arXiv subjects

Tian Wang

Publications and source records attributed to Tian Wang.

At least 55 records · Page 3Linked to original sources

arXiv2026

Hybrid Distillation with CoT Guidance for Edge-Drone Control Code Generation

With large language models demonstrating significant potential in code generation tasks, their application to onboard control of resource-constrained Unmanned Aerial Vehicles has emerged as an important research direction. However, a notable contradiction exists between the high resource consumption of large models and the real-time, lightweight requirements of UAV platforms. This paper proposes an integrated approach that combines knowledge distillation, chain-of-thought guidance, and supervised fine-tuning for UAV multi-SDK control tasks, aiming to efficiently transfer complex reasoning and code generation capabilities to smaller models. Firstly, a high-quality dataset covering various mainstream UAV SDKs is constructed, featuring instruction-code-reasoning chains, and incorporates counterfactual negative samples for data augmentation, guiding the model to learn the end-to-end logic from instruction parsing to code generation. Secondly, leveraging DeepSeek-Coder-V2-Lite quantized via QLoRA as the teacher model, and based on a hybrid black-box and white-box distillation strategy, high-quality chain-of-thought soft labels are generated. These are combined with a weighted cross-entropy loss using hard labels to transfer complex reasoning capabilities to the smaller student model. Finally, through prompt tuning engineering optimized for the UAV control scenario, the model performance on core tasks such as SDK type recognition and function call matching is enhanced. Experimental results indicate that the distilled lightweight model maintains high code generation accuracy while achieving significant improvements in deployment and inference efficiency, effectively demonstrating the feasibility and superiority of our approach in achieving precise and lightweight intelligent control for UAVs

cs.AI↗

arXiv2026

Spectral point transformer for significant wave height estimation from sea clutter

This paper presents a method for estimating significant wave height (Hs) from sparse S_pectral P_oint using a T_ransformer-based approach (SPT). Based on empirical observations that only a minority of spectral points with strong power contribute to wave energy, the proposed SPT effectively integrates geometric and spectral characteristics of ocean surface waves to estimate Hs through multi-dimensional feature representation. The experiment reveals an intriguing phenomenon: the learned features of SPT align well with physical dispersion relations, where the contribution-score map of selected points is concentrated along dispersion curves. Compared to conventional vision networks that process image sequences and full spectra, SPT demonstrates superior performance in Hs regression while consuming significantly fewer computational resources. On a consumer-grade GPU, SPT completes the training of regression model for 1080 sea clutter image sequences within 4 minutes, showcasing its potential to reduce deployment costs for radar wave-measuring systems. The open-source implementation of SPT will be available at https://github.com/joeyee/spt

eess.SP↗

arXiv2025

Enhancing AIGC Service Efficiency with Adaptive Multi-Edge Collaboration in A Distributed System

The Artificial Intelligence Generated Content (AIGC) technique has gained significant traction for producing diverse content. However, existing AIGC services typically operate within a centralized framework, resulting in high response times. To address this issue, we integrate collaborative Mobile Edge Computing (MEC) technology to reduce processing delays for AIGC services. Current collaborative MEC methods primarily support single-server offloading or facilitate interactions among fixed Edge Servers (ESs), limiting flexibility and resource utilization across all ESs to meet the varying computing and networking requirements of AIGC services. We propose AMCoEdge, an adaptive multi-server collaborative MEC approach to enhancing AIGC service efficiency. The AMCoEdge fully utilizes the computing and networking resources across all ESs through adaptive multi-ES selection and dynamic workload allocation, thereby minimizing the offloading make-span of AIGC services. Our design features an online distributed algorithm based on deep reinforcement learning, accompanied by theoretical analyses that confirm an approximate linear time complexity. Simulation results show that our method outperforms state-of-the-art baselines, achieving at least an 11.04% reduction in task offloading make-span and a 44.86% decrease in failure rate. Additionally, we develop a distributed prototype system to implement and evaluate our AMCoEdge method for real AIGC service execution, demonstrating service delays that are 9.23% - 31.98% lower than the three representative methods.

