arXiv subjects

Zhe Xu

Publications and source records attributed to Zhe Xu.

At least 109 records · Page 6Linked to original sources

arXiv2024

Discrete-state Continuous-time Diffusion for Graph Generation

Graph is a prevalent discrete data structure, whose generation has wide applications such as drug discovery and circuit design. Diffusion generative models, as an emerging research focus, have been applied to graph generation tasks. Overall, according to the space of states and time steps, diffusion generative models can be categorized into discrete-/continuous-state discrete-/continuous-time fashions. In this paper, we formulate the graph diffusion generation in a discrete-state continuous-time setting, which has never been studied in previous graph diffusion models. The rationale of such a formulation is to preserve the discrete nature of graph-structured data and meanwhile provide flexible sampling trade-offs between sample quality and efficiency. Analysis shows that our training objective is closely related to generation quality, and our proposed generation framework enjoys ideal invariant/equivariant properties concerning the permutation of node ordering. Our proposed model shows competitive empirical performance against state-of-the-art graph generation solutions on various benchmarks and, at the same time, can flexibly trade off the generation quality and efficiency in the sampling phase.

cs.LG↗

arXiv2024

MMedAgent: Learning to Use Medical Tools with Multi-modal Agent

Multi-Modal Large Language Models (MLLMs), despite being successful, exhibit limited generality and often fall short when compared to specialized models. Recently, LLM-based agents have been developed to address these challenges by selecting appropriate specialized models as tools based on user inputs. However, such advancements have not been extensively explored within the medical domain. To bridge this gap, this paper introduces the first agent explicitly designed for the medical field, named \textbf{M}ulti-modal \textbf{Med}ical \textbf{Agent} (MMedAgent). We curate an instruction-tuning dataset comprising six medical tools solving seven tasks across five modalities, enabling the agent to choose the most suitable tools for a given task. Comprehensive experiments demonstrate that MMedAgent achieves superior performance across a variety of medical tasks compared to state-of-the-art open-source methods and even the closed-source model, GPT-4o. Furthermore, MMedAgent exhibits efficiency in updating and integrating new medical tools. Codes and models are all available.

cs.CL↗

arXiv2024

An End-to-End Reinforcement Learning Based Approach for Micro-View Order-Dispatching in Ride-Hailing

Assigning orders to drivers under localized spatiotemporal context (micro-view order-dispatching) is a major task in Didi, as it influences ride-hailing service experience. Existing industrial solutions mainly follow a two-stage pattern that incorporate heuristic or learning-based algorithms with naive combinatorial methods, tackling the uncertainty of both sides' behaviors, including emerging timings, spatial relationships, and travel duration, etc. In this paper, we propose a one-stage end-to-end reinforcement learning based order-dispatching approach that solves behavior prediction and combinatorial optimization uniformly in a sequential decision-making manner. Specifically, we employ a two-layer Markov Decision Process framework to model this problem, and present \underline{D}eep \underline{D}ouble \underline{S}calable \underline{N}etwork (D2SN), an encoder-decoder structure network to generate order-driver assignments directly and stop assignments accordingly. Besides, by leveraging contextual dynamics, our approach can adapt to the behavioral patterns for better performance. Extensive experiments on Didi's real-world benchmarks justify that the proposed approach significantly outperforms competitive baselines in optimizing matching efficiency and user experience tasks. In addition, we evaluate the deployment outline and discuss the gains and experiences obtained during the deployment tests from the view of large-scale engineering implementation.

cs.LG↗

arXiv2024

Technique Report of CVPR 2024 PBDL Challenges

The intersection of physics-based vision and deep learning presents an exciting frontier for advancing computer vision technologies. By leveraging the principles of physics to inform and enhance deep learning models, we can develop more robust and accurate vision systems. Physics-based vision aims to invert the processes to recover scene properties such as shape, reflectance, light distribution, and medium properties from images. In recent years, deep learning has shown promising improvements for various vision tasks, and when combined with physics-based vision, these approaches can enhance the robustness and accuracy of vision systems. This technical report summarizes the outcomes of the Physics-Based Vision Meets Deep Learning (PBDL) 2024 challenge, held in CVPR 2024 workshop. The challenge consisted of eight tracks, focusing on Low-Light Enhancement and Detection as well as High Dynamic Range (HDR) Imaging. This report details the objectives, methodologies, and results of each track, highlighting the top-performing solutions and their innovative approaches.

