arXiv subjects

Jun Ma

Publications and source records attributed to Jun Ma.

At least 199 records · Page 11Linked to original sources

arXiv2025

Self-Enhanced Reasoning Training: Activating Latent Reasoning in Small Models for Enhanced Reasoning Distillation

The rapid advancement of large language models (LLMs) has significantly enhanced their reasoning abilities, enabling increasingly complex tasks. However, these capabilities often diminish in smaller, more computationally efficient models like GPT-2. Recent research shows that reasoning distillation can help small models acquire reasoning capabilities, but most existing methods focus primarily on improving teacher-generated reasoning paths. Our observations reveal that small models can generate high-quality reasoning paths during sampling, even without chain-of-thought prompting, though these paths are often latent due to their low probability under standard decoding strategies. To address this, we propose Self-Enhanced Reasoning Training (SERT), which activates and leverages latent reasoning capabilities in small models through self-training on filtered, self-generated reasoning paths under zero-shot conditions. Experiments using OpenAI's GPT-3.5 as the teacher model and GPT-2 models as the student models demonstrate that SERT enhances the reasoning abilities of small models, improving their performance in reasoning distillation.

cs.CL↗

arXiv2025

SWEA: Updating Factual Knowledge in Large Language Models via Subject Word Embedding Altering

The general capabilities of large language models (LLMs) make them the infrastructure for various AI applications, but updating their inner knowledge requires significant resources. Recent model editing is a promising technique for efficiently updating a small amount of knowledge of LLMs and has attracted much attention. In particular, local editing methods, which directly update model parameters, are proven suitable for updating small amounts of knowledge. Local editing methods update weights by computing least squares closed-form solutions and identify edited knowledge by vector-level matching in inference, which achieve promising results. However, these methods still require a lot of time and resources to complete the computation. Moreover, vector-level matching lacks reliability, and such updates disrupt the original organization of the model's parameters. To address these issues, we propose a detachable and expandable Subject Word Embedding Altering (SWEA) framework, which finds the editing embeddings through token-level matching and adds them to the subject word embeddings in Transformer input. To get these editing embeddings, we propose optimizing then suppressing fusion method, which first optimizes learnable embedding vectors for the editing target and then suppresses the Knowledge Embedding Dimensions (KEDs) to obtain final editing embeddings. We thus propose SWEA$\oplus$OS method for editing factual knowledge in LLMs. We demonstrate the overall state-of-the-art (SOTA) performance of SWEA$\oplus$OS on the CounterFact and zsRE datasets. To further validate the reasoning ability of SWEA$\oplus$OS in editing knowledge, we evaluate it on the more complex RippleEdits benchmark. The results demonstrate that SWEA$\oplus$OS possesses SOTA reasoning ability.

cs.CL↗

arXiv2025

How to Alleviate Catastrophic Forgetting in LLMs Finetuning? Hierarchical Layer-Wise and Element-Wise Regularization

Large Language Models (LLMs) exhibit strong general language capabilities. However, fine-tuning these models on domain-specific tasks often leads to catastrophic forgetting, where the model overwrites or loses essential knowledge acquired during pretraining. This phenomenon significantly limits the broader applicability of LLMs. To address this challenge, we propose a novel approach to compute the element-wise importance of model parameters crucial for preserving general knowledge during fine-tuning. Our method utilizes a dual-objective optimization strategy: (1) regularization loss based on element-wise parameter importance, which constrains the updates to parameters crucial for general knowledge; (2) cross-entropy loss to adapt to domain-specific tasks. Additionally, we introduce layer-wise coefficients to account for the varying contributions of different layers, dynamically balancing the dual-objective optimization. Extensive experiments on scientific, medical, and physical tasks using GPT-J and LLaMA-3 demonstrate that our approach mitigates catastrophic forgetting while enhancing model adaptability. Compared to previous methods, our solution is approximately 20 times faster and requires only 10-15% of the storage, highlighting the practical efficiency. The code will be released.

cs.CL↗

arXiv2025

FRTree Planner: Robot Navigation in Cluttered and Unknown Environments with Tree of Free Regions

