arXiv subjects

Pin Lv

Publications and source records attributed to Pin Lv.

12 recordsLinked to original sources

arXiv2026

CERF: Communication-Efficient and Retraining-Free Collaborative Perception

Collaborative perception shares information among multiple agents to obtain a comprehensive scene representation, enhancing the perceptual capability of individual agents. However, most existing methods rely on transmitting and fusing dense feature maps for collaboration, which incurs inevitable communication overhead and heterogeneity challenges, limiting their practicality for real-world deployment. To address these challenges, we propose CERF, a novel Communication-Efficient and Retraining-Free framework for open heterogeneous collaborative perception. In CERF, we introduce a new virtual modality (termed Poture), which is generated from the perception outputs of other agents, to augment the extracted Bird's Eye View (BEV) features of the ego agent. To mitigate transmission delays, we employ a Kalman-filter based tracker and a motion forecasting model to derive the current predictions from historical perception results. Extensive experiments demonstrate that CERF achieves performance comparable to mainstream intermediate-collaboration methods while reducing communication overhead by 95% across various downstream tasks. Furthermore, CERF enables seamless integration of unknown heterogeneous agents into the existing collaborative framework without additional retraining costs. Code is available at https://github.com/uestchjw/CERF.

cs.CV↗

arXiv2025

Breaking the MoE LLM Trilemma: Dynamic Expert Clustering with Structured Compression

Mixture-of-Experts (MoE) Large Language Models (LLMs) face a trilemma of load imbalance, parameter redundancy, and communication overhead. We introduce a unified framework based on dynamic expert clustering and structured compression to address these issues cohesively. Our method employs an online clustering procedure that periodically regroups experts using a fused metric of parameter and activation similarity, which stabilizes expert utilization. To our knowledge, this is one of the first frameworks to leverage the semantic embedding capability of the router to dynamically reconfigure the model's architecture during training for substantial efficiency gains. Within each cluster, we decompose expert weights into a shared base matrix and extremely low-rank residual adapters, achieving up to fivefold parameter reduction per group while preserving specialization. This structure enables a two-stage hierarchical routing strategy: tokens are first assigned to a cluster, then to specific experts within it, drastically reducing the routing search space and the volume of all-to-all communication. Furthermore, a heterogeneous precision scheme, which stores shared bases in FP16 and residual factors in INT4, coupled with dynamic offloading of inactive clusters, reduces peak memory consumption to levels comparable to dense models. Evaluated on GLUE and WikiText-103, our framework matches the quality of standard MoE models while reducing total parameters by approximately 80%, improving throughput by 10% to 20%, and lowering expert load variance by a factor of over three. Our work demonstrates that structural reorganization is a principled path toward scalable, efficient, and memory-effective MoE LLMs. Code is available at https://github.com/szdtzpj/Breaking_the_moe_trilemma

cs.CL↗

arXiv2025

Proactive Constrained Policy Optimization with Preemptive Penalty

Safe Reinforcement Learning (RL) often faces significant issues such as constraint violations and instability, necessitating the use of constrained policy optimization, which seeks optimal policies while ensuring adherence to specific constraints like safety. Typically, constrained optimization problems are addressed by the Lagrangian method, a post-violation remedial approach that may result in oscillations and overshoots. Motivated by this, we propose a novel method named Proactive Constrained Policy Optimization (PCPO) that incorporates a preemptive penalty mechanism. This mechanism integrates barrier items into the objective function as the policy nears the boundary, imposing a cost. Meanwhile, we introduce a constraint-aware intrinsic reward to guide boundary-aware exploration, which is activated only when the policy approaches the constraint boundary. We establish theoretical upper and lower bounds for the duality gap and the performance of the PCPO update, shedding light on the method's convergence characteristics. Additionally, to enhance the optimization performance, we adopt a policy iteration approach. An interesting finding is that PCPO demonstrates significant stability in experiments. Experimental results indicate that the PCPO framework provides a robust solution for policy optimization under constraints, with important implications for future research and practical applications.

cs.LG↗

arXiv2025

Is Intermediate Fusion All You Need for UAV-based Collaborative Perception?

