arXiv subjects

Shaohua Wu

Publications and source records attributed to Shaohua Wu.

At least 19 recordsLinked to original sources

arXiv2026

"We are all in big trouble! *Shock Emoji": Personal Narratives in Expressing Emotions, Opinions, and Data Regarding Climate Change in TikTok Short Videos

Climate change is a source of anxiety about the future. Understanding how people express themselves about climate change enables us to address such concerns. To study climate change expression on social media, we analyzed 200 TikTok videos tagged with #climatechange, identifying four categories of content: expression-feelings, views-appeals, news-information, and trend-hijacking. We found that creators use humor to package sharp critiques, avoiding direct confrontation. They replace complex discussions with life stories, such as adopting a vegetarian lifestyle or deleting emails. They borrow from news media to present fragmented information as scientific interpretations, creating a perception of scientific credibility, balancing scientific accuracy with emotionality. Analysis of viewer responses showed they engaged empathetically, reshaping interpretations of videos. These interactions risk reinforcing existing views but help build community on TikTok, which lacks community structure. This study reveals how creators may retell news on science using personal narratives, highlighting how short-form videos enable climate communication.

cs.HC↗

arXiv2026

Fast AI Model Partition for Split Learning over Edge Networks

Split learning (SL) is a distributed learning paradigm that can enable computation-intensive artificial intelligence (AI) applications by partitioning AI models between mobile devices and edge servers. %fully utilizing distributed computing resources for computation-intensive mobile intelligence applications. However, the model partitioning problem in SL becomes challenging due to the diverse and complex architectures of AI models. In this paper, we formulate an optimal model partitioning problem to minimize training delay in SL. To solve the problem, we represent an arbitrary AI model as a directed acyclic graph (DAG), where the model's layers and inter-layer connections are mapped to vertices and edges, and training delays are captured as edge weights. Then, we propose a general model partitioning algorithm by transforming the problem into a minimum \textit{s-t} cut problem on the DAG. Theoretical analysis shows that the two problems are equivalent, such that the optimal model partition can be obtained via a maximum-flow method. Furthermore, taking AI models with block structures into consideration, we design a low-complexity block-wise model partitioning algorithm to determine the optimal model partition. Specifically, the algorithm simplifies the DAG by abstracting each block (i.e., a repeating component comprising multiple layers in an AI model) into a single vertex. Extensive experimental results on a hardware testbed equipped with NVIDIA Jetson devices demonstrate that the proposed solution can reduce algorithm running time by up to 13.0$\times$ and training delay by up to 38.95\%, compared to state-of-the-art baselines.

cs.LG↗

arXiv2026

A Generalizable Framework for Building Executable Domain-Specific LLMs under Data Scarcity: Demonstration on Semiconductor TCAD Simulation

Scientific and engineering verticals often suffer from data scarcity and strict executability requirements: models must generate not only fluent text, but also syntactically valid, tool-compilable scripts. We present a schema-first alignment framework for building compact, executable domain-specific LLMs in low-resource settings. The framework integrates three core components: (i) large-scale synthetic QA data generation from expert documentation to instill foundational domain knowledge; (ii) a code-centric IR->DPO workflow that converts verified tool decks into interpretable intermediate representations (IR), performs equivalence-preserving diversification, and constructs preference pairs to directly optimize instruction compliance and code executability; and (iii) a controlled evaluation of Retrieval-Augmented Generation (RAG), showing that while RAG benefits general LLMs, it can marginally degrade the performance of already domain-aligned models. We demonstrate the framework by instantiating TcadGPT for semiconductor Technology Computer-Aided Design (TCAD). Using 1.5M synthetic QA pairs and an IR-driven DPO dataset, TcadGPT attains 85.6% semantic accuracy and an 80.0% syntax pass rate on SDE executability tests, substantially outperforming state-of-the-art general LLMs such as GPT-4o. To probe portability beyond TCAD, we apply the same recipe to the open-source FEM solver Elmer, observing consistent improvements in script-level success rates over general-purpose baselines. All datasets, benchmarks, and code (including P1, P2, and IR->DPO) are released for reproducibility. Together, these results suggest that the proposed framework provides a robust and reproducible path toward executable LLMs in specialized, data-scarce professional domains.

