arXiv subjects

Hongwei Zhang

Publications and source records attributed to Hongwei Zhang.

At least 37 records · Page 2Linked to original sources

arXiv2025

ChromFound: Towards A Universal Foundation Model for Single-Cell Chromatin Accessibility Data

The advent of single-cell Assay for Transposase-Accessible Chromatin using sequencing (scATAC-seq) offers an innovative perspective for deciphering regulatory mechanisms by assembling a vast repository of single-cell chromatin accessibility data. While foundation models have achieved significant success in single-cell transcriptomics, there is currently no foundation model for scATAC-seq that supports zero-shot high-quality cell identification and comprehensive multi-omics analysis simultaneously. Key challenges lie in the high dimensionality and sparsity of scATAC-seq data, as well as the lack of a standardized schema for representing open chromatin regions (OCRs). Here, we present ChromFound, a foundation model tailored for scATAC-seq. ChromFound utilizes a hybrid architecture and genome-aware tokenization to effectively capture genome-wide long contexts and regulatory signals from dynamic chromatin landscapes. Pretrained on 1.97 million cells from 30 tissues and 6 disease conditions, ChromFound demonstrates broad applicability across 6 diverse tasks. Notably, it achieves robust zero-shot performance in generating universal cell representations and exhibits excellent transferability in cell type annotation and cross-omics prediction. By uncovering enhancer-gene links undetected by existing computational methods, ChromFound offers a promising framework for understanding disease risk variants in the noncoding genome.

q-bio.GN↗

arXiv2025

Co-Sight: Enhancing LLM-Based Agents via Conflict-Aware Meta-Verification and Trustworthy Reasoning with Structured Facts

Long-horizon reasoning in LLM-based agents often fails not from generative weakness but from insufficient verification of intermediate reasoning. Co-Sight addresses this challenge by turning reasoning into a falsifiable and auditable process through two complementary mechanisms: Conflict-Aware Meta-Verification (CAMV) and Trustworthy Reasoning with Structured Facts (TRSF). CAMV reformulates verification as conflict identification and targeted falsification, allocating computation only to disagreement hotspots among expert agents rather than to full reasoning chains. This bounds verification cost to the number of inconsistencies and improves efficiency and reliability. TRSF continuously organizes, validates, and synchronizes evidence across agents through a structured facts module. By maintaining verified, traceable, and auditable knowledge, it ensures that all reasoning is grounded in consistent, source-verified information and supports transparent verification throughout the reasoning process. Together, TRSF and CAMV form a closed verification loop, where TRSF supplies structured facts and CAMV selectively falsifies or reinforces them, yielding transparent and trustworthy reasoning. Empirically, Co-Sight achieves state-of-the-art accuracy on GAIA (84.4%) and Humanity's Last Exam (35.5%), and strong results on Chinese-SimpleQA (93.8%). Ablation studies confirm that the synergy between structured factual grounding and conflict-aware verification drives these improvements. Co-Sight thus offers a scalable paradigm for reliable long-horizon reasoning in LLM-based agents. Code is available at https://github.com/ZTE-AICloud/Co-Sight/tree/cosight2.0_benchmarks.

cs.AI↗

arXiv2025

HetaRAG: Hybrid Deep Retrieval-Augmented Generation across Heterogeneous Data Stores

Retrieval-augmented generation (RAG) has become a dominant paradigm for mitigating knowledge hallucination and staleness in large language models (LLMs) while preserving data security. By retrieving relevant evidence from private, domain-specific corpora and injecting it into carefully engineered prompts, RAG delivers trustworthy responses without the prohibitive cost of fine-tuning. Traditional retrieval-augmented generation (RAG) systems are text-only and often rely on a single storage backend, most commonly a vector database. In practice, this monolithic design suffers from unavoidable trade-offs: vector search captures semantic similarity yet loses global context; knowledge graphs excel at relational precision but struggle with recall; full-text indexes are fast and exact yet semantically blind; and relational engines such as MySQL provide strong transactional guarantees but no semantic understanding. We argue that these heterogeneous retrieval paradigms are complementary, and propose a principled fusion scheme to orchestrate them synergistically, mitigating the weaknesses of any single modality. In this work we introduce HetaRAG, a hybrid, deep-retrieval augmented generation framework that orchestrates cross-modal evidence from heterogeneous data stores. We plan to design a system that unifies vector indices, knowledge graphs, full-text engines, and structured databases into a single retrieval plane, dynamically routing and fusing evidence to maximize recall, precision, and contextual fidelity. To achieve this design goal, we carried out preliminary explorations and constructed an initial RAG pipeline; this technical report provides a brief overview. The partial code is available at https://github.com/KnowledgeXLab/HetaRAG.