Collaborative perception enhances environmental awareness through inter-agent communication and is regarded as a promising solution to intelligent transportation systems. However, existing collaborative methods for Unmanned Aerial Vehicles (UAVs) overlook the unique characteristics of the UAV perspective, resulting in substantial communication overhead. To address this issue, we propose a novel communication-efficient collaborative perception framework based on late-intermediate fusion, dubbed LIF. The core concept is to exchange informative and compact detection results and shift the fusion stage to the feature representation level. In particular, we leverage vision-guided positional embedding (VPE) and box-based virtual augmented feature (BoBEV) to effectively integrate complementary information from various agents. Additionally, we innovatively introduce an uncertainty-driven communication mechanism that uses uncertainty evaluation to select high-quality and reliable shared areas. Experimental results demonstrate that our LIF achieves superior performance with minimal communication bandwidth, proving its effectiveness and practicality. Code and models are available at https://github.com/uestchjw/LIF.

cs.CV↗

arXiv2025

FeaKM: Robust Collaborative Perception under Noisy Pose Conditions

Collaborative perception is essential for networks of agents with limited sensing capabilities, enabling them to work together by exchanging information to achieve a robust and comprehensive understanding of their environment. However, localization inaccuracies often lead to significant spatial message displacement, which undermines the effectiveness of these collaborative efforts. To tackle this challenge, we introduce FeaKM, a novel method that employs Feature-level Keypoints Matching to effectively correct pose discrepancies among collaborating agents. Our approach begins by utilizing a confidence map to identify and extract salient points from intermediate feature representations, allowing for the computation of their descriptors. This step ensures that the system can focus on the most relevant information, enhancing the matching process. We then implement a target-matching strategy that generates an assignment matrix, correlating the keypoints identified by different agents. This is critical for establishing accurate correspondences, which are essential for effective collaboration. Finally, we employ a fine-grained transformation matrix to synchronize the features of all agents and ascertain their relative statuses, ensuring coherent communication among them. Our experimental results demonstrate that FeaKM significantly outperforms existing methods on the DAIR-V2X dataset, confirming its robustness even under severe noise conditions. The code and implementation details are available at https://github.com/uestchjw/FeaKM.

cs.CV↗

arXiv2024

Tree-of-Code: A Tree-Structured Exploring Framework for End-to-End Code Generation and Execution in Complex Task Handling

Solving complex reasoning tasks is a key real-world application of agents. Thanks to the pretraining of Large Language Models (LLMs) on code data, recent approaches like CodeAct successfully use code as LLM agents' action, achieving good results. However, CodeAct greedily generates the next action's code block by relying on fragmented thoughts, resulting in inconsistency and instability. Moreover, CodeAct lacks action-related ground-truth (GT), making its supervision signals and termination conditions questionable in multi-turn interactions. To address these issues, we first introduce a simple yet effective end-to-end code generation paradigm, CodeProgram, which leverages code's systematic logic to align with global reasoning and enable cohesive problem-solving. Then, we propose Tree-of-Code (ToC), which self-grows CodeProgram nodes based on the executable nature of the code and enables self-supervision in a GT-free scenario. Experimental results on two datasets using ten popular zero-shot LLMs show ToC remarkably boosts accuracy by nearly 20% over CodeAct with less than 1/4 turns. Several LLMs even perform better on one-turn CodeProgram than on multi-turn CodeAct. To further investigate the trade-off between efficacy and efficiency, we test different ToC tree sizes and exploration mechanisms. We also highlight the potential of ToC's end-to-end data generation for supervised and reinforced fine-tuning.

cs.SE↗

arXiv2024

Tracing Human Stress from Physiological Signals using UWB Radar

Stress tracing is an important research domain that supports many applications, such as health care and stress management; and its closest related works are derived from stress detection. However, these existing works cannot well address two important challenges facing stress detection. First, most of these studies involve asking users to wear physiological sensors to detect their stress states, which has a negative impact on the user experience. Second, these studies have failed to effectively utilize multimodal physiological signals, which results in less satisfactory detection results. This paper formally defines the stress tracing problem, which emphasizes the continuous detection of human stress states. A novel deep stress tracing method, named DST, is presented. Note that DST proposes tracing human stress based on physiological signals collected by a noncontact ultrawideband radar, which is more friendly to users when collecting their physiological signals. In DST, a signal extraction module is carefully designed at first to robustly extract multimodal physiological signals from the raw RF data of the radar, even in the presence of body movement. Afterward, a multimodal fusion module is proposed in DST to ensure that the extracted multimodal physiological signals can be effectively fused and utilized. Extensive experiments are conducted on three real-world datasets, including one self-collected dataset and two publicity datasets. Experimental results show that the proposed DST method significantly outperforms all the baselines in terms of tracing human stress states. On average, DST averagely provides a 6.31% increase in detection accuracy on all datasets, compared with the best baselines.

