance technique, using real images as guides during the denoising process of a diffusion model. The model's attention on class prompt is leveraged to ensure the preservation of similar foreground object while diversifying the background. Furthermore, we introduce a gradient-based generation guidance method, which employs two losses to generate more challenging samples and prevent the generated images from being too similar to previously generated ones. Experimental results on the CIFAR and ImageNet datasets demonstrate that our method achieves better performance with a significantly reduced number of generated images. Code is available at https://github.com/hunto/ActGen.

cs.CV↗

arXiv2024

Partial mass dynamics of the defocussing nonlinear Schrödinger equation

We study the long time dynamics of the defocussing NLS equation. Compared with previous literature, we revisit the direct and inverse scattering map to obtain asymptotics in some weighted energy space that requires less restrictive decay and regularity assumptions. The main result is derived from an application of uniform resolvent bound and an approximation argument in the spirit of Riemann-Lebesgue lemma. As a consequence, our result depicts the long time dynamics of the zeros of the solution to the defocussing NLS equation.

math.AP↗

arXiv2024

Cohomology theory of Rota-Baxter family BiHom-$Ω$-associative algebras

In this paper, we first introduce the concept of Rota-Baxter family BiHom-$Ω$-associative algebras, then we define the cochain complex of BiHom-$Ω$-associative algebras and verify it via Maurer-Cartan methods. Next, we further introduce and study the cohomology theory of Rota-Baxter family BiHom-$Ω$-associative algebras of weight $λ$ and show that this cohomology controls the corresponding deformations. Finally, we study abelian extensions of Rota-Baxter family BiHom-$Ω$-associative algebras in terms of the second cohomology group.

math.RA↗

arXiv2024

Training-free Composite Scene Generation for Layout-to-Image Synthesis

Recent breakthroughs in text-to-image diffusion models have significantly advanced the generation of high-fidelity, photo-realistic images from textual descriptions. Yet, these models often struggle with interpreting spatial arrangements from text, hindering their ability to produce images with precise spatial configurations. To bridge this gap, layout-to-image generation has emerged as a promising direction. However, training-based approaches are limited by the need for extensively annotated datasets, leading to high data acquisition costs and a constrained conceptual scope. Conversely, training-free methods face challenges in accurately locating and generating semantically similar objects within complex compositions. This paper introduces a novel training-free approach designed to overcome adversarial semantic intersections during the diffusion conditioning phase. By refining intra-token loss with selective sampling and enhancing the diffusion process with attention redistribution, we propose two innovative constraints: 1) an inter-token constraint that resolves token conflicts to ensure accurate concept synthesis; and 2) a self-attention constraint that improves pixel-to-pixel relationships. Our evaluations confirm the effectiveness of leveraging layout information for guiding the diffusion process, generating content-rich images with enhanced fidelity and complexity. Code is available at https://github.com/Papple-F/csg.git.

cs.CV↗

arXiv2024

A Decision-Making GPT Model Augmented with Entropy Regularization for Autonomous Vehicles

In the domain of autonomous vehicles (AVs), decision-making is a critical factor that significantly influences the efficacy of autonomous navigation. As the field progresses, the enhancement of decision-making capabilities in complex environments has become a central area of research within data-driven methodologies. Despite notable advances, existing learning-based decision-making strategies in autonomous vehicles continue to reveal opportunities for further refinement, particularly in the articulation of policies and the assurance of safety. In this study, the decision-making challenges associated with autonomous vehicles are conceptualized through the framework of the Constrained Markov Decision Process (CMDP) and approached as a sequence modeling problem. Utilizing the Generative Pre-trained Transformer (GPT), we introduce a novel decision-making model tailored for AVs, which incorporates entropy regularization techniques to bolster exploration and enhance safety performance. Comprehensive experiments conducted across various scenarios affirm that our approach surpasses several established baseline methods, particularly in terms of safety and overall efficacy.

