arXiv subjects

Chenxi Liu

Publications and source records attributed to Chenxi Liu.

At least 55 records · Page 3Linked to original sources

arXiv2025

Anatomical Region-Guided Contrastive Decoding: A Plug-and-Play Strategy for Mitigating Hallucinations in Medical VLMs

Medical Vision-Language Models (MedVLMs) show immense promise in clinical applicability. However, their reliability is hindered by hallucinations, where models often fail to derive answers from visual evidence, instead relying on learned textual priors. Existing mitigation strategies for MedVLMs have distinct limitations: training-based methods rely on costly expert annotations, limiting scalability, while training-free interventions like contrastive decoding, though data-efficient, apply a global, untargeted correction whose effects in complex real-world clinical settings can be unreliable. To address these challenges, we introduce Anatomical Region-Guided Contrastive Decoding (ARCD), a plug-and-play strategy that mitigates hallucinations by providing targeted, region-specific guidance. Our module leverages an anatomical mask to direct a three-tiered contrastive decoding process. By dynamically re-weighting at the token, attention, and logits levels, it verifiably steers the model's focus onto specified regions, reinforcing anatomical understanding and suppressing factually incorrect outputs. Extensive experiments across diverse datasets, including chest X-ray, CT, brain MRI, and ocular ultrasound, demonstrate our method's effectiveness in improving regional understanding, reducing hallucinations, and enhancing overall diagnostic accuracy.

cs.CV↗

arXiv2025

Language-Instructed Reasoning for Group Activity Detection via Multimodal Large Language Model

Group activity detection (GAD) aims to simultaneously identify group members and categorize their collective activities within video sequences. Existing deep learning-based methods develop specialized architectures (e.g., transformer networks) to model the dynamics of individual roles and semantic dependencies between individuals and groups. However, they rely solely on implicit pattern recognition from visual features and struggle with contextual reasoning and explainability. In this work, we propose LIR-GAD, a novel framework of language-instructed reasoning for GAD via Multimodal Large Language Model (MLLM). Our approach expand the original vocabulary of MLLM by introducing an activity-level token and multiple cluster-specific tokens. We process video frames alongside two specially designed tokens and language instructions, which are then integrated into the MLLM. The pretrained commonsense knowledge embedded in the MLLM enables the token and tokens to effectively capture the semantic information of collective activities and learn distinct representational features of different groups, respectively. Also, we introduce a multi-label classification loss to further enhance the token's ability to learn discriminative semantic representations. Then, we design a Multimodal Dual-Alignment Fusion (MDAF) module that integrates MLLM's hidden embeddings corresponding to the designed tokens with visual features, significantly enhancing the performance of GAD. Both quantitative and qualitative experiments demonstrate the superior performance of our proposed method in GAD taks.

cs.CV↗

arXiv2025

Batch Denoising for AIGC Service Provisioning in Wireless Edge Networks

Artificial intelligence-generated content (AIGC) service provisioning in wireless edge networks involves two phases: content generation on edge servers and content transmission to mobile devices. In this paper, we take image generation as a representative application and propose a batch denoising framework, followed by a joint optimization of content generation and transmission, with the objective of maximizing the average AIGC service quality under an end-to-end service delay constraint. Motivated by the empirical observations that (i) batch denoising effectively reduces per-step denoising delay by enhancing parallelism and (ii) early denoising steps have a greater impact on generation quality than later steps, we develop the STACKING algorithm to optimize batch denoising. The STACKING operates independently of any specific form of the content quality function and achieves lower computational complexity. Building on the batch solution, we further optimize bandwidth allocation across AIGC services. Simulation results demonstrate the superior performance of our algorithm in delivering high-quality, lower-latency AIGC services.