cs.HC↗

arXiv2024

MERIT: Multimodal Wearable Vital Sign Waveform Monitoring

Cardiovascular disease (CVD) is the leading cause of death and premature mortality worldwide, with occupational environments significantly influencing CVD risk, underscoring the need for effective cardiac monitoring and early warning systems. Existing methods of monitoring vital signs require subjects to remain stationary, which is impractical for daily monitoring as individuals are often in motion. To address this limitation, we propose MERIT, a multimodality-based wearable system designed for precise ECG waveform monitoring without movement restrictions. Daily activities, involving frequent arm movements, can significantly affect sensor data and complicate the reconstruction of accurate ECG signals. To mitigate motion impact and enhance ECG signal reconstruction, we introduce a deep independent component analysis (Deep-ICA) module and a multimodal fusion module. We conducted experiments with 15 subjects. Our results, compared with commercial wearable devices and existing methods, demonstrate that MERIT accurately reconstructs ECG waveforms during various office activities, offering a reliable solution for fine-grained cardiac monitoring in dynamic environments.

eess.SY↗

arXiv2024

Utilizing Quantum Processor for the Analysis of Strongly Correlated Materials

This study introduces a systematic approach for analyzing strongly correlated systems by adapting the conventional quantum cluster method to a quantum circuit model. We have developed a more concise formula for calculating the cluster's Green's function, requiring only real-number computations on the quantum circuit instead of complex ones. This approach is inherently more suited to quantum circuits, which primarily yield statistical probabilities. As an illustrative example, we explored the Hubbard model on a 2D lattice. The ground state is determined utilizing Xiaohong, a superconducting quantum processor equipped with 66 qubits, supplied by QuantumCTek Co., Ltd. Subsequently, we employed the circuit model to compute the real-time retarded Green's function for the cluster, which is then used to determine the lattice Green's function. We conducted an examination of the band structure in the insulator phase of the lattice system. This preliminary investigation lays the groundwork for exploring a wealth of innovative physics within the field of condensed matter physics.

quant-ph↗

arXiv2023

VILAS: Exploring the Effects of Vision and Language Context in Automatic Speech Recognition

Enhancing automatic speech recognition (ASR) performance by leveraging additional multimodal information has shown promising results in previous studies. However, most of these works have primarily focused on utilizing visual cues derived from human lip motions. In fact, context-dependent visual and linguistic cues can also benefit in many scenarios. In this paper, we first propose ViLaS (Vision and Language into Automatic Speech Recognition), a novel multimodal ASR model based on the continuous integrate-and-fire (CIF) mechanism, which can integrate visual and textual context simultaneously or separately, to facilitate speech recognition. Next, we introduce an effective training strategy that improves performance in modal-incomplete test scenarios. Then, to explore the effects of integrating vision and language, we create VSDial, a multimodal ASR dataset with multimodal context cues in both Chinese and English versions. Finally, empirical results are reported on the public Flickr8K and self-constructed VSDial datasets. We explore various cross-modal fusion schemes, analyze fine-grained crossmodal alignment on VSDial, and provide insights into the effects of integrating multimodal information on speech recognition.

eess.AS↗

arXiv2017

Using Argument-based Features to Predict and Analyse Review Helpfulness

We study the helpful product reviews identification problem in this paper. We observe that the evidence-conclusion discourse relations, also known as arguments, often appear in product reviews, and we hypothesise that some argument-based features, e.g. the percentage of argumentative sentences, the evidences-conclusions ratios, are good indicators of helpful reviews. To validate this hypothesis, we manually annotate arguments in 110 hotel reviews, and investigate the effectiveness of several combinations of argument-based features. Experiments suggest that, when being used together with the argument-based features, the state-of-the-art baseline features can enjoy a performance boost (in terms of F1) of 11.01\% in average.

cs.CL↗

arXiv2017

The low temperature performance of CsI(Na) crystals for WIPMs direct searches

Previous studies showed that CsI(Na) crystals have significantly different waveforms between alpha and gamma scintillations. In this work, the light yield and PSD capability of CsI(Na) scintillators as a function of the temperature down to 80 K has been studied. As temperature drops, the fast component rises and the slow component decreases. By cooling the CsI(Na) crystals, the light yield of high ionization events are enhanced significantly, while the light yield of background gamma events are suppressed. At 110 K, CsI(Na) crystal achieves the optimal balance between low threshold and good background rejection performance. The different responses of CsI(Na) to gamma and alpha at different temperatures are explained with self-trapped and activator luminescence centers.

physics.ins-det↗