cs.RO↗

arXiv2024

ERASER: Machine Unlearning in MLaaS via an Inference Serving-Aware Approach

Over the past years, Machine Learning-as-a-Service (MLaaS) has received a surging demand for supporting Machine Learning-driven services to offer revolutionized user experience across diverse application areas. MLaaS provides inference service with low inference latency based on an ML model trained using a dataset collected from numerous individual data owners. Recently, for the sake of data owners' privacy and to comply with the "right to be forgotten (RTBF)" as enacted by data protection legislation, many machine unlearning methods have been proposed to remove data owners' data from trained models upon their unlearning requests. However, despite their promising efficiency, almost all existing machine unlearning methods handle unlearning requests independently from inference requests, which unfortunately introduces a new security issue of inference service obsolescence and a privacy vulnerability of undesirable exposure for machine unlearning in MLaaS. In this paper, we propose the ERASER framework for machinE unleaRning in MLaAS via an inferencE seRving-aware approach. ERASER strategically choose appropriate unlearning execution timing to address the inference service obsolescence issue. A novel inference consistency certification mechanism is proposed to avoid the violation of RTBF principle caused by postponed unlearning executions, thereby mitigating the undesirable exposure vulnerability. ERASER offers three groups of design choices to allow for tailor-made variants that best suit the specific environments and preferences of various MLaaS systems. Extensive empirical evaluations across various settings confirm ERASER's effectiveness, e.g., it can effectively save up to 99% of inference latency and 31% of computation overhead over the inference-oblivion baseline.

cs.CR↗

arXiv2024

Exact complex mobility edges and flagellate spectra for non-Hermitian quasicrystals with exponential hoppings

We propose a class of general non-Hermitian quasiperiodic lattice models with exponential hoppings and analytically determine the genuine complex mobility edges by solving its dual counterpart exactly utilizing Avila's global theory. Our analytical formula unveils that the complex mobility edges usually form a loop structure in the complex energy plane. By shifting the eigenenergy a constant $t$, the complex mobility edges of the family of models with different hopping parameter $t$ can be described by a unified formula, formally independent of $t$. By scanning the hopping parameter, we demonstrate the existence of a type of intriguing flagellate-like spectra in complex energy plane, in which the localized states and extended states are well separated by the complex mobility edges. Our result provides a firm ground for understanding the complex mobility edges in non-Hermitian quasiperiodic lattices.

cond-mat.dis-nn↗

arXiv2024

Phase transition of the consistent maximal displacement of branching Brownian motion

Consider branching Brownian motion in which we begin with one particle at the origin, particles independently move according to Brownian motion, and particles split into two at rate one. It is well-known that the right-most particle at time $t$ will be near $\sqrt{2} t$. Roberts considered the so-called consistent maximal displacement and showed that with high probability, there will be a particle at time $t$ whose ancestors stayed within a distance $ct^{1/3}$ of the curve $s \mapsto \sqrt{2} s$ for all $s \in [0, t]$, where $c = (3 π^2)^{1/3}/\sqrt{2}$. We consider the question of how close the trajectory of a particle can stay to the curve $s \mapsto (\sqrt{2} + \varepsilon) s$ for all $s \in [0, t]$, where $\varepsilon> 0$ is small. We find that there is a phase transition, with the behavior changing when $t$ is of the order $\varepsilon^{-3/2}$. This result allows us to determine, for branching Brownian motion in which particles have a drift to the left of $\sqrt{2} + \varepsilon$ and are killed at the origin, the position at which a particle needs to begin at time zero for there to be a high probability that the process avoids extinction until time $t$.

math.PR↗

arXiv2024

MedFLIP: Medical Vision-and-Language Self-supervised Fast Pre-Training with Masked Autoencoder

Within the domain of medical analysis, extensive research has explored the potential of mutual learning between Masked Autoencoders(MAEs) and multimodal data. However, the impact of MAEs on intermodality remains a key challenge. We introduce MedFLIP, a Fast Language-Image Pre-training method for Medical analysis. We explore MAEs for zero-shot learning with crossed domains, which enhances the model's ability to learn from limited data, a common scenario in medical diagnostics. We verify that masking an image does not affect inter-modal learning. Furthermore, we propose the SVD loss to enhance the representation learning for characteristics of medical images, aiming to improve classification accuracy by leveraging the structural intricacies of such data. Our theory posits that masking encourages semantic preservation, robust feature extraction, regularization, domain adaptation, and invariance learning. Lastly, we validate using language will improve the zero-shot performance for the medical image analysis. MedFLIP's scaling of the masking process marks an advancement in the field, offering a pathway to rapid and precise medical image analysis without the traditional computational bottlenecks. Through experiments and validation, MedFLIP demonstrates efficient performance improvements, helps for future research and application in medical diagnostics.

eess.IV↗

arXiv2024

RGB-T Object Detection via Group Shuffled Multi-receptive Attention and Multi-modal Supervision