cs.NI↗

arXiv2025

See, Think, Act: Online Shopper Behavior Simulation with VLM Agents

LLMs have recently demonstrated strong potential in simulating online shopper behavior. Prior work has improved action prediction by applying SFT on action traces with LLM-generated rationales, and by leveraging RL to further enhance reasoning capabilities. Despite these advances, current approaches rely on text-based inputs and overlook the essential role of visual perception in shaping human decision-making during web GUI interactions. In this paper, we investigate the integration of visual information, specifically webpage screenshots, into behavior simulation via VLMs, leveraging OPeRA dataset. By grounding agent decision-making in both textual and visual modalities, we aim to narrow the gap between synthetic agents and real-world users, thereby enabling more cognitively aligned simulations of online shopping behavior. Specifically, we employ SFT for joint action prediction and rationale generation, conditioning on the full interaction context, which comprises action history, past HTML observations, and the current webpage screenshot. To further enhance reasoning capabilities, we integrate RL with a hierarchical reward structure, scaled by a difficulty-aware factor that prioritizes challenging decision points. Empirically, our studies show that incorporating visual grounding yields substantial gains: the combination of text and image inputs improves exact match accuracy by more than 6% over text-only inputs. These results indicate that multi-modal grounding not only boosts predictive accuracy but also enhances simulation fidelity in visually complex environments, which captures nuances of human attention and decision-making that text-only agents often miss. Finally, we revisit the design space of behavior simulation frameworks, identify key methodological limitations, and propose future research directions toward building efficient and effective human behavior simulators.

cs.CY↗

arXiv2025

HeFS: Helper-Enhanced Feature Selection via Pareto-Optimized Genetic Search

Feature selection is a combinatorial optimization problem that is NP-hard. Conventional approaches often employ heuristic or greedy strategies, which are prone to premature convergence and may fail to capture subtle yet informative features. This limitation becomes especially critical in high-dimensional datasets, where complex and interdependent feature relationships prevail. We introduce the HeFS (Helper-Enhanced Feature Selection) framework to refine feature subsets produced by existing algorithms. HeFS systematically searches the residual feature space to identify a Helper Set - features that complement the original subset and improve classification performance. The approach employs a biased initialization scheme and a ratio-guided mutation mechanism within a genetic algorithm, coupled with Pareto-based multi-objective optimization to jointly maximize predictive accuracy and feature complementarity. Experiments on 18 benchmark datasets demonstrate that HeFS consistently identifies overlooked yet informative features and achieves superior performance over state-of-the-art methods, including in challenging domains such as gastric cancer classification, drug toxicity prediction, and computer science applications. The code and datasets are available at https://healthinformaticslab.org/supp/.

cs.LG↗

arXiv2025

Diffusion Models for Reinforcement Learning: Foundations, Taxonomy, and Development

Diffusion Models (DMs), as a leading class of generative models, offer key advantages for reinforcement learning (RL), including multi-modal expressiveness, stable training, and trajectory-level planning. This survey delivers a comprehensive and up-to-date synthesis of diffusion-based RL. We first provide an overview of RL, highlighting its challenges, and then introduce the fundamental concepts of DMs, investigating how they are integrated into RL frameworks to address key challenges in this research field. We establish a dual-axis taxonomy that organizes the field along two orthogonal dimensions: a function-oriented taxonomy that clarifies the roles DMs play within the RL pipeline, and a technique-oriented taxonomy that situates implementations across online versus offline learning regimes. We also provide a comprehensive examination of this progression from single-agent to multi-agent domains, thereby forming several frameworks for DM-RL integration and highlighting their practical utility. Furthermore, we outline several categories of successful applications of diffusion-based RL across diverse domains, discuss open research issues of current methodologies, and highlight key directions for future research to advance the field. Finally, we summarize the survey to identify promising future development directions. We are actively maintaining a GitHub repository (https://github.com/ChangfuXu/D4RL-FTD) for papers and other related resources to apply DMs for RL.

cs.LG↗

arXiv2025

A Survey on Code Generation with LLM-based Agents

Code generation agents powered by large language models (LLMs) are revolutionizing the software development paradigm. Distinct from previous code generation techniques, code generation agents are characterized by three core features. 1) Autonomy: the ability to independently manage the entire workflow, from task decomposition to coding and debugging. 2) Expanded task scope: capabilities that extend beyond generating code snippets to encompass the full software development lifecycle (SDLC). 3) Enhancement of engineering practicality: a shift in research emphasis from algorithmic innovation toward practical engineering challenges, such as system reliability, process management, and tool integration. This domain has recently witnessed rapid development and an explosion in research, demonstrating significant application potential. This paper presents a systematic survey of the field of LLM-based code generation agents. We trace the technology's developmental trajectory from its inception and systematically categorize its core techniques, including both single-agent and multi-agent architectures. Furthermore, this survey details the applications of LLM-based agents across the full SDLC, summarizes mainstream evaluation benchmarks and metrics, and catalogs representative tools. Finally, by analyzing the primary challenges, we identify and propose several foundational, long-term research directions for the future work of the field.