In this work, we present FRTree planner, a novel robot navigation framework that leverages a tree structure of free regions, specifically designed for navigation in cluttered and unknown environments with narrow passages. The framework continuously incorporates real-time perceptive information to identify distinct navigation options and dynamically expands the tree toward explorable and traversable directions. This dynamically constructed tree incrementally encodes the geometric and topological information of the collision-free space, enabling efficient selection of the intermediate goals, navigating around dead-end situations, and avoidance of dynamic obstacles without a prior map. Crucially, our method performs a comprehensive analysis of the geometric relationship between free regions and the robot during online replanning. In particular, the planner assesses the accessibility of candidate passages based on the robot's geometries, facilitating the effective selection of the most viable intermediate goals through accessible narrow passages while minimizing unnecessary detours. By combining the free region information with a bi-level trajectory optimization tailored for robots with specific geometries, our approach generates robust and adaptable obstacle avoidance strategies in confined spaces. Through extensive simulations and real-world experiments, FRTree demonstrates its superiority over benchmark methods in generating safe, efficient motion plans through highly cluttered and unknown terrains with narrow gaps.

cs.RO↗

arXiv2025

Robot Navigation in Unknown and Cluttered Workspace with Dynamical System Modulation in Starshaped Roadmap

Compared to conventional decomposition methods that use ellipses or polygons to represent free space, starshaped representation can better capture the natural distribution of sensor data, thereby exploiting a larger portion of traversable space. This paper introduces a novel motion planning and control framework for navigating robots in unknown and cluttered environments using a dynamically constructed starshaped roadmap. Our approach generates a starshaped representation of the surrounding free space from real-time sensor data using piece-wise polynomials. Additionally, an incremental roadmap maintaining the connectivity information is constructed, and a searching algorithm efficiently selects short-term goals on this roadmap. Importantly, this framework addresses dead-end situations with a graph updating mechanism. To ensure safe and efficient movement within the starshaped roadmap, we propose a reactive controller based on Dynamic System Modulation (DSM). This controller facilitates smooth motion within starshaped regions and their intersections, avoiding conservative and short-sighted behaviors and allowing the system to handle intricate obstacle configurations in unknown and cluttered environments. Comprehensive evaluations in both simulations and real-world experiments show that the proposed method achieves higher success rates and reduced travel times compared to other methods. It effectively manages intricate obstacle configurations, avoiding conservative and myopic behaviors.

cs.RO↗

arXiv2025

CurbNet: Curb Detection Framework Based on LiDAR Point Cloud Segmentation

Curb detection is a crucial function in intelligent driving, essential for determining drivable areas on the road. However, the complexity of road environments makes curb detection challenging. This paper introduces CurbNet, a novel framework for curb detection utilizing point cloud segmentation. To address the lack of comprehensive curb datasets with 3D annotations, we have developed the 3D-Curb dataset based on SemanticKITTI, currently the largest and most diverse collection of curb point clouds. Recognizing that the primary characteristic of curbs is height variation, our approach leverages spatially rich 3D point clouds for training. To tackle the challenges posed by the uneven distribution of curb features on the xy-plane and their dependence on high-frequency features along the z-axis, we introduce the Multi-Scale and Channel Attention (MSCA) module, a customized solution designed to optimize detection performance. Additionally, we propose an adaptive weighted loss function group specifically formulated to counteract the imbalance in the distribution of curb point clouds relative to other categories. Extensive experiments conducted on 2 major datasets demonstrate that our method surpasses existing benchmarks set by leading curb detection and point cloud segmentation models. Through the post-processing refinement of the detection results, we have significantly reduced noise in curb detection, thereby improving precision by 4.5 points. Similarly, our tolerance experiments also achieve state-of-the-art results. Furthermore, real-world experiments and dataset analyses mutually validate each other, reinforcing CurbNet's superior detection capability and robust generalizability. The project website is available at: https://github.com/guoyangzhao/CurbNet/.

cs.CV↗

arXiv2025

Multi-Class Segmentation of Aortic Branches and Zones in Computed Tomography Angiography: The AortaSeg24 Challenge

Multi-class segmentation of the aorta in computed tomography angiography (CTA) scans is essential for diagnosing and planning complex endovascular treatments for patients with aortic dissections. However, existing methods reduce aortic segmentation to a binary problem, limiting their ability to measure diameters across different branches and zones. Furthermore, no open-source dataset is currently available to support the development of multi-class aortic segmentation methods. To address this gap, we organized the AortaSeg24 MICCAI Challenge, introducing the first dataset of 100 CTA volumes annotated for 23 clinically relevant aortic branches and zones. This dataset was designed to facilitate both model development and validation. The challenge attracted 121 teams worldwide, with participants leveraging state-of-the-art frameworks such as nnU-Net and exploring novel techniques, including cascaded models, data augmentation strategies, and custom loss functions. We evaluated the submitted algorithms using the Dice Similarity Coefficient (DSC) and Normalized Surface Distance (NSD), highlighting the approaches adopted by the top five performing teams. This paper presents the challenge design, dataset details, evaluation metrics, and an in-depth analysis of the top-performing algorithms. The annotated dataset, evaluation code, and implementations of the leading methods are publicly available to support further research. All resources can be accessed at https://aortaseg24.grand-challenge.org.