Multispectral object detection, utilizing both visible (RGB) and thermal infrared (T) modals, has garnered significant attention for its robust performance across diverse weather and lighting conditions. However, effectively exploiting the complementarity between RGB-T modals while maintaining efficiency remains a critical challenge. In this paper, a very simple Group Shuffled Multi-receptive Attention (GSMA) module is proposed to extract and combine multi-scale RGB and thermal features. Then, the extracted multi-modal features are directly integrated with a multi-level path aggregation neck, which significantly improves the fusion effect and efficiency. Meanwhile, multi-modal object detection often adopts union annotations for both modals. This kind of supervision is not sufficient and unfair, since objects observed in one modal may not be seen in the other modal. To solve this issue, Multi-modal Supervision (MS) is proposed to sufficiently supervise RGB-T object detection. Comprehensive experiments on two challenging benchmarks, KAIST and DroneVehicle, demonstrate the proposed model achieves the state-of-the-art accuracy while maintaining competitive efficiency.

cs.CV↗

arXiv2024

Delay-Aware Multi-Agent Reinforcement Learning for Cooperative Adaptive Cruise Control with Model-based Stability Enhancement

Cooperative Adaptive Cruise Control (CACC) represents a quintessential control strategy for orchestrating vehicular platoon movement within Connected and Automated Vehicle (CAV) systems, significantly enhancing traffic efficiency and reducing energy consumption. In recent years, the data-driven methods, such as reinforcement learning (RL), have been employed to address this task due to their significant advantages in terms of efficiency and flexibility. However, the delay issue, which often arises in real-world CACC systems, is rarely taken into account by current RL-based approaches. To tackle this problem, we propose a Delay-Aware Multi-Agent Reinforcement Learning (DAMARL) framework aimed at achieving safe and stable control for CACC. We model the entire decision-making process using a Multi-Agent Delay-Aware Markov Decision Process (MADA-MDP) and develop a centralized training with decentralized execution (CTDE) MARL framework for distributed control of CACC platoons. An attention mechanism-integrated policy network is introduced to enhance the performance of CAV communication and decision-making. Additionally, a velocity optimization model-based action filter is incorporated to further ensure the stability of the platoon. Experimental results across various delay conditions and platoon sizes demonstrate that our approach consistently outperforms baseline methods in terms of platoon safety, stability and overall performance.

cs.RO↗

arXiv2024

Evaluation of Drivers' Interaction Ability at Social Scenarios: A Process-Based Framework

Assessing drivers' interaction capabilities is crucial for understanding human driving behavior and enhancing the interactive abilities of autonomous vehicles. In scenarios involving strong interaction, existing metrics focused on interaction outcomes struggle to capture the evolutionary process of drivers' interactive behaviors, making it challenging for autonomous vehicles to dynamically assess and respond to other agents during interactions. To address this issue, we propose a framework for assessing drivers' interaction capabilities, oriented towards the interactive process itself, which includes three components: Interaction Risk Perception, Interaction Process Modeling, and Interaction Ability Scoring. We quantify interaction risks through motion state estimation and risk field theory, followed by introducing a dynamic action assessment benchmark based on a game-theoretical rational agent model, and designing a capability scoring metric based on morphological similarity distance. By calculating real-time differences between a driver's actions and the assessment benchmark, the driver's interaction capabilities are scored dynamically. We validated our framework at unsignalized intersections as a typical scenario. Validation analysis on driver behavior datasets from China and the USA shows that our framework effectively distinguishes and evaluates conservative and aggressive driving states during interactions, demonstrating good adaptability and effectiveness in various regional settings.

cs.RO↗

arXiv2024

BiHom-$Ω$-associative algebras and related structures

In this paper, we first propose the concepts of BiHom-$Ω$-associative algebras, BiHom-$Ω$-dendriform algebras, BiHom-$Ω$-pre-Lie algebras and BiHom-$Ω$-Lie algebras. We then obtain a new BiHom-$Ω$-associative (resp. Lie) algebra by defining a new multiplication on a BiHom-$Ω$-associative (resp. Lie) algebra with the Rota-Baxter family of weight $λ$.In addition, we generalize the classical relationships of associative algebras, pre-Lie algebras, dendriform algebras and Lie algebras to the BiHom-$Ω$ version.

math.RA↗

arXiv2024

DDM-Lag : A Diffusion-based Decision-making Model for Autonomous Vehicles with Lagrangian Safety Enhancement