cs.DC↗

arXiv2025

Water induced bandgap engineering in nanoribbons of hexagonal boron nitride

Different from hexagonal boron nitride (hBN) sheets, the bandgap of hBN nanoribbons (BNNRs) can be changed by spatial/electrostatic confinement. It has been predicted that a transverse electric field can narrow the bandgap and even cause an insulator-metal transition in BNNRs. However, experimentally introducing an overhigh electric field across the BNNR remains challenging. Here, we theoretically and experimentally demonstrate that water adsorption greatly reduces bandgap of zigzag oriented BNNRs (zBNNRs). Ab initio calculations show that water adsorbed beside the BNNR induces a transverse equivalent electric field of over 2 V/nm thereby reducing its bandgap. Field effect transistors were successfully fabricated from zBNNRs with different widths. The conductance of zBNNRs with adsorbates of water could be tuned over 3 orders in magnitude via electrical field modulation at room temperature. Furthermore, photocurrent response measurements were taken to determine the optical bandgap in zBNNR. Wider zBNNRs exhibit a bandgap down to 1.17 eV. This study yields fundamental insights in new routes toward realizing electronic/optoelectronic devices and circuits based on hexagonal boron nitride.

cond-mat.mtrl-sci↗

arXiv2025

Pronounced scale-dependent charge carrier density in graphene quantum Hall devices

The miniaturization of quantum Hall resistance standards (QHRS) using epitaxial graphene on silicon carbide necessitates understanding how device dimensions impact performance. This study reveals a pronounced scale-dependent carrier density in graphene Hall devices: under electron doping, carrier density decreases with increasing channel width (Wd), while the opposite occurs under hole doping. This phenomenon, most significant for Wd less than 400 um, directly influences the onset of magnetic field required for quantization. Fermi velocity measurements and angle-resolved photoemission spectroscopy (ARPES) analysis indicate that band structure modifications and electron-electron interactions underlie this size dependence. Utilizing machine learning with limited data, we optimized the device geometry, identifying a channel width of ~360 um as the optimal balance between resistance uncertainty and on-chip integration density. This work provides key insights for designing high-performance, miniaturized graphene-based QHRS arrays.

cond-mat.mes-hall↗

arXiv2025

OpenVLN: Open-world Aerial Vision-Language Navigation

Vision-language models (VLMs) have been widely-applied in ground-based vision-language navigation (VLN). However, the vast complexity of outdoor aerial environments compounds data acquisition challenges and imposes long-horizon trajectory planning requirements on Unmanned Aerial Vehicles (UAVs), introducing novel complexities for aerial VLN. To address these challenges, we propose a data-efficient Open-world aerial Vision-Language Navigation (i.e., OpenVLN) framework, which could execute language-guided flight with limited data constraints and enhance long-horizon trajectory planning capabilities in complex aerial environments. Specifically, we reconfigure a reinforcement learning framework to optimize the VLM for UAV navigation tasks, which can efficiently fine-tune VLM by using rule-based policies under limited training data. Concurrently, we introduce a long-horizon planner for trajectory synthesis that dynamically generates precise UAV actions via value-based rewards. To the end, we conduct sufficient navigation experiments on the TravelUAV benchmark with dataset scaling across diverse reward settings. Our method demonstrates consistent performance gains of up to 4.34% in Success Rate, 6.19% in Oracle Success Rate, and 4.07% in Success weighted by Path Length over baseline methods, validating its deployment efficacy for long-horizon UAV navigation in complex aerial environments.