cs.CE↗

arXiv2026

A Chromatographic Process Design and Optimization Platform Powered by Large Language Models: A Case Application on Extract of Ginkgo Biloba Leaf

Chromatographic separation technology has been widely applied in pharmaceutical, chemical, and food industries due to its high efficiency. However, traditional human-dependent chromatographic process development faces challenges such as reliance on expert experience, long development cycles, and labor intensity. ChromR, a large language model (LLM)-driven platform for chromatographic process design and optimization, is presented in this work. The platform integrates ChromLLM, a domain-specific LLM trained for chromatography, along with a multi-agent system and an automated chromatographic experimental device. The multi-agent system comprises four agents: domain knowledge answering, experimental design, experimental execution, and data analysis. ChromR enables automatic completion of the entire workflow-including initial process parameter recommendation, experimental design, automated execution, data analysis, and multi-objective optimization. By utilizing ChromR, dependency on expert knowledge is effectively reduced, while labor input and development time are significantly decreased. Chromatographic purification of the extract of Ginkgo biloba leaf (EGBL) was selected as a case study. ChromR successfully developed a chromatographic process within one week that meets multiple objectives, including fraction quality and production efficiency, reducing development time to approximately one-seventh of that required by the conventional paradigm. An intelligent, automated, and universally applicable new paradigm was established for chromatographic process development.

cs.MA↗

arXiv2025

Yuan-TecSwin: A text conditioned Diffusion model with Swin-transformer blocks

Diffusion models have shown remarkable capacity in image synthesis based on their U-shaped architecture and convolutional neural networks (CNN) as basic blocks. The locality of the convolution operation in CNN may limit the model's ability to understand long-range semantic information. To address this issue, we propose Yuan-TecSwin, a text-conditioned diffusion model with Swin-transformer in this work. The Swin-transformer blocks take the place of CNN blocks in the encoder and decoder, to improve the non-local modeling ability in feature extraction and image restoration. The text-image alignment is improved with a well-chosen text encoder, effective utilization of text embedding, and careful design in the incorporation of text condition. Using an adapted time step to search in different diffusion stages, inference performance is further improved by 10%. Yuan-TecSwin achieves the state-of-the-art FID score of 1.37 on ImageNet generation benchmark, without any additional models at different denoising stages. In a side-by-side comparison, we find it difficult for human interviewees to tell the model-generated images from the human-painted ones.

cs.CV↗

arXiv2025

Twinning for Space-Air-Ground-Sea Integrated Networks: Beyond Conventional Digital Twin Towards Goal-Oriented Semantic Twin

A space-air-ground-sea integrated network (SAGSIN) has emerged as a cornerstone of 6G systems, establishing a unified global architecture by integrating multi-domain network resources. Motivated by the demand for real-time situational awareness and intelligent operational maintenance, digital twin (DT) technology was initially regarded as a promising solution, owing to its capability to create virtual replicas and emulate physical system behaviors. However, in the context of SAGSIN, the high-fidelity, full-scale modeling paradigm inherent to conventional DTs encounters fundamental limitations, including prohibitive computational overhead, delayed model synchronization, and cross-system semantic gaps. To address these limitations, this survey paper proposes a novel twinning framework: goal-oriented semantic twin (GOST). Unlike DTs that pursue physical mirroring, GOST prioritizes ``utility'' over ``fidelity,'' leveraging semantic technologies and goal-oriented principles to construct lightweight, task-specific representations. This paper systematically articulates the GOST framework through three layers: knowledge-based semantics, data-driven semantics, and goal-oriented principles. Furthermore, we provide a comprehensive tutorial on constructing GOST by detailing its core enabling technologies and introduce a multidimensional evaluation framework for GOST. We present a case study targeting collaborative tracking tasks in remote satellite-UAV networks, demonstrating that GOST significantly outperforms conventional DTs in timeliness of perceptual data and collaborative tracking. Finally, we outline research directions, establishing GOST as a transformative twinning paradigm to guide the development of SAGSIN.

cs.DC↗

arXiv2025

SimpleVSF: VLM-Scoring Fusion for Trajectory Prediction of End-to-End Autonomous Driving