cs.CV↗

arXiv2024

Origin of the Chromospheric Umbral Waves in Sunspots

Oscillations are ubiquitous in sunspots and the associated higher atmospheres. However, it is still unclear whether these oscillations are driven by the external acoustic waves (p-modes) or generated by the internal magnetoconvection. To obtain clues about the driving source of umbral waves in sunspots, we analyzed the spiral wave patterns (SWPs) in two sunspots registered by IRIS MgII 2796 Å slit-jaw images. By tracking the motion of the SWPs, we find for the first time that two one-armed SWPs coexist in the umbra, and they can rotate either in the same or opposite directions. Furthermore, by analyzing the spatial distribution of the oscillation centers of the one-armed SWPs within the umbra (the oscillation center is defined as the location where the SWP first appears), we find that the chromospheric umbral waves repeatedly originate from the regions with high oscillation power and most of the umbral waves occur in the dark nuclei and strong magnetic field regions of the umbra. Our study results indicate that the chromospheric umbral waves are likely excited by the p-mode oscillations.

astro-ph.SR↗

arXiv2024

State-Constrained Zero-Sum Differential Games with One-Sided Information

We study zero-sum differential games with state constraints and one-sided information, where the informed player (Player 1) has a categorical payoff type unknown to the uninformed player (Player 2). The goal of Player 1 is to minimize his payoff without violating the constraints, while that of Player 2 is to violate the state constraints if possible, or to maximize the payoff otherwise. One example of the game is a man-to-man matchup in football. Without state constraints, Cardaliaguet (2007) showed that the value of such a game exists and is convex to the common belief of players. Our theoretical contribution is an extension of this result to games with state constraints and the derivation of the primal and dual subdynamic principles necessary for computing behavioral strategies. Different from existing works that are concerned about the scalability of no-regret learning in games with discrete dynamics, our study reveals the underlying structure of strategies for belief manipulation resulting from information asymmetry and state constraints. This structure will be necessary for scalable learning on games with continuous actions and long time windows. We use a simplified football game to demonstrate the utility of this work, where we reveal player positions and belief states in which the attacker should (or should not) play specific random deceptive moves to take advantage of information asymmetry, and compute how the defender should respond.

cs.GT↗

arXiv2024

Pontryagin Neural Operator for Solving Parametric General-Sum Differential Games

The values of two-player general-sum differential games are viscosity solutions to Hamilton-Jacobi-Isaacs (HJI) equations. Value and policy approximations for such games suffer from the curse of dimensionality (CoD). Alleviating CoD through physics-informed neural networks (PINN) encounters convergence issues when differentiable values with large Lipschitz constants are present due to state constraints. On top of these challenges, it is often necessary to learn generalizable values and policies across a parametric space of games, e.g., for game parameter inference when information is incomplete. To address these challenges, we propose in this paper a Pontryagin-mode neural operator that outperforms the current state-of-the-art hybrid PINN model on safety performance across games with parametric state constraints. Our key contribution is the introduction of a costate loss defined on the discrepancy between forward and backward costate rollouts, which are computationally cheap. We show that the costate dynamics, which can reflect state constraint violation, effectively enables the learning of differentiable values with large Lipschitz constants, without requiring manually supervised data as suggested by the hybrid PINN model. More importantly, we show that the close relationship between costates and policies makes the former critical in learning feedback control policies with generalizable safety performance.

cs.LG↗

arXiv2024

Class-Imbalanced Graph Learning without Class Rebalancing

Class imbalance is prevalent in real-world node classification tasks and poses great challenges for graph learning models. Most existing studies are rooted in a class-rebalancing (CR) perspective and address class imbalance with class-wise reweighting or resampling. In this work, we approach the root cause of class-imbalance bias from an topological paradigm. Specifically, we theoretically reveal two fundamental phenomena in the graph topology that greatly exacerbate the predictive bias stemming from class imbalance. On this basis, we devise a lightweight topological augmentation framework BAT to mitigate the class-imbalance bias without class rebalancing. Being orthogonal to CR, BAT can function as an efficient plug-and-play module that can be seamlessly combined with and significantly boost existing CR techniques. Systematic experiments on real-world imbalanced graph learning tasks show that BAT can deliver up to 46.27% performance gain and up to 72.74% bias reduction over existing techniques. Code, examples, and documentations are available at https://github.com/ZhiningLiu1998/BAT.