cs.RO↗

arXiv2025

Signatures of magnetism in zigzag graphene nanoribbon embedded in h-BN lattice

Zigzag edges of graphene have long been predicted to exhibit magnetic electronic state near the Fermi level, which can cause spin-related phenomena and offer unique potentials for graphene-based spintronics. However, the magnetic conduction channels along these edges have yet been reported experimentally. Here, we report the observation on signatures of magnetism in zigzag graphene nanoribbons (zGNRs) embedded in hexagonal boron nitride (h-BN). The in-plane bonding with BN can stabilize the edges of zGNRs, and thus enable a direct probing of the intrinsic magnetism. Firstly, the presence of magnetism of a zGNR was confirmed by scanning NV center microscopy. And then, zGNR was fabricated into a transistor with a width of ~9 nm wide and a channel length of sub-50 nm. By performing magneto-transport measurements, Fabry-Pérot interference patterns were observed in the transistor at 4 Kelvin, which indicates a coherent transport through the channel. A large magnetoresistance of ~175 Ω, corresponding to a ratio of ~1.3 %, was observed at the same temperature. More importantly, such magneto-transport signal is highly anisotropic on the magnetic field direction, and its appearance extends well above room temperature. All these evidences corroborate the existence of robust magnetic ordering in the edge state of zGNR. The findings on zGNR embedded in h-BN provide an effective platform for the future exploration of graphene-based spintronic devices.

cond-mat.mes-hall↗

arXiv2025

Nonequilibrium dynamics of membraneless active droplets

Membraneless droplets or liquid condensates formed via liquid-liquid phase separation (LLPS) play a pivotal role in cell biology and hold potential for biomedical engineering. While membraneless droplets are often studied in the context of interactions between passive components, it is increasingly recognized that active matter inclusions, such as molecular motors and catalytic enzymes in cells, play important roles in the formation, transport and interaction of membraneless droplets. Here we developed a bacteria-polymer active phase separation system to study the nonequilibrium effect of active matter inclusions on the LLPS dynamics. We found that the presence of bacterial active matter accelerated the initial condensation of phase-separated liquid droplets but subsequently arrested the droplet coarsening process, resulting in a stable suspension of membraneless active droplets packed with motile bacterial cells. The arrested phase separation of the bacterial active droplet system presumably arises from anti-phase entrainment of interface fluctuations between neighboring droplets, which reduces the frequency of inter-droplet contact and suppresses droplet coarsening. In addition, the active stresses generated by cells within the droplets give rise to an array of nonequilibrium phenomena, such as dominant long-wavelength fluctuations and enhanced droplet transport with short-term persistent motion due to spontaneous symmetry breaking. Our study reveals a unique mechanism for arrested phase separation and long-term stability in membraneless droplet systems. The bacteria-polymer active phase separation system opens a new avenue for studying the dynamics of membraneless active droplets relevant to non-equilibrium LLPS in cells and in biomedical engineering applications.

cond-mat.soft↗

arXiv2025

Explore Data Left Behind in Reinforcement Learning for Reasoning Language Models

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an effective approach for improving the reasoning abilities of large language models (LLMs). The Group Relative Policy Optimization (GRPO) family has demonstrated strong performance in training LLMs with RLVR. However, as models train longer and scale larger, more training prompts become residual prompts, those with zero variance rewards that provide no training signal. Consequently, fewer prompts contribute to training, reducing diversity and hindering effectiveness. To fully exploit these residual prompts, we propose the Explore Residual Prompts in Policy Optimization (ERPO) framework, which encourages exploration on residual prompts and reactivates their training signals. ERPO maintains a history tracker for each prompt and adaptively increases the sampling temperature for residual prompts that previously produced all correct responses. This encourages the model to generate more diverse reasoning traces, introducing incorrect responses that revive training signals. Empirical results on the Qwen2.5 series demonstrate that ERPO consistently surpasses strong baselines across multiple mathematical reasoning benchmarks.

cs.CL↗

arXiv2025

Discovering and Reasoning of Causality in the Hidden World with Large Language Models