End-to-end autonomous driving has emerged as a promising paradigm for achieving robust and intelligent driving policies. However, existing end-to-end methods still face significant challenges, such as suboptimal decision-making in complex scenarios. In this paper,we propose SimpleVSF (Simple VLM-Scoring Fusion), a novel framework that enhances end-to-end planning by leveraging the cognitive capabilities of Vision-Language Models (VLMs) and advanced trajectory fusion techniques. We utilize the conventional scorers and the novel VLM-enhanced scorers. And we leverage a robust weight fusioner for quantitative aggregation and a powerful VLM-based fusioner for qualitative, context-aware decision-making. As the leading approach in the ICCV 2025 NAVSIM v2 End-to-End Driving Challenge, our SimpleVSF framework demonstrates state-of-the-art performance, achieving a superior balance between safety, comfort, and efficiency.

cs.RO↗

arXiv2025

Error Floor of ML-Decoded Spinal Codes in the Finite Blocklength Regime

Spinal codes is a new family of capacity-achieving rateless codes that has been shown to achieve better rate performance compared to Raptor codes, Strider codes, and rateless Low-Density Parity-Check (LDPC) codes. This correspondence addresses the performance limitations of Spinal codes in the finite block length regime, uncovering an error floor phenomenon at high Signal-to-Noise Ratios (SNRs). We develop an analytical expression to approximate the error floor and devise SNR thresholds at which the error floor initiates. Numerical results across {Additive White Gaussian Noise (AWGN), rayleigh, and nakagami-m fading channels} verify the accuracy of our analysis. The analysis and numerical results also show that transmitting more passes of symbols can lower the error floor but does not affect the SNR threshold, providing insights on the performance target, the working SNR region, and the code design.

cs.IT↗

arXiv2025

Scenario-Agnostic Deep-Learning-Based Localization with Contrastive Self-Supervised Pre-training

Wireless localization has become a promising technology for offering intelligent location-based services. Although its localization accuracy is improved under specific scenarios, the short of environmental dynamic vulnerability still hinders this approach from being fully practical applications. In this paper, we propose CSSLoc, a novel framework on contrastive self-supervised pre-training to learn generic representations for accurate localization in various scenarios. Without the location information supervision, CSSLoc attempts to learn an insightful metric on the similarity discrimination of radio data, in such a scenario-agnostic manner that the similar samples are closely clustered together and different samples are separated in the representation space. Furthermore, the trained feature encoder can be directly transferred for downstream localization tasks, and the location predictor is trained to estimate accurate locations with the robustness of environmental dynamics. With extensive experimental results, CSSLoc can outperform classical and state-of-the-art DNN-based localization schemes in typical indoor scenarios, pushing deep-learning-based localization from specificity to generality.

eess.SP↗

arXiv2025

Joint Transmission and Control in a Goal-oriented NOMA Network

Goal-oriented communication shifts the focus from merely delivering timely information to maximizing decision-making effectiveness by prioritizing the transmission of high-value information. In this context, we introduce the Goal-oriented Tensor (GoT), a novel closed-loop metric designed to directly quantify the ultimate utility in Goal-oriented systems, capturing how effectively the transmitted information meets the underlying application's objectives. Leveraging the GoT, we model a Goal-oriented Non-Orthogonal Multiple Access (NOMA) network comprising multiple transmission-control loops. Operating under a pull-based framework, we formulate the joint optimization of transmission and control as a Partially Observable Markov Decision Process (POMDP), which we solve by deriving the belief state and training a Double-Dueling Deep Q-Network (D3QN). This framework enables adaptive decision-making for power allocation and control actions. Simulation results reveal a fundamental trade-off between transmission efficiency and control fidelity. Additionally, the superior utility of NOMA over Orthogonal Multiple Access (OMA) in multi-loop remote control scenarios is demonstrated.