cs.LG↗

arXiv2024

Masked Graph Transformer for Large-Scale Recommendation

Graph Transformers have garnered significant attention for learning graph-structured data, thanks to their superb ability to capture long-range dependencies among nodes. However, the quadratic space and time complexity hinders the scalability of Graph Transformers, particularly for large-scale recommendation. Here we propose an efficient Masked Graph Transformer, named MGFormer, capable of capturing all-pair interactions among nodes with a linear complexity. To achieve this, we treat all user/item nodes as independent tokens, enhance them with positional embeddings, and feed them into a kernelized attention module. Additionally, we incorporate learnable relative degree information to appropriately reweigh the attentions. Experimental results show the superior performance of our MGFormer, even with a single attention layer.

cs.IR↗

arXiv2024

Value Approximation for Two-Player General-Sum Differential Games with State Constraints

Solving Hamilton-Jacobi-Isaacs (HJI) PDEs numerically enables equilibrial feedback control in two-player differential games, yet faces the curse of dimensionality (CoD). While physics-informed neural networks (PINNs) have shown promise in alleviating CoD in solving PDEs, vanilla PINNs fall short in learning discontinuous solutions due to their sampling nature, leading to poor safety performance of the resulting policies when values are discontinuous due to state or temporal logic constraints. In this study, we explore three potential solutions to this challenge: (1) a hybrid learning method that is guided by both supervisory equilibria and the HJI PDE, (2) a value-hardening method where a sequence of HJIs are solved with increasing Lipschitz constant on the constraint violation penalty, and (3) the epigraphical technique that lifts the value to a higher dimensional state space where it becomes continuous. Evaluations through 5D and 9D vehicle and 13D drone simulations reveal that the hybrid method outperforms others in terms of generalization and safety performance by taking advantage of both the supervisory equilibrium values and costates, and the low cost of PINN loss gradients.

cs.RO↗

arXiv2024

Negative-energy waves in the vertical threads of a solar prominence

Solar prominences, intricate structures on the Sun's limb, have been a subject of fascination due to their thread-like features and dynamic behaviors. Utilizing data from the New Vacuum Solar Telescope (NVST), Chinese H_alpha Solar Explorer (CHASE), and Solar Dynamics Observatory (SDO), this study investigates the transverse swaying motions observed in the vertical threads of a solar prominence during its eruption onset on May 11, 2023. The transverse swaying motions were observed to propagate upward, accompanied by upflowing materials at an inclination of 31 degrees relative to the plane of the sky. These motions displayed small-amplitude oscillations with corrected velocities of around 3-4 km/s and periods of 13-17 minutes. Over time, the oscillations of swaying motion exhibited an increasing pattern in displacement amplitudes, oscillatory periods, and projected velocity amplitudes. Their phase velocities are estimated to be about 26-34 km/s. An important finding is that these oscillations'phase velocities are comparable to the upward flow velocities, measured to be around 30-34 km/s. We propose that this phenomenon is associated with negative-energy wave instabilities, which require comparable velocities of the waves and flows, as indicated by our findings. This phenomenon may contribute to the instability and observed disruption of the prominence. By using prominence seismology, the Alfven speed and magnetic field strength of the vertical threads have been estimated to be approximately 21.5 km/s and 2 Gauss, respectively. This study reveals the dynamics and magnetic properties of solar prominences, contributing to our understanding of their behavior in the solar atmosphere.

astro-ph.SR↗

arXiv2024

Dynamic Demonstration Retrieval and Cognitive Understanding for Emotional Support Conversation