cs.SE↗

arXiv2025

SynerGen: Contextualized Generative Recommender for Unified Search and Recommendation

The dominant retrieve-then-rank pipeline in large-scale recommender systems suffers from mis-calibration and engineering overhead due to its architectural split and differing optimization objectives. While recent generative sequence models have shown promise in unifying retrieval and ranking by auto-regressively generating ranked items, existing solutions typically address either personalized search or query-free recommendation, often exhibiting performance trade-offs when attempting to unify both. We introduce \textit{SynerGen}, a novel generative recommender model that bridges this critical gap by providing a single generative backbone for both personalized search and recommendation, while simultaneously excelling at retrieval and ranking tasks. Trained on behavioral sequences, our decoder-only Transformer leverages joint optimization with InfoNCE for retrieval and a hybrid pointwise-pairwise loss for ranking, allowing semantic signals from search to improve recommendation and vice versa. We also propose a novel time-aware rotary positional embedding to effectively incorporate time information into the attention mechanism. \textit{SynerGen} achieves significant improvements on widely adopted recommendation and search benchmarks compared to strong generative recommender and joint search and recommendation baselines. This work demonstrates the viability of a single generative foundation model for industrial-scale unified information access.

cs.CL↗

arXiv2025

Chirality-Driven Magnetization Emerges from Relativistic Four-Current Dynamics

Chirality-induced spin selectivity (CISS) is a striking quantum phenomenon in which electron transport through chiral molecules leads to spin polarization -- even in the absence of external magnetic fields or magnetic components. Although observed in systems such as DNA, helicenes, proteins, and polymers, the fundamental physical origin of CISS remains unresolved. Here, we introduce a time-dependent relativistic four-current framework, in which charge and current densities evolve according to the time-dependent variational principle. Real-time relativistic four-current simulations enable direct analysis of helical currents and induced magnetization dynamics. Applied to helicenes -- axially chiral molecules lacking stereocenters -- our simulations reveal curvature-induced helical electron currents that generate spontaneous magnetic fields aligned along the molecular axis. These fields are handedness-dependent and reach magnitudes of $10^{-1}$ Tesla per single helicene strand. Our results suggest that CISS may arise from intrinsic, relativistic curvature-induced helical currents and the associated magnetic fields within chiral molecules. This four-current mechanism offers a self-contained explanation for the driving force underlying spin selectivity, independent of interfacial effects or unphysically enhanced spin-orbit coupling. Furthermore, our results provide a new perspective that offers a unifying framework with the potential to reconcile many existing hypotheses and theoretical models, while also suggesting several testable predictions that can be examined experimentally.

cond-mat.mes-hall↗

arXiv2025

Exploring Reasoning-Infused Text Embedding with Large Language Models for Zero-Shot Dense Retrieval

Transformer-based models such as BERT and E5 have significantly advanced text embedding by capturing rich contextual representations. However, many complex real-world queries require sophisticated reasoning to retrieve relevant documents beyond surface-level lexical matching, where encoder-only retrievers often fall short. Decoder-only large language models (LLMs), known for their strong reasoning capabilities, offer a promising alternative. Despite this potential, existing LLM-based embedding methods primarily focus on contextual representation and do not fully exploit the reasoning strength of LLMs. To bridge this gap, we propose Reasoning-Infused Text Embedding (RITE), a simple but effective approach that integrates logical reasoning into the text embedding process using generative LLMs. RITE builds upon existing language model embedding techniques by generating intermediate reasoning texts in the token space before computing embeddings, thereby enriching representations with inferential depth. Experimental results on BRIGHT, a reasoning-intensive retrieval benchmark, demonstrate that RITE significantly enhances zero-shot retrieval performance across diverse domains, underscoring the effectiveness of incorporating reasoning into the embedding process.

cs.CL↗

arXiv2025

STEM: Efficient Relative Capability Evaluation of LLMs through Structured Transition Samples