eess.IV↗

arXiv2025

Bilevel Multi-Armed Bandit-Based Hierarchical Reinforcement Learning for Interaction-Aware Self-Driving at Unsignalized Intersections

In this work, we present BiM-ACPPO, a bilevel multi-armed bandit-based hierarchical reinforcement learning framework for interaction-aware decision-making and planning at unsignalized intersections. Essentially, it proactively takes the uncertainties associated with surrounding vehicles (SVs) into consideration, which encompass those stemming from the driver's intention, interactive behaviors, and the varying number of SVs. Intermediate decision variables are introduced to enable the high-level RL policy to provide an interaction-aware reference, for guiding low-level model predictive control (MPC) and further enhancing the generalization ability of the proposed framework. By leveraging the structured nature of self-driving at unsignalized intersections, the training problem of the RL policy is modeled as a bilevel curriculum learning task, which is addressed by the proposed Exp3.S-based BiMAB algorithm. It is noteworthy that the training curricula are dynamically adjusted, thereby facilitating the sample efficiency of the RL training process. Comparative experiments are conducted in the high-fidelity CARLA simulator, and the results indicate that our approach achieves superior performance compared to all baseline methods. Furthermore, experimental results in two new urban driving scenarios clearly demonstrate the commendable generalization performance of the proposed method.

cs.RO↗

arXiv2025

Periodic solutions for McKean-Vlasov SDEs under periodic distribution-dependent Lyapunov conditions

In this paper, we prove the existence of periodic solutions for McKean-Vlasov SDEs under periodic distribution-dependent Lyapunov conditions, which is obtained by periodic Markov processes with state space $\mathbb R^d\times \mathcal P(\mathbb R^d)$. Here $\mathcal P(\mathbb R^d)$ denotes the space of probability measures on $\mathbb R^d$. In addition, we show the convergence to the periodic solution and the continuous dependence on parameters of periodic solutions for McKean-Vlasov SDEs. Finally, we provide several examples to illustrate our theoretical results.

math.DS↗

arXiv2025

SAMScore: A Content Structural Similarity Metric for Image Translation Evaluation

Image translation has wide applications, such as style transfer and modality conversion, usually aiming to generate images having both high degrees of realism and faithfulness. These problems remain difficult, especially when it is important to preserve content structures. Traditional image-level similarity metrics are of limited use, since the content structures of an image are high-level, and not strongly governed by pixel-wise faithfulness to an original image. To fill this gap, we introduce SAMScore, a generic content structural similarity metric for evaluating the faithfulness of image translation models. SAMScore is based on the recent high-performance Segment Anything Model (SAM), which allows content similarity comparisons with standout accuracy. We applied SAMScore on 19 image translation tasks, and found that it is able to outperform all other competitive metrics on all tasks. We envision that SAMScore will prove to be a valuable tool that will help to drive the vibrant field of image translation, by allowing for more precise evaluations of new and evolving translation models. The code is available at https://github.com/Kent0n-Li/SAMScore.

cs.CV↗

arXiv2025

Reward-Driven Automated Curriculum Learning for Interaction-Aware Self-Driving at Unsignalized Intersections

In this work, we present a reward-driven automated curriculum reinforcement learning approach for interaction-aware self-driving at unsignalized intersections, taking into account the uncertainties associated with surrounding vehicles (SVs). These uncertainties encompass the uncertainty of SVs' driving intention and also the quantity of SVs. To deal with this problem, the curriculum set is specifically designed to accommodate a progressively increasing number of SVs. By implementing an automated curriculum selection mechanism, the importance weights are rationally allocated across various curricula, thereby facilitating improved sample efficiency and training outcomes. Furthermore, the reward function is meticulously designed to guide the agent towards effective policy exploration. Thus the proposed framework could proactively address the above uncertainties at unsignalized intersections by employing the automated curriculum learning technique that progressively increases task difficulty, and this ensures safe self-driving through effective interaction with SVs. Comparative experiments are conducted in $Highway\_Env$, and the results indicate that our approach achieves the highest task success rate, attains strong robustness to initialization parameters of the curriculum selection module, and exhibits superior adaptability to diverse situational configurations at unsignalized intersections. Furthermore, the effectiveness of the proposed method is validated using the high-fidelity CARLA simulator.