Emotional Support Conversation (ESC) systems are pivotal in providing empathetic interactions, aiding users through negative emotional states by understanding and addressing their unique experiences. In this paper, we tackle two key challenges in ESC: enhancing contextually relevant and empathetic response generation through dynamic demonstration retrieval, and advancing cognitive understanding to grasp implicit mental states comprehensively. We introduce Dynamic Demonstration Retrieval and Cognitive-Aspect Situation Understanding (\ourwork), a novel approach that synergizes these elements to improve the quality of support provided in ESCs. By leveraging in-context learning and persona information, we introduce an innovative retrieval mechanism that selects informative and personalized demonstration pairs. We also propose a cognitive understanding module that utilizes four cognitive relationships from the ATOMIC knowledge source to deepen situational awareness of help-seekers' mental states. Our supportive decoder integrates information from diverse knowledge sources, underpinning response generation that is both empathetic and cognitively aware. The effectiveness of \ourwork is demonstrated through extensive automatic and human evaluations, revealing substantial improvements over numerous state-of-the-art models, with up to 13.79\% enhancement in overall performance of ten metrics. Our codes are available for public access to facilitate further research and development.

cs.CL↗

arXiv2024

Distributed Robust Learning based Formation Control of Mobile Robots based on Bioinspired Neural Dynamics

This paper addresses the challenges of distributed formation control in multiple mobile robots, introducing a novel approach that enhances real-world practicability. We first introduce a distributed estimator using a variable structure and cascaded design technique, eliminating the need for derivative information to improve the real time performance. Then, a kinematic tracking control method is developed utilizing a bioinspired neural dynamic-based approach aimed at providing smooth control inputs and effectively resolving the speed jump issue. Furthermore, to address the challenges for robots operating with completely unknown dynamics and disturbances, a learning-based robust dynamic controller is developed. This controller provides real time parameter estimates while maintaining its robustness against disturbances. The overall stability of the proposed method is proved with rigorous mathematical analysis. At last, multiple comprehensive simulation studies have shown the advantages and effectiveness of the proposed method.

cs.RO↗

arXiv2024

Diversified and Personalized Multi-rater Medical Image Segmentation

Annotation ambiguity due to inherent data uncertainties such as blurred boundaries in medical scans and different observer expertise and preferences has become a major obstacle for training deep-learning based medical image segmentation models. To address it, the common practice is to gather multiple annotations from different experts, leading to the setting of multi-rater medical image segmentation. Existing works aim to either merge different annotations into the "groundtruth" that is often unattainable in numerous medical contexts, or generate diverse results, or produce personalized results corresponding to individual expert raters. Here, we bring up a more ambitious goal for multi-rater medical image segmentation, i.e., obtaining both diversified and personalized results. Specifically, we propose a two-stage framework named D-Persona (first Diversification and then Personalization). In Stage I, we exploit multiple given annotations to train a Probabilistic U-Net model, with a bound-constrained loss to improve the prediction diversity. In this way, a common latent space is constructed in Stage I, where different latent codes denote diversified expert opinions. Then, in Stage II, we design multiple attention-based projection heads to adaptively query the corresponding expert prompts from the shared latent space, and then perform the personalized medical image segmentation. We evaluated the proposed model on our in-house Nasopharyngeal Carcinoma dataset and the public lung nodule dataset (i.e., LIDC-IDRI). Extensive experiments demonstrated our D-Persona can provide diversified and personalized results at the same time, achieving new SOTA performance for multi-rater medical image segmentation. Our code will be released at https://github.com/ycwu1997/D-Persona.

cs.CV↗

arXiv2024

Imaging and spectroscopic observations of a confined solar filament eruption with two-stage evolution

Solar filament eruptions are often characterized by stepwise evolution due to the involvement of multiple mechanisms, such as magnetohydrodynamic instabilities and magnetic reconnection. In this article, we investigated a confined filament eruption with a distinct two-stage evolution by using the imaging and spectroscopic observations from the Interface Region Imaging Spectrograph (IRIS) and the Solar Dynamics Observatory (SDO). The eruption originated from a kinked filament thread that separated from an active region filament. In the first stage, the filament thread rose slowly and was obstructed due to flux pile-up in its front. This obstruction brought the filament thread into reconnection with a nearby loop-like structure, which enlarged the flux rope and changed its connectivity through the foot-point migration. The newly formed flux rope became more kink unstable and drove the rapid eruption in the second stage. It ascended into the upper atmosphere and initiated the reconnection with the overlying field. Finally, the flux rope was totally disintegrated, producing several solar jets along the overlying field. These observations demonstrate that the external reconnection between the flux rope and overlying field can destroy the flux rope, thus playing a crucial role in confining the solar eruptions.