cs.IT↗

arXiv2025

Adaptive Split Learning over Energy-Constrained Wireless Edge Networks

Split learning (SL) is a promising approach for training artificial intelligence (AI) models, in which devices collaborate with a server to train an AI model in a distributed manner, based on a same fixed split point. However, due to the device heterogeneity and variation of channel conditions, this way is not optimal in training delay and energy consumption. In this paper, we design an adaptive split learning (ASL) scheme which can dynamically select split points for devices and allocate computing resource for the server in wireless edge networks. We formulate an optimization problem to minimize the average training latency subject to long-term energy consumption constraint. The difficulties in solving this problem are the lack of future information and mixed integer programming (MIP). To solve it, we propose an online algorithm leveraging the Lyapunov theory, named OPEN, which decomposes it into a new MIP problem only with the current information. Then, a two-layer optimization method is proposed to solve the MIP problem. Extensive simulation results demonstrate that the ASL scheme can reduce the average training delay and energy consumption by 53.7% and 22.1%, respectively, as compared to the existing SL schemes.

cs.LG↗

arXiv2025

Energy-Efficient Split Learning for Fine-Tuning Large Language Models in Edge Networks

In this letter, we propose an energy-efficient split learning (SL) framework for fine-tuning large language models (LLMs) using geo-distributed personal data at the network edge, where LLMs are split and alternately across massive mobile devices and an edge server. Considering the device heterogeneity and channel dynamics in edge networks, a \underline{C}ut l\underline{A}yer and computing \underline{R}esource \underline{D}ecision (CARD) algorithm is developed to minimize training delay and energy consumption. Simulation results demonstrate that the proposed approach reduces the average training delay and server's energy consumption by 70.8% and 53.1%, compared to the benchmarks, respectively.

cs.LG↗

arXiv2024

Split Knowledge Distillation for Large Models in IoT: Architecture, Challenges, and Solutions

Large models (LMs) have immense potential in Internet of Things (IoT) systems, enabling applications such as intelligent voice assistants, predictive maintenance, and healthcare monitoring. However, training LMs on edge servers raises data privacy concerns, while deploying them directly on IoT devices is constrained by limited computational and memory resources. We analyze the key challenges of training LMs in IoT systems, including energy constraints, latency requirements, and device heterogeneity, and propose potential solutions such as dynamic resource management, adaptive model partitioning, and clustered collaborative training. Furthermore, we propose a split knowledge distillation framework to efficiently distill LMs into smaller, deployable versions for IoT devices while ensuring raw data remains local. This framework integrates knowledge distillation and split learning to minimize energy consumption and meet low model training delay requirements. A case study is presented to evaluate the feasibility and performance of the proposed framework.

cs.LG↗

arXiv2024

SimpleBEV: Improved LiDAR-Camera Fusion Architecture for 3D Object Detection

More and more research works fuse the LiDAR and camera information to improve the 3D object detection of the autonomous driving system. Recently, a simple yet effective fusion framework has achieved an excellent detection performance, fusing the LiDAR and camera features in a unified bird's-eye-view (BEV) space. In this paper, we propose a LiDAR-camera fusion framework, named SimpleBEV, for accurate 3D object detection, which follows the BEV-based fusion framework and improves the camera and LiDAR encoders, respectively. Specifically, we perform the camera-based depth estimation using a cascade network and rectify the depth results with the depth information derived from the LiDAR points. Meanwhile, an auxiliary branch that implements the 3D object detection using only the camera-BEV features is introduced to exploit the camera information during the training phase. Besides, we improve the LiDAR feature extractor by fusing the multi-scaled sparse convolutional features. Experimental results demonstrate the effectiveness of our proposed method. Our method achieves 77.6\% NDS accuracy on the nuScenes dataset, showcasing superior performance in the 3D object detection track.

cs.CV↗

arXiv2024

Sampling to Achieve the Goal: An Age-aware Remote Markov Decision Process

Age of Information (AoI) has been recognized as an important metric to measure the freshness of information. Central to this consensus is that minimizing AoI can enhance the freshness of information, thereby facilitating the accuracy of subsequent decision-making processes. However, to date the direct causal relationship that links AoI to the utility of the decision-making process is unexplored. To fill this gap, this paper provides a sampling-control co-design problem, referred to as an age-aware remote Markov Decision Process (MDP) problem, to explore this unexplored relationship. Our framework revisits the sampling problem in [1] with a refined focus: moving from AoI penalty minimization to directly optimizing goal-oriented remote decision-making process under random delay. We derive that the age-aware remote MDP problem can be reduced to a standard MDP problem without delays, and reveal that treating AoI solely as a metric for optimization is not optimal in achieving remote decision making. Instead, AoI can serve as important side information to facilitate remote decision making.