cs.RO↗

arXiv2025

CoDriveVLM: VLM-Enhanced Urban Cooperative Dispatching and Motion Planning for Future Autonomous Mobility on Demand Systems

The increasing demand for flexible and efficient urban transportation solutions has spotlighted the limitations of traditional Demand Responsive Transport (DRT) systems, particularly in accommodating diverse passenger needs and dynamic urban environments. Autonomous Mobility-on-Demand (AMoD) systems have emerged as a promising alternative, leveraging connected and autonomous vehicles (CAVs) to provide responsive and adaptable services. However, existing methods primarily focus on either vehicle scheduling or path planning, which often simplify complex urban layouts and neglect the necessity for simultaneous coordination and mutual avoidance among CAVs. This oversimplification poses significant challenges to the deployment of AMoD systems in real-world scenarios. To address these gaps, we propose CoDriveVLM, a novel framework that integrates high-fidelity simultaneous dispatching and cooperative motion planning for future AMoD systems. Our method harnesses Vision-Language Models (VLMs) to enhance multi-modality information processing, and this enables comprehensive dispatching and collision risk evaluation. The VLM-enhanced CAV dispatching coordinator is introduced to effectively manage complex and unforeseen AMoD conditions, thus supporting efficient scheduling decision-making. Furthermore, we propose a scalable decentralized cooperative motion planning method via consensus alternating direction method of multipliers (ADMM) focusing on collision risk evaluation and decentralized trajectory optimization. Simulation results demonstrate the feasibility and robustness of CoDriveVLM in various traffic conditions, showcasing its potential to significantly improve the fidelity and effectiveness of AMoD systems in future urban transportation networks. The code is available at https://github.com/henryhcliu/CoDriveVLM.git.

cs.RO↗

arXiv2025

LearningFlow: Automated Policy Learning Workflow for Urban Driving with Large Language Models

Recent advancements in reinforcement learning (RL) demonstrate the significant potential in autonomous driving. Despite this promise, challenges such as the manual design of reward functions and low sample efficiency in complex environments continue to impede the development of safe and effective driving policies. To tackle these issues, we introduce LearningFlow, an innovative automated policy learning workflow tailored to urban driving. This framework leverages the collaboration of multiple large language model (LLM) agents throughout the RL training process. LearningFlow includes a curriculum sequence generation process and a reward generation process, which work in tandem to guide the RL policy by generating tailored training curricula and reward functions. Particularly, each process is supported by an analysis agent that evaluates training progress and provides critical insights to the generation agent. Through the collaborative efforts of these LLM agents, LearningFlow automates policy learning across a series of complex driving tasks, and it significantly reduces the reliance on manual reward function design while enhancing sample efficiency. Comprehensive experiments are conducted in the high-fidelity CARLA simulator, along with comparisons with other existing methods, to demonstrate the efficacy of our proposed approach. The results demonstrate that LearningFlow excels in generating rewards and curricula. It also achieves superior performance and robust generalization across various driving tasks, as well as commendable adaptation to different RL algorithms.

cs.RO↗

arXiv2025

How to Bridge the Gap between Modalities: Survey on Multimodal Large Language Model

We explore Multimodal Large Language Models (MLLMs), which integrate LLMs like GPT-4 to handle multimodal data, including text, images, audio, and more. MLLMs demonstrate capabilities such as generating image captions and answering image-based questions, bridging the gap towards real-world human-computer interactions and hinting at a potential pathway to artificial general intelligence. However, MLLMs still face challenges in addressing the semantic gap in multimodal data, which may lead to erroneous outputs, posing potential risks to society. Selecting the appropriate modality alignment method is crucial, as improper methods might require more parameters without significant performance improvements. This paper aims to explore modality alignment methods for LLMs and their current capabilities. Implementing effective modality alignment can help LLMs address environmental issues and enhance accessibility. The study surveys existing modality alignment methods for MLLMs, categorizing them into four groups: (1) Multimodal Converter, which transforms data into a format that LLMs can understand; (2) Multimodal Perceiver, which improves how LLMs percieve different types of data; (3) Tool Learning, which leverages external tools to convert data into a common format, usually text; and (4) Data-Driven Method, which teaches LLMs to understand specific data types within datasets.

cs.CL↗

arXiv2025

Local Reactive Control for Mobile Manipulators with Whole-Body Safety in Complex Environments