Evaluating large language models (LLMs) has become increasingly challenging as model capabilities advance rapidly. While recent models often achieve higher scores on standard benchmarks, these improvements do not consistently reflect enhanced real-world reasoning capabilities. Moreover, widespread overfitting to public benchmarks and the high computational cost of full evaluations have made it both expensive and less effective to distinguish meaningful differences between models. To address these challenges, we propose the \textbf{S}tructured \textbf{T}ransition \textbf{E}valuation \textbf{M}ethod (STEM), a lightweight and interpretable evaluation framework for efficiently estimating the relative capabilities of LLMs. STEM identifies \textit{significant transition samples} (STS) by analyzing consistent performance transitions among LLMs of the same architecture but varying parameter scales. These samples enable STEM to effectively estimate the capability position of an unknown model. Qwen3 model family is applied to construct the STS pool on six diverse and representative benchmarks. To assess generalizability. Experimental results indicate that STEM reliably captures performance trends, aligns with ground-truth rankings of model capability. These findings highlight STEM as a practical and scalable method for fine-grained, architecture-agnostic evaluation of LLMs.

cs.CL↗

arXiv2025

Adaptive AI Agent Placement and Migration in Edge Intelligence Systems

The rise of LLMs such as ChatGPT and Claude fuels the need for AI agents capable of real-time task handling. However, migrating data-intensive, multi-modal edge workloads to cloud data centers, traditionally used for agent deployment, introduces significant latency. Deploying AI agents at the edge improves efficiency and reduces latency. However, edge environments present challenges due to limited and heterogeneous resources. Maintaining QoS for mobile users necessitates agent migration, which is complicated by the complexity of AI agents coordinating LLMs, task planning, memory, and external tools. This paper presents the first systematic deployment and management solution for LLM-based AI agents in dynamic edge environments. We propose a novel adaptive framework for AI agent placement and migration in edge intelligence systems. Our approach models resource constraints and latency/cost, leveraging ant colony algorithms and LLM-based optimization for efficient decision-making. It autonomously places agents to optimize resource utilization and QoS and enables lightweight agent migration by transferring only essential state. Implemented on a distributed system using AgentScope and validated across globally distributed edge servers, our solution significantly reduces deployment latency and migration costs.

cs.AI↗

arXiv2025

EAT: QoS-Aware Edge-Collaborative AIGC Task Scheduling via Attention-Guided Diffusion Reinforcement Learning

The growth of Artificial Intelligence (AI) and large language models has enabled the use of Generative AI (GenAI) in cloud data centers for diverse AI-Generated Content (AIGC) tasks. Models like Stable Diffusion introduce unavoidable delays and substantial resource overhead, which are unsuitable for users at the network edge with high QoS demands. Deploying AIGC services on edge servers reduces transmission times but often leads to underutilized resources and fails to optimally balance inference latency and quality. To address these issues, this paper introduces a QoS-aware \underline{E}dge-collaborative \underline{A}IGC \underline{T}ask scheduling (EAT) algorithm. Specifically: 1) We segment AIGC tasks and schedule patches to various edge servers, formulating it as a gang scheduling problem that balances inference latency and quality while considering server heterogeneity, such as differing model distributions and cold start issues. 2) We propose a reinforcement learning-based EAT algorithm that uses an attention layer to extract load and task queue information from edge servers and employs a diffusion-based policy network for scheduling, efficiently enabling model reuse. 3) We develop an AIGC task scheduling system that uses our EAT algorithm to divide tasks and distribute them across multiple edge servers for processing. Experimental results based on our system and large-scale simulations show that our EAT algorithm can reduce inference latency by up to 56\% compared to baselines. We release our open-source code at https://github.com/zzf1955/EAT.

cs.DC↗

arXiv2025

Distribution of supersingular primes for abelian surfaces

Let $A/K$ be an absolutely simple abelian surface defined over a number field $K$. We give unconditional upper bounds for the number of prime ideals $\mathfrak{p}$ of $K$ with norm up to $x$ such that $A$ has supersingular reduction at $\mathfrak{p}$. These bounds are obtained in three distinct settings, depending on the endomorphism algebra of $A$, namely, the case of trivial endomorphisms, real multiplication (RM), and quaternion multiplication (QM). In the RM case and when $K=\mathbb{Q}$, our results further implies an unconditional upper bound on the distribution of Frobenius traces of $A$. Furthermore, in the RM setting, we study the distribution of the middle coefficients of Frobenius polynomials of $A$ at primes where the reduction of $A$ splits.