cs.IT↗

arXiv2024

SimpleLLM4AD: An End-to-End Vision-Language Model with Graph Visual Question Answering for Autonomous Driving

Many fields could benefit from the rapid development of the large language models (LLMs). The end-to-end autonomous driving (e2eAD) is one of the typically fields facing new opportunities as the LLMs have supported more and more modalities. Here, by utilizing vision-language model (VLM), we proposed an e2eAD method called SimpleLLM4AD. In our method, the e2eAD task are divided into four stages, which are perception, prediction, planning, and behavior. Each stage consists of several visual question answering (VQA) pairs and VQA pairs interconnect with each other constructing a graph called Graph VQA (GVQA). By reasoning each VQA pair in the GVQA through VLM stage by stage, our method could achieve e2e driving with language. In our method, vision transformers (ViT) models are employed to process nuScenes visual data, while VLM are utilized to interpret and reason about the information extracted from the visual inputs. In the perception stage, the system identifies and classifies objects from the driving environment. The prediction stage involves forecasting the potential movements of these objects. The planning stage utilizes the gathered information to develop a driving strategy, ensuring the safety and efficiency of the autonomous vehicle. Finally, the behavior stage translates the planned actions into executable commands for the vehicle. Our experiments demonstrate that SimpleLLM4AD achieves competitive performance in complex driving scenarios.

cs.CV↗

arXiv2024

Unified Upper Bounds on the ML decoding Error Probability of Spinal Codes over Fading Channels

Performance evaluation of particular channel coding has been a significant topic in coding theory, often involving the use of bounding techniques. This paper focuses on the new family of capacity-achieving codes, Spinal codes, to provide a comprehensive analysis framework to tightly upper bound the block error rate (BLER) of Spinal codes in the finite block length (FBL) regime. First, we resort to a variant of the Gallager random coding bound to upper bound the BLER of Spinal codes over the fading channel. Then, this paper derives a new bound without resorting to the use of Gallager random coding bound, achieving provable tightness over the wide range of signal-to-noise ratios (SNR). The derived BLER upper bounds in this paper are generalized, facilitating the performance evaluations of Spinal codes over different types of fast fading channels. Over the Rayleigh, Nakagami-m, and Rician fading channels, this paper explicitly derived the BLER upper bounds on Spinal codes as case studies. Based on the bounds, we theoretically reveal that the tail transmission pattern (TTP) for ML-decoded Spinal codes remains optimal in terms of reliability performance. Simulations verify the tightness of the bounds and the insights obtained.

cs.IT↗

arXiv2024

Semantics-Empowered Space-Air-Ground-Sea Integrated Network: New Paradigm, Frameworks, and Challenges

In the coming sixth generation (6G) communication era, to provide seamless and ubiquitous connections, the space-air-ground-sea integrated network (SAGSIN) is envisioned to address the challenges of communication coverage in areas with difficult conditions, such as the forest, desert, and sea. Considering the fundamental limitations of the SAGSIN including large-scale scenarios, highly dynamic channels, and limited device capabilities, traditional communications based on Shannon information theory cannot satisfy the communication demands. Moreover, bit-level reconstruction is usually redundant for many human-to-machine or machine-to-machine applications in the SAGSIN. Therefore, it is imperative to consider high-level communications towards semantics exchange, called semantic communications. In this survey, according to the interpretations of the term "semantics", including "significance", "meaning", and "effectiveness-related information", we review state-of-the-art works on semantic communications from three perspectives, which are 1) significance representation and protection, 2) meaning similarity measurement and meaning enhancement, and 3) ultimate effectiveness and effectiveness yielding. Sequentially, three types of semantic communication systems can be correspondingly introduced, namely the significance-oriented, meaning-oriented, and effectiveness/task-oriented semantic communication systems. Implementation of the above three types of systems in the SAGSIN necessitates a new perception-communication-computing-actuation-integrated paradigm (PCCAIP), where all the available perception, computing, and actuation techniques jointly facilitates significance-oriented sampling & transmission, semantic extraction & reconstruction, and task decision. Finally, we point out some future challenges on semantic communications in the SAGSIN. ...

cs.IT↗