Revealing hidden causal variables alongside the underlying causal mechanisms is essential to the development of science. Despite the progress in the past decades, existing practice in causal discovery (CD) heavily relies on high-quality measured variables, which are usually given by human experts. In fact, the lack of well-defined high-level variables behind unstructured data has been a longstanding roadblock to a broader real-world application of CD. This procedure can naturally benefit from an automated process that can suggest potential hidden variables in the system. Interestingly, Large language models (LLMs) are trained on massive observations of the world and have demonstrated great capability in processing unstructured data. To leverage the power of LLMs, we develop a new framework termed Causal representatiOn AssistanT (COAT) that incorporates the rich world knowledge of LLMs to propose useful measured variables for CD with respect to high-value target variables on their paired unstructured data. Instead of directly inferring causality with LLMs, COAT constructs feedback from intermediate CD results to LLMs to refine the proposed variables. Given the target variable and the paired unstructured data, we first develop COAT-MB that leverages the predictivity of the proposed variables to iteratively uncover the Markov Blanket of the target variable. Built upon COAT-MB, COAT-PAG further extends to uncover a more complete causal graph, i.e., Partial Ancestral Graph, by iterating over the target variables and actively seeking new high-level variables. Moreover, the reliable CD capabilities of COAT also extend the debiased causal inference to unstructured data by discovering an adjustment set. We establish theoretical guarantees for the CD results and verify their efficiency and reliability across realistic benchmarks and real-world case studies.

cs.LG↗

arXiv2025

Modality-Balancing Preference Optimization of Large Multimodal Models by Adversarial Negative Mining

The task adaptation and alignment of Large Multimodal Models (LMMs) have been significantly advanced by instruction tuning and further strengthened by recent preference optimization. Yet, most LMMs still suffer from severe modality imbalance during reasoning, i.e., outweighing language prior biases over visual inputs, which bottlenecks their generalization to downstream tasks and causes hallucinations. However, existing preference optimization approaches for LMMs do not focus on restraining the internal biases of their Large Language Model (LLM) backbones when curating the training data. Moreover, they heavily rely on offline data and lack the capacity to explore diverse responses adaptive to dynamic distributional shifts during training. Meanwhile, Group Relative Policy Optimization (GRPO), a recent method using online-generated data and verified rewards to improve reasoning capabilities, remains largely underexplored in LMM alignment. In this paper, we propose a novel preference learning framework, Modality-Balancing Preference Optimization (MBPO), to address the modality imbalance in LMMs. MBPO constructs a more effective offline preference dataset by generating hard negatives, i.e., rejected responses misled by LLM biases due to limited usage of visual information, through adversarial perturbation of input images. Moreover, MBPO leverages the easy-to-verify nature of close-ended tasks to generate online responses with verified rewards. GRPO is then employed to train the model with offline-online hybrid data. Extensive experiments demonstrate that MBPO can enhance LMM performance on challenging vision-language tasks and effectively reduce hallucinations.

cs.LG↗

arXiv2025

V2X-UniPool: Unifying Multimodal Perception and Knowledge Reasoning for Autonomous Driving

Autonomous driving (AD) has achieved significant progress, yet single-vehicle perception remains constrained by sensing range and occlusions. Vehicle-to-Everything (V2X) communication addresses these limits by enabling collaboration across vehicles and infrastructure, but it also faces heterogeneity, synchronization, and latency constraints. Language models offer strong knowledge-driven reasoning and decision-making capabilities, but they are not inherently designed to process raw sensor streams and are prone to hallucination. We propose V2X-UniPool, the first framework that unifies V2X perception with language-based reasoning for knowledge-driven AD. It transforms multimodal V2X data into structured, language-based knowledge, organizes it in a time-indexed knowledge pool for temporally consistent reasoning, and employs Retrieval-Augmented Generation (RAG) to ground decisions in real-time context. Experiments on the real-world DAIR-V2X dataset show that V2X-UniPool achieves state-of-the-art planning accuracy and safety while reducing communication cost by more than 80\%, achieving the lowest overhead among evaluated methods. These results highlight the promise of bridging V2X perception and language reasoning to advance scalable and trustworthy driving. Our code is available at: https://github.com/Xuewen2025/V2X-UniPool

cs.AI↗

arXiv2025

STRATA-TS: Selective Knowledge Transfer for Urban Time Series Forecasting with Retrieval-Guided Reasoning