math.NT↗

arXiv2025

Effective open image theorem and a Linnik type problem for elliptic curves

We study an effective open image theorem for families of elliptic curves and products of elliptic curves ordered by conductor. Unconditionally, we prove that for $100\%$ of pairs of elliptic curves, the largest prime $\ell$, for which the associated mod $\ell$ Galois representation fails to be surjective, is small. Additionally, for semistable families, our bound on $\ell$ is comparable to the result obtained under the Generalized Riemann Hypothesis. We reduce the problem to a Linnik type problem for modular forms and apply the zero density estimates. This method, together with an analysis of the local Galois representations of elliptic curves, allows us to show similar results for single elliptic curves.

math.NT↗

arXiv2025

MolProphecy: Bridging Medicinal Chemists' Knowledge and Molecular Pre-Trained Models via a Multi-Modal Framework

MolProphecy is a human-in-the-loop (HITL) multi-modal framework designed to integrate chemists' domain knowledge into molecular property prediction models. While molecular pre-trained models have enabled significant gains in predictive accuracy, they often fail to capture the tacit, interpretive reasoning central to expert-driven molecular design. To address this, MolProphecy employs ChatGPT as a virtual chemist to simulate expert-level reasoning and decision-making. The generated chemist knowledge is embedded by the large language model (LLM) as a dedicated knowledge representation and then fused with graph-based molecular features through a gated cross-attention mechanism, enabling joint reasoning over human-derived and structural features. Evaluated on four benchmark datasets (FreeSolv, BACE, SIDER, and ClinTox), MolProphecy outperforms state-of-the-art (SOTA) models, achieving a 15.0 percent reduction in RMSE on FreeSolv and a 5.39 percent improvement in AUROC on BACE. Analysis reveals that chemist knowledge and structural features provide complementary contributions, improving both accuracy and interpretability. MolProphecy offers a practical and generalizable approach for collaborative drug discovery, with the flexibility to incorporate real chemist input in place of the current simulated proxy--without the need for model retraining. The implementation is publicly available at https://github.com/zhangruochi/MolProphecy.

cs.LG↗

arXiv2025

DeepSelective: Interpretable Prognosis Prediction via Feature Selection and Compression in EHR Data

The rapid accumulation of Electronic Health Records (EHRs) has transformed healthcare by providing valuable data that enhance clinical predictions and diagnoses. While conventional machine learning models have proven effective, they often lack robust representation learning and depend heavily on expert-crafted features. Although deep learning offers powerful solutions, it is often criticized for its lack of interpretability. To address these challenges, we propose DeepSelective, a novel end to end deep learning framework for predicting patient prognosis using EHR data, with a strong emphasis on enhancing model interpretability. DeepSelective combines data compression techniques with an innovative feature selection approach, integrating custom-designed modules that work together to improve both accuracy and interpretability. Our experiments demonstrate that DeepSelective not only enhances predictive accuracy but also significantly improves interpretability, making it a valuable tool for clinical decision-making. The source code is freely available at http://www.healthinformaticslab.org/supp/resources.php .

cs.LG↗

arXiv2025

Adaptive Configuration Selection for Multi-Model Inference Pipelines in Edge Computing

The growing demand for real-time processing tasks is driving the need for multi-model inference pipelines on edge devices. However, cost-effectively deploying these pipelines while optimizing Quality of Service (QoS) and costs poses significant challenges. Existing solutions often neglect device resource constraints, focusing mainly on inference accuracy and cost efficiency. To address this, we develop a framework for configuring multi-model inference pipelines. Specifically: 1) We model the decision-making problem by considering the pipeline's QoS, costs, and device resource limitations. 2) We create a feature extraction module using residual networks and a load prediction model based on Long Short-Term Memory (LSTM) to gather comprehensive node and pipeline status information. Then, we implement a Reinforcement Learning (RL) algorithm based on policy gradients for online configuration decisions. 3) Experiments conducted in a real Kubernetes cluster show that our approach significantly improve QoS while reducing costs and shorten decision-making time for complex pipelines compared to baseline algorithms.

cs.DC↗