Mobile manipulators typically encounter significant challenges in navigating narrow, cluttered environments due to their high-dimensional state spaces and complex kinematics. While reactive methods excel in dynamic settings, they struggle to efficiently incorporate complex, coupled constraints across the entire state space. In this work, we present a novel local reactive controller that reformulates the time-domain single-step problem into a multi-step optimization problem in the spatial domain, leveraging the propagation of a serial kinematic chain. This transformation facilitates the formulation of customized, decoupled link-specific constraints, which is further solved efficiently with augmented Lagrangian differential dynamic programming (AL-DDP). Our approach naturally absorbs spatial kinematic propagation in the forward pass and processes all link-specific constraints simultaneously during the backward pass, enhancing both constraint management and computational efficiency. Notably, in this framework, we formulate collision avoidance constraints for each link using accurate geometric models with extracted free regions, and this improves the maneuverability of the mobile manipulator in narrow, cluttered spaces. Experimental results showcase significant improvements in safety, efficiency, and task completion rates. These findings underscore the robustness of the proposed method, particularly in narrow, cluttered environments where conventional approaches could falter. The open-source project can be found at https://github.com/Chunx1nZHENG/MM-with-Whole-Body-Safety-Release.git.

cs.RO↗

arXiv2025

UDMC: Unified Decision-Making and Control Framework for Urban Autonomous Driving with Motion Prediction of Traffic Participants

Current autonomous driving systems often struggle to balance decision-making and motion control while ensuring safety and traffic rule compliance, especially in complex urban environments. Existing methods may fall short due to separate handling of these functionalities, leading to inefficiencies and safety compromises. To address these challenges, we introduce UDMC, an interpretable and unified Level 4 autonomous driving framework. UDMC integrates decision-making and motion control into a single optimal control problem (OCP), considering the dynamic interactions with surrounding vehicles, pedestrians, road lanes, and traffic signals. By employing innovative potential functions to model traffic participants and regulations, and incorporating a specialized motion prediction module, our framework enhances on-road safety and rule adherence. The integrated design allows for real-time execution of flexible maneuvers suited to diverse driving scenarios. High-fidelity simulations conducted in CARLA exemplify the framework's computational efficiency, robustness, and safety, resulting in superior driving performance when compared against various baseline models. Our open-source project is available at https://github.com/henryhcliu/udmc_carla.git.

cs.RO↗

arXiv2024

A maximum penalised likelihood approach for semiparametric accelerated failure time models with time-varying covariates and partly interval censoring

Accelerated failure time (AFT) models are frequently used to model survival data, providing a direct quantification of the relationship between event times and covariates. These models allow for the acceleration or deceleration of failure times through a multiplicative factor that accounts for the effect of covariates. While existing literature provides numerous methods for fitting AFT models with time-fixed covariates, adapting these approaches to scenarios involving both time-varying covariates and partly interval-censored data remains challenging. Motivated by a randomised clinical trial dataset on advanced melanoma patients, we propose a maximum penalised likelihood approach for fitting a semiparametric AFT model to survival data with partly interval-censored failure times. This method also accommodates both time-fixed and time-varying covariates. We utilise Gaussian basis functions to construct a smooth approximation of the non-parametric baseline hazard and fit the model using a constrained optimisation approach. The effectiveness of our method is demonstrated through extensive simulations. Finally, we illustrate the relevance of our approach by applying it to a dataset from a randomised clinical trial involving patients with advanced melanoma.

stat.ME↗

arXiv2024

Efficient MedSAMs: Segment Anything in Medical Images on Laptop

Promptable segmentation foundation models have emerged as a transformative approach to addressing the diverse needs in medical images, but most existing models require expensive computing, posing a big barrier to their adoption in clinical practice. In this work, we organized the first international competition dedicated to promptable medical image segmentation, featuring a large-scale dataset spanning nine common imaging modalities from over 20 different institutions. The top teams developed lightweight segmentation foundation models and implemented an efficient inference pipeline that substantially reduced computational requirements while maintaining state-of-the-art segmentation accuracy. Moreover, the post-challenge phase advanced the algorithms through the design of performance booster and reproducibility tasks, resulting in improved algorithms and validated reproducibility of the winning solution. Furthermore, the best-performing algorithms have been incorporated into the open-source software with a user-friendly interface to facilitate clinical adoption. The data and code are publicly available to foster the further development of medical image segmentation foundation models and pave the way for impactful real-world applications.

eess.IV↗