Urban forecasting models often face a severe data imbalance problem: only a few cities have dense, long-span records, while many others expose short or incomplete histories. Direct transfer from data-rich to data-scarce cities is unreliable because only a limited subset of source patterns truly benefits the target domain, whereas indiscriminate transfer risks introducing noise and negative transfer. We present STRATA-TS (Selective TRAnsfer via TArget-aware retrieval for Time Series), a framework that combines domain-adapted retrieval with reasoning-capable large models to improve forecasting in scarce data regimes. STRATA-TS employs a patch-based temporal encoder to identify source subsequences that are semantically and dynamically aligned with the target query. These retrieved exemplars are then injected into a retrieval-guided reasoning stage, where an LLM performs structured inference over target inputs and retrieved support. To enable efficient deployment, we distill the reasoning process into a compact open model via supervised fine-tuning. Extensive experiments on three parking availability datasets across Singapore, Nottingham, and Glasgow demonstrate that STRATA-TS consistently outperforms strong forecasting and transfer baselines, while providing interpretable knowledge transfer pathways.

cs.LG↗

arXiv2025

Traffic Co-Simulation Framework Empowered by Infrastructure Camera Sensing and Reinforcement Learning

Traffic simulations are commonly used to optimize urban traffic flow, with reinforcement learning (RL) showing promising potential for automated traffic signal control, particularly in intelligent transportation systems involving connected automated vehicles. Multi-agent reinforcement learning (MARL) is particularly effective for learning control strategies for traffic lights in a network using iterative simulations. However, existing methods often assume perfect vehicle detection, which overlooks real-world limitations related to infrastructure availability and sensor reliability. This study proposes a co-simulation framework integrating CARLA and SUMO, which combines high-fidelity 3D modeling with large-scale traffic flow simulation. Cameras mounted on traffic light poles within the CARLA environment use a YOLO-based computer vision system to detect and count vehicles, providing real-time traffic data as input for adaptive signal control in SUMO. MARL agents trained with four different reward structures leverage this visual feedback to optimize signal timings and improve network-wide traffic flow. Experiments in a multi-intersection test-bed demonstrate the effectiveness of the proposed MARL approach in enhancing traffic conditions using real-time camera based detection. The framework also evaluates the robustness of MARL under faulty or sparse sensing and compares the performance of YOLOv5 and YOLOv8 for vehicle detection. Results show that while better accuracy improves performance, MARL agents can still achieve significant improvements with imperfect detection, demonstrating scalability and adaptability for real-world scenarios.

eess.SY↗

arXiv2025

Mesh Processing Non-Meshes via Neural Displacement Fields

Mesh processing pipelines are mature, but adapting them to newer non-mesh surface representations -- which enable fast rendering with compact file size -- requires costly meshing or transmitting bulky meshes, negating their core benefits for streaming applications. We present a compact neural field that enables common geometry processing tasks across diverse surface representations. Given an input surface, our method learns a neural map from its coarse mesh approximation to the surface. The full representation totals only a few hundred kilobytes, making it ideal for lightweight transmission. Our method enables fast extraction of manifold and Delaunay meshes for intrinsic shape analysis, and compresses scalar fields for efficient delivery of costly precomputed results. Experiments and applications show that our fast, compact, and accurate approach opens up new possibilities for interactive geometry processing.

cs.GR↗

arXiv2025

Edge-Based Multimodal Sensor Data Fusion with Vision Language Models (VLMs) for Real-time Autonomous Vehicle Accident Avoidance