cs.IR↗

arXiv2025

Prompt-based Multimodal Semantic Communication for Multi-spectral Image Segmentation

Multimodal semantic communication has gained widespread attention due to its ability to enhance downstream task performance. A key challenge in such systems is the effective fusion of features from different modalities, which requires the extraction of rich and diverse semantic representations from each modality. To this end, we propose ProMSC-MIS, a Prompt-based Multimodal Semantic Communication system for Multi-spectral Image Segmentation. Specifically, we propose a pre-training algorithm where features from one modality serve as prompts for another, guiding unimodal semantic encoders to learn diverse and complementary semantic representations. We further introduce a semantic fusion module that combines cross-attention mechanisms and squeeze-and-excitation (SE) networks to effectively fuse cross-modal features. Simulation results show that ProMSC-MIS significantly outperforms benchmark methods across various channel-source compression levels, while maintaining low computational complexity and storage overhead. Our scheme has great potential for applications such as autonomous driving and nighttime surveillance.

eess.IV↗

arXiv2025

Efficient Network Automatic Relevance Determination

We propose Network Automatic Relevance Determination (NARD), an extension of ARD for linearly probabilistic models, to simultaneously model sparse relationships between inputs $X \in \mathbb R^{d \times N}$ and outputs $Y \in \mathbb R^{m \times N}$, while capturing the correlation structure among the $Y$. NARD employs a matrix normal prior which contains a sparsity-inducing parameter to identify and discard irrelevant features, thereby promoting sparsity in the model. Algorithmically, it iteratively updates both the precision matrix and the relationship between $Y$ and the refined inputs. To mitigate the computational inefficiencies of the $\mathcal O(m^3 + d^3)$ cost per iteration, we introduce Sequential NARD, which evaluates features sequentially, and a Surrogate Function Method, leveraging an efficient approximation of the marginal likelihood and simplifying the calculation of determinant and inverse of an intermediate matrix. Combining the Sequential update with the Surrogate Function method further reduces computational costs. The computational complexity per iteration for these three methods is reduced to $\mathcal O(m^3+p^3)$, $\mathcal O(m^3 + d^2)$, $\mathcal O(m^3+p^2)$, respectively, where $p \ll d$ is the final number of features in the model. Our methods demonstrate significant improvements in computational efficiency with comparable performance on both synthetic and real-world datasets.

cs.AI↗

arXiv2025

Reinforcement learning in pursuit-evasion differential game: safety, stability and robustness

Safety and stability are two critical concerns in pursuit-evasion (PE) problems in an obstacle-rich environment. Most existing works combine control barrier functions (CBFs) and reinforcement learning (RL) to provide an efficient and safe solution. However, they do not consider the presence of disturbances, such as wind gust and actuator fault, which may exist in many practical applications. This paper integrates CBFs and a sliding mode control (SMC) term into RL to simultaneously address safety, stability, and robustness to disturbances. However, this integration is significantly challenging due to the strong coupling between the CBF and SMC terms. Inspired by Stackelberg game, we handle the coupling issue by proposing a hierarchical design scheme where SMC and safe control terms interact with each other in a leader-follower manner. Specifically, the CBF controller, acting as the leader, enforces safety independently of the SMC design; while the SMC term, as the follower, is designed based on the CBF controller. We then formulate the PE problem as a zero-sum game and propose a safe robust RL framework to learn the min-max strategy online. A sufficient condition is provided under which the proposed algorithm remains effective even when constraints are conflicting. Simulation results demonstrate the effectiveness of the proposed safe robust RL framework.

eess.SY↗

arXiv2025

Refine Medical Diagnosis Using Generation Augmented Retrieval and Clinical Practice Guidelines

Current medical language models, adapted from large language models (LLMs), typically predict ICD code-based diagnosis from electronic health records (EHRs) because these labels are readily available. However, ICD codes do not capture the nuanced, context-rich reasoning clinicians use for diagnosis. Clinicians synthesize diverse patient data and reference clinical practice guidelines (CPGs) to make evidence-based decisions. This misalignment limits the clinical utility of existing models. We introduce GARMLE-G, a Generation-Augmented Retrieval framework that grounds medical language model outputs in authoritative CPGs. Unlike conventional Retrieval-Augmented Generation based approaches, GARMLE-G enables hallucination-free outputs by directly retrieving authoritative guideline content without relying on model-generated text. It (1) integrates LLM predictions with EHR data to create semantically rich queries, (2) retrieves relevant CPG knowledge snippets via embedding similarity, and (3) fuses guideline content with model output to generate clinically aligned recommendations. A prototype system for hypertension diagnosis was developed and evaluated on multiple metrics, demonstrating superior retrieval precision, semantic relevance, and clinical guideline adherence compared to RAG-based baselines, while maintaining a lightweight architecture suitable for localized healthcare deployment. This work provides a scalable, low-cost, and hallucination-free method for grounding medical language models in evidence-based clinical practice, with strong potential for broader clinical deployment.