Decision-making stands as a pivotal component in the realm of autonomous vehicles (AVs), playing a crucial role in navigating the intricacies of autonomous driving. Amidst the evolving landscape of data-driven methodologies, enhancing decision-making performance in complex scenarios has emerged as a prominent research focus. Despite considerable advancements, current learning-based decision-making approaches exhibit potential for refinement, particularly in aspects of policy articulation and safety assurance. To address these challenges, we introduce DDM-Lag, a Diffusion Decision Model, augmented with Lagrangian-based safety enhancements. This work conceptualizes the sequential decision-making challenge inherent in autonomous driving as a problem of generative modeling, adopting diffusion models as the medium for assimilating patterns of decision-making. We introduce a hybrid policy update strategy for diffusion models, amalgamating the principles of behavior cloning and Q-learning, alongside the formulation of an Actor-Critic architecture for the facilitation of updates. To augment the model's exploration process with a layer of safety, we incorporate additional safety constraints, employing a sophisticated policy optimization technique predicated on Lagrangian relaxation to refine the policy learning endeavor comprehensively. Empirical evaluation of our proposed decision-making methodology was conducted across a spectrum of driving tasks, distinguished by their varying degrees of complexity and environmental contexts. The comparative analysis with established baseline methodologies elucidates our model's superior performance, particularly in dimensions of safety and holistic efficacy.

cs.RO↗

arXiv2024

Enhancing Social Decision-Making of Autonomous Vehicles: A Mixed-Strategy Game Approach With Interaction Orientation Identification

The integration of Autonomous Vehicles (AVs) into existing human-driven traffic systems poses considerable challenges, especially within environments where human and machine interactions are frequent and complex, such as at unsignalized intersections. To deal with these challenges, we introduce a novel framework predicated on dynamic and socially-aware decision-making game theory to augment the social decision-making prowess of AVs in mixed driving environments. This comprehensive framework is delineated into three primary modules: Interaction Orientation Identification, Mixed-Strategy Game Modeling, and Expert Mode Learning. We introduce 'Interaction Orientation' as a metric to evaluate the social decision-making tendencies of various agents, incorporating both environmental factors and trajectory characteristics. The mixed-strategy game model developed as part of this framework considers the evolution of future traffic scenarios and includes a utility function that balances safety, operational efficiency, and the unpredictability of environmental conditions. To adapt to real-world driving complexities, our framework utilizes a dynamic optimization framework for assimilating and learning from expert human driving strategies. These strategies are compiled into a comprehensive strategy library, serving as a reference for future decision-making processes. The proposed approach is validated through extensive driving datasets and human-in-loop driving experiments, and the results demonstrate marked enhancements in decision timing and precision.

cs.RO↗

arXiv2024

Gate-tunable quantum acoustoelectric transport in graphene

Transport probes the motion of quasiparticles in response to external excitations. Apart from the well-known electric and thermoelectric transport, acoustoelectric transport induced by traveling acoustic waves has been rarely explored. Here, by adopting a hybrid nanodevices integrated with piezoelectric substrates, we establish a simple design of acoustoelectric transport with gate tunability. We fabricate dual-gated acoustoelectric devices based on BN-encapsuled graphene on LiNbO3. Longitudinal and transverse acoustoelectric voltages are generated by launching pulsed surface acoustic wave. The gate dependence of zero-field longitudinal acoustoelectric signal presents strikingly similar profiles as that of Hall resistivity, providing a valid approach for extracting carrier density without magnetic field. In magnetic fields, acoustoelectric quantum oscillations appear due to Landau quantization, which are more robust and pronounced than Shubnikov-de Haas oscillations. Our work demonstrates a feasible acoustoelectric setup with gate tunability, which can be extended to the broad scope of various Van der Waals materials.

cond-mat.mes-hall↗

arXiv2024

Converging/diverging self-similar shock waves: from collapse to reflection

We solve the continuation problem for the non-isentropic Euler equations following the collapse of an imploding shock wave. More precisely, we prove that the self-similar Güderley imploding shock solutions for a perfect gas with adiabatic exponent $γ\in(1,3]$ admit a self-similar extension consisting of two regions of smooth flow separated by an outgoing spherically symmetric shock wave of finite strength. In addition, for $γ\in(1,\frac53]$, we show that there is a unique choice of shock wave that gives rise to a globally defined self-similar flow with physical state at the spatial origin.

math.AP↗