astro-ph.SR↗

arXiv2024

Using Large Language Models to Automate and Expedite Reinforcement Learning with Reward Machine

We present LARL-RM (Large language model-generated Automaton for Reinforcement Learning with Reward Machine) algorithm in order to encode high-level knowledge into reinforcement learning using automaton to expedite the reinforcement learning. Our method uses Large Language Models (LLM) to obtain high-level domain-specific knowledge using prompt engineering instead of providing the reinforcement learning algorithm directly with the high-level knowledge which requires an expert to encode the automaton. We use chain-of-thought and few-shot methods for prompt engineering and demonstrate that our method works using these approaches. Additionally, LARL-RM allows for fully closed-loop reinforcement learning without the need for an expert to guide and supervise the learning since LARL-RM can use the LLM directly to generate the required high-level knowledge for the task at hand. We also show the theoretical guarantee of our algorithm to converge to an optimal policy. We demonstrate that LARL-RM speeds up the convergence by 30% by implementing our method in two case studies.

cs.LG↗

arXiv2024

Hierarchical Control for Cooperative Teams in Competitive Autonomous Racing

We investigate the problem of autonomous racing among teams of cooperative agents that are subject to realistic racing rules. Our work extends previous research on hierarchical control in head-to-head autonomous racing by considering a generalized version of the problem while maintaining the two-level hierarchical control structure. A high-level tactical planner constructs a discrete game that encodes the complex rules using simplified dynamics to produce a sequence of target waypoints. The low-level path planner uses these waypoints as a reference trajectory and computes high-resolution control inputs by solving a simplified formulation of a racing game with a simplified representation of the realistic racing rules. We explore two approaches for the low-level path planner: training a multi-agent reinforcement learning (MARL) policy and solving a linear-quadratic Nash game (LQNG) approximation. We evaluate our controllers on simple and complex tracks against three baselines: an end-to-end MARL controller, a MARL controller tracking a fixed racing line, and an LQNG controller tracking a fixed racing line. Quantitative results show our hierarchical methods outperform the baselines in terms of race wins, overall team performance, and compliance with the rules. Qualitatively, we observe the hierarchical controllers mimic actions performed by expert human drivers such as coordinated overtaking, defending against multiple opponents, and long-term planning for delayed advantages.

cs.MA↗

arXiv2024

Hierarchical Control for Head-to-Head Autonomous Racing

We develop a hierarchical controller for head-to-head autonomous racing. We first introduce a formulation of a racing game with realistic safety and fairness rules. A high-level planner approximates the original formulation as a discrete game with simplified state, control, and dynamics to easily encode the complex safety and fairness rules and calculates a series of target waypoints. The low-level controller takes the resulting waypoints as a reference trajectory and computes high-resolution control inputs by solving an alternative formulation approximation with simplified objectives and constraints. We consider two approaches for the low-level planner, constructing two hierarchical controllers. One approach uses multi-agent reinforcement learning (MARL), and the other solves a linear-quadratic Nash game (LQNG) to produce control inputs. The controllers are compared against three baselines: an end-to-end MARL controller, a MARL controller tracking a fixed racing line, and an LQNG controller tracking a fixed racing line. Quantitative results show that the proposed hierarchical methods outperform their respective baseline methods in terms of head-to-head race wins and abiding by the rules. The hierarchical controller using MARL for low-level control consistently outperformed all other methods by winning over 90% of head-to-head races and more consistently adhered to the complex racing rules. Qualitatively, we observe the proposed controllers mimicking actions performed by expert human drivers such as shielding/blocking, overtaking, and long-term planning for delayed advantages. We show that hierarchical planning for game-theoretic reasoning produces competitive behavior even when challenged with complex rules and constraints.

cs.MA↗