cs.CL↗

arXiv2025

Fast on the Easy, Deep on the Hard: Efficient Reasoning via Powered Length Penalty

Large language models (LLMs) have demonstrated significant advancements in reasoning capabilities, performing well on various challenging benchmarks. Techniques like Chain-of-Thought prompting have been introduced to further improve reasoning. However, these approaches frequently generate longer outputs, which in turn increase computational latency. Although some methods use reinforcement learning to shorten reasoning, they often apply uniform penalties without considering the problem's complexity, leading to suboptimal outcomes. In this study, we seek to enhance the efficiency of LLM reasoning by promoting conciseness for simpler problems while preserving sufficient reasoning for more complex ones for accuracy, thus improving the model's overall performance. Specifically, we manage the model's reasoning efficiency by dividing the reward function and including a novel penalty for output length. Our approach has yielded impressive outcomes in benchmark evaluations across three datasets: GSM8K, MATH500, and AIME2024. For the comparatively simpler datasets GSM8K and MATH500, our method has effectively shortened output lengths while preserving or enhancing accuracy. On the more demanding AIME2024 dataset, our approach has resulted in improved accuracy.

cs.CL↗

arXiv2025

Design and Implementation of ARA Wireless Living Lab for Rural Broadband and Applications

Addressing the broadband gap between rural and urban regions requires rural-focused wireless research and innovation. In the meantime, rural regions provide rich, diverse use cases of advanced wireless, and they offer unique real-world settings for piloting applications that advance the frontiers of wireless systems (e.g., teleoperation of ground and aerial vehicles). To fill the broadband gap and to leverage the unique opportunities that rural regions provide for piloting advanced wireless applications, we design and implement the ARA wireless living lab for research and innovation in rural wireless systems and their applications in precision agriculture, community services, and so on. ARA focuses on the unique community, application, and economic context of rural regions, and it features the first-of-its-kind, real-world deployment of long-distance, high-capacity terrestrial wireless x-haul and access platforms as well as low-earth-orbit (LEO) satellite communications platforms across a rural area of diameter over 30 km. With both software-defined radios and programmable COTS systems, and through effective orchestration of these wireless resources with fiber as well as compute resources embedded end-to-end across user equipment (UE), base stations (BS), edge, and cloud, including support for Bring Your Own Device (BYOD), ARA offers programmability, performance, robustness, and heterogeneity at the same time, thus enabling rural-focused co-evolution of wireless and applications while helping advance the frontiers of wireless systems in domains such as Open RAN, NextG, and agriculture applications.

cs.NI↗

arXiv2025

Learning-Based Tracking Perimeter Control for Two-region Macroscopic Traffic Dynamics

Leveraging the concept of the macroscopic fundamental diagram (MFD), perimeter control can alleviate network-level congestion by identifying critical intersections and regulating them effectively. Considering the time-varying nature of travel demand and the equilibrium of accumulation state, we extend the conventional set-point perimeter control (SPC) problem for the two-region MFD system as an optimal tracking perimeter control problem (OTPCP). Unlike the SPC schemes that stabilize the traffic dynamics to the desired equilibrium point, the proposed tracking perimeter control (TPC) scheme regulates the traffic dynamics to a desired trajectory in a differential framework. Due to the inherent network uncertainties, such as heterogeneity of traffic dynamics and demand disturbance, the system dynamics could be uncertain or even unknown. To address these issues, we propose an adaptive dynamic programming (ADP) approach to solving the OTPCP without utilizing the well-calibrated system dynamics. Numerical experiments demonstrate the effectiveness of the proposed ADP-based TPC. Compared with the SPC scheme, the proposed TPC scheme achieves a 20.01% reduction in total travel time and a 3.15% improvement in cumulative trip completion. Moreover, the proposed adaptive TPC approach can regulate the accumulation state under network uncertainties and demand disturbances to the desired time-varying equilibrium trajectory that aims to maximize the trip completion under a nominal demand pattern. These results validate the robustness of the adaptive TPC approach.

eess.SY↗

arXiv2025

NextG-GPT: Leveraging GenAI for Advancing Wireless Networks and Communication Research