Autonomous driving (AD) systems relying solely on onboard sensors may fail to detect distant or obstacle hazards, potentially causing preventable collisions; however, existing transformer-based Vehicle-to-Everything (V2X) approaches, which mitigate AD sensing limitations, either lack effective multimodal fusion and reasoning or struggle to meet real-time performance requirements under complex, high-dimensional traffic conditions. This paper proposes the Real-time Edge-based Autonomous Co-pilot Trajectory planner (REACT), a V2X-integrated trajectory optimization framework for AD based on a fine-tuned lightweight Vision-Language Model (VLM). REACT integrates infrastructure-provided hazard alerts with onboard sensor data, capturing intricate surrounding traffic dynamics and vehicle intents through visual embeddings, interpreting precise numerical data from symbolic inputs, and employing contextual reasoning to generate optimized, safety-oriented trajectories. To ensure robust real-time deployment on edge devices, REACT innovatively employs Residual Trajectory Fusion (RTF) design and specialized edge-adaptation strategies to reduce model complexity and improve inference efficiency. Evaluated on the DeepAccident benchmark, REACT achieves state-of-the-art performance, a 77% collision rate reduction, a 48.2% Video Panoptic Quality (VPQ), and a 0.57-second inference latency on the Jetson AGX Orin. Ablation studies validate the contribution of each input, module, and edge adaptation strategy. These results highlight the effectiveness of lightweight VLMs in enabling real-time cooperative planning on edge platforms and underscore the potential of language-guided contextual reasoning for improving traffic safety and responsiveness.

cs.AI↗

arXiv2025

SAMITE: Position Prompted SAM2 with Calibrated Memory for Visual Object Tracking

Visual Object Tracking (VOT) is widely used in applications like autonomous driving to continuously track targets in videos. Existing methods can be roughly categorized into template matching and autoregressive methods, where the former usually neglects the temporal dependencies across frames and the latter tends to get biased towards the object categories during training, showing weak generalizability to unseen classes. To address these issues, some methods propose to adapt the video foundation model SAM2 for VOT, where the tracking results of each frame would be encoded as memory for conditioning the rest of frames in an autoregressive manner. Nevertheless, existing methods fail to overcome the challenges of object occlusions and distractions, and do not have any measures to intercept the propagation of tracking errors. To tackle them, we present a SAMITE model, built upon SAM2 with additional modules, including: (1) Prototypical Memory Bank: We propose to quantify the feature-wise and position-wise correctness of each frame's tracking results, and select the best frames to condition subsequent frames. As the features of occluded and distracting objects are feature-wise and position-wise inaccurate, their scores would naturally be lower and thus can be filtered to intercept error propagation; (2) Positional Prompt Generator: To further reduce the impacts of distractors, we propose to generate positional mask prompts to provide explicit positional clues for the target, leading to more accurate tracking. Extensive experiments have been conducted on six benchmarks, showing the superiority of SAMITE. The code is available at https://github.com/Sam1224/SAMITE.

cs.CV↗

arXiv2025

EV-STLLM: Electric vehicle charging forecasting based on spatio-temporal large language models with multi-frequency and multi-scale information fusion

With the proliferation of electric vehicles (EVs), accurate charging demand and station occupancy forecasting are critical for optimizing urban energy and the profit of EVs aggregator. Existing approaches in this field usually struggle to capture the complex spatio-temporal dependencies in EV charging behaviors, and their limited model parameters hinder their ability to learn complex data distribution representations from large datasets. To this end, we propose a novel EV spatio-temporal large language model (EV-STLLM) for accurate prediction. Our proposed framework is divided into two modules. In the data processing module, we utilize variational mode decomposition (VMD) for data denoising, and improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) for data multi-frequency decomposition. Fuzzy information granulation (FIG) for extracting multi-scale information. Additionally, ReliefF is used for feature selection to mitigate redundancy. In the forecasting module, the EV-STLLM is used to directly achieve EV charging and occupancy forecasting. Firstly, we fully capture the intrinsic spatio-temporal characteristics of the data by integrating adjacency matrices derived from the regional stations network and spatio-temporal-frequency embedding information. Then, the partially frozen graph attention (PFGA) module is utilized to maintain the sequential feature modeling capabilities of the pre-trained large model while incorporating EV domain knowledge. Extensive experiments using real-world data from Shenzhen, China, demonstrate that our proposed framework can achieve superior accuracy and robustness compared to the state-of-the-art benchmarks.

cs.CE↗