Artificial intelligence (AI) and wireless networking advancements have created new opportunities to enhance network efficiency and performance. In this paper, we introduce Next-Generation GPT (NextG-GPT), an innovative framework that integrates retrieval-augmented generation (RAG) and large language models (LLMs) within the wireless systems' domain. By leveraging state-of-the-art LLMs alongside a domain-specific knowledge base, NextG-GPT provides context-aware real-time support for researchers, optimizing wireless network operations. Through a comprehensive evaluation of LLMs, including Mistral-7B, Mixtral-8x7B, LLaMa3.1-8B, and LLaMa3.1-70B, we demonstrate significant improvements in answer relevance, contextual accuracy, and overall correctness. In particular, LLaMa3.1-70B achieves a correctness score of 86.2% and an answer relevancy rating of 90.6%. By incorporating diverse datasets such as ORAN-13K-Bench, TeleQnA, TSpec-LLM, and Spec5G, we improve NextG-GPT's knowledge base, generating precise and contextually aligned responses. This work establishes a new benchmark in AI-driven support for next-generation wireless network research, paving the way for future innovations in intelligent communication systems.

cs.ET↗

arXiv2025

Strategic learning for disturbance rejection in multi-agent systems: Nash and Minmax in graphical games

This article investigates the optimal control problem with disturbance rejection for discrete-time multi-agent systems under cooperative and non-cooperative graphical games frameworks. Given the practical challenges of obtaining accurate models, Q-function-based policy iteration methods are proposed to seek the Nash equilibrium solution for the cooperative graphical game and the distributed minmax solution for the non-cooperative graphical game. To implement these methods online, two reinforcement learning frameworks are developed, an actor-disturber-critic structure for the cooperative graphical game and an actor-adversary-disturber-critic structure for the non-cooperative graphical game. The stability of the proposed methods is rigorously analyzed, and simulation results are provided to illustrate the effectiveness of the proposed methods.

eess.SY↗

arXiv2025

An Integrated AI-Enabled System Using One Class Twin Cross Learning (OCT-X) for Early Gastric Cancer Detection

Early detection of gastric cancer, a leading cause of cancer-related mortality worldwide, remains hampered by the limitations of current diagnostic technologies, leading to high rates of misdiagnosis and missed diagnoses. To address these challenges, we propose an integrated system that synergizes advanced hardware and software technologies to balance speed-accuracy. Our study introduces the One Class Twin Cross Learning (OCT-X) algorithm. Leveraging a novel fast double-threshold grid search strategy (FDT-GS) and a patch-based deep fully convolutional network, OCT-X maximizes diagnostic accuracy through real-time data processing and seamless lesion surveillance. The hardware component includes an all-in-one point-of-care testing (POCT) device with high-resolution imaging sensors, real-time data processing, and wireless connectivity, facilitated by the NI CompactDAQ and LabVIEW software. Our integrated system achieved an unprecedented diagnostic accuracy of 99.70%, significantly outperforming existing models by up to 4.47%, and demonstrated a 10% improvement in multirate adaptability. These findings underscore the potential of OCT-X as well as the integrated system in clinical diagnostics, offering a path toward more accurate, efficient, and less invasive early gastric cancer detection. Future research will explore broader applications, further advancing oncological diagnostics. Code is available at https://github.com/liu37972/Multirate-Location-on-OCT-X-Learning.git.

eess.IV↗

arXiv2025

AraRACH: Enhancing NextG Random Access Reliability in Programmable Wireless Living Labs

The rapid evolution of wireless technologies has intensified interest in open and fully programmable radio access networks for whole-stack research, innovation, and evaluation of emerging solutions. Large-scale wireless living labs, such as ARA, equipped with real-world infrastructure play a vital role in this evolution by enabling researchers to prototype and evaluate advanced algorithms for next-generation wireless systems in outdoor and over-the-air environments benefiting from real-world fidelity and end-to-end programmability. However, at the core of this innovation is the performance in terms of coverage and reliability of these wireless living labs. For instance, interfacing power amplifiers and low noise amplifiers with software-defined radios (SDRs) for experimenting outdoors introduces issues in random access procedure-a process crucial in establishing connectivity between user equipment (UE) and the core network in 5G and 6G systems. Therefore, to ensure seamless connectivity and reliable communications in open-source 5G software stacks such as OpenAirInterface (OAI), we propose a slot-based approach to the 5G random access procedure leveraging full downlink (DL) and uplink (UL) slots instead of using special or mixed slots. We highlight how this approach achieves reliable 5G connectivity over 1 mile-the longest communication range that has been achieved so far in real-world settings using open-source 5G software stacks and the Universal Software Radio Peripheral (USRP) SDRs. We also demonstrate that, in a highly obstructed environment such as an industrial setting, we can increase the probability of a successful random access procedure to 90%-100% when we use at least 9 OFDM symbols to transmit msg2 and msg3.

cs.NI↗

arXiv2025

ReVeal: A Physics-Informed Neural Network for High-Fidelity Radio Environment Mapping

Accurately mapping the radio environment (e.g., identifying wireless signal strength at specific frequency bands and geographic locations) is crucial for efficient spectrum sharing, enabling secondary users (SUs) to access underutilized spectrum bands while protecting primary users (PUs). However, current models are either not generalizable due to shadowing, interference, and fading or are computationally too expensive, limiting real-world applicability. To address the shortcomings of existing models, we derive a second-order partial differential equation (PDE) for the Received Signal Strength Indicator (RSSI) based on a statistical model used in the literature. We then propose ReVeal (Re-constructor and Visualizer of Spectrum Landscape), a novel Physics-Informed Neural Network (PINN) that integrates the PDE residual into a neural network loss function to accurately model the radio environment based on sparse RF sensor measurements. ReVeal is validated using real-world measurement data from the rural and suburban areas of the ARA testbed and benchmarked against existing methods.ReVeal outperforms the existing methods in predicting the radio environment; for instance, with a root mean square error (RMSE) of only 1.95 dB, ReVeal achieves an accuracy that is an order of magnitude higher than existing methods such as the 3GPP and ITU-R channel models, ray-tracing, and neural networks. ReVeal achieves both high accuracy and low computational complexity while only requiring sparse RF sampling, for instance, only requiring 30 training sample points across an area of 514 square kilometers.

eess.SP↗

arXiv2025

CoKV: Optimizing KV Cache Allocation via Cooperative Game

Large language models (LLMs) have achieved remarkable success on various aspects of human life. However, one of the major challenges in deploying these models is the substantial memory consumption required to store key-value pairs (KV), which imposes significant resource demands. Recent research has focused on KV cache budget allocation, with several approaches proposing head-level budget distribution by evaluating the importance of individual attention heads. These methods, however, assess the importance of heads independently, overlooking their cooperative contributions within the model, which may result in a deviation from their true impact on model performance. In light of this limitation, we propose CoKV, a novel method that models the cooperation between heads in model inference as a cooperative game. By evaluating the contribution of each head within the cooperative game, CoKV can allocate the cache budget more effectively. Extensive experiments show that CoKV achieves state-of-the-art performance on the LongBench benchmark using LLama-3-8B-Instruct and Mistral-7B models.

cs.LG↗

arXiv2025

How Collective Intelligence Emerges in a Crowd of People Through Learned Division of Labor: A Case Study

This paper investigates the factors fostering collective intelligence (CI) through a case study of *LinYi's Experiment, where over 2000 human players collectively controll an avatar car. By conducting theoretical analysis and replicating observed behaviors through numerical simulations, we demonstrate how self-organized division of labor (DOL) among individuals fosters the emergence of CI and identify two essential conditions fostering CI by formulating this problem into a stability problem of a Markov Jump Linear System (MJLS). These conditions, independent of external stimulus, emphasize the importance of both elite and common players in fostering CI. Additionally, we propose an index for emergence of CI and a distributed method for estimating joint actions, enabling individuals to learn their optimal social roles without global action information of the whole crowd.

cs.MA↗

arXiv2025

SNR-EQ-JSCC: Joint Source-Channel Coding with SNR-Based Embedding and Query

Coping with the impact of dynamic channels is a critical issue in joint source-channel coding (JSCC)-based semantic communication systems. In this paper, we propose a lightweight channel-adaptive semantic coding architecture called SNR-EQ-JSCC. It is built upon the generic Transformer model and achieves channel adaptation (CA) by Embedding the signal-to-noise ratio (SNR) into the attention blocks and dynamically adjusting attention scores through channel-adaptive Queries. Meanwhile, penalty terms are introduced in the loss function to stabilize the training process. Considering that instantaneous SNR feedback may be imperfect, we propose an alternative method that uses only the average SNR, which requires no retraining of SNR-EQ-JSCC. Simulation results conducted on image transmission demonstrate that the proposed SNR-EQJSCC outperforms the state-of-the-art SwinJSCC in peak signal-to-noise ratio (PSNR) and perception metrics while only requiring 0.05% of the storage overhead and 6.38% of the computational complexity for CA. Moreover, the channel-adaptive query method demonstrates significant improvements in perception metrics. When instantaneous SNR feedback is imperfect, SNR-EQ-JSCC using only the average SNR still surpasses baseline schemes.

cs.IT↗