arXiv subjects

Jianwei Wu

Publications and source records attributed to Jianwei Wu.

6 recordsLinked to original sources

arXiv2026

RELATE: A Reinforcement Learning-Enhanced LLM Framework for Advertising Text Generation

In online advertising, advertising text plays a critical role in attracting user engagement and driving advertiser value. Existing industrial systems typically follow a two-stage paradigm, where candidate texts are first generated and subsequently aligned with online performance metrics such as click-through rate(CTR). This separation often leads to misaligned optimization objectives and low funnel efficiency, limiting global optimality. To address these limitations, we propose RELATE, a reinforcement learning-based end-to-end framework that unifies generation and objective alignment within a single model. Instead of decoupling text generation from downstream metric alignment, RELATE integrates performance and compliance objectives directly into the generation process via policy learning. To better capture ultimate advertiser value beyond click-level signals, We incorporate conversion-oriented metrics into the objective and jointly model them with compliance constraints as multi-dimensional rewards, enabling the model to generate high-quality ad texts that improve conversion performance under policy constraints. Extensive experiments on large-scale industrial datasets demonstrate that RELATE consistently outperforms baselines. Furthermore, online deployment on a production advertising platform yields statistically significant improvements in click-through conversion rate(CTCVR) under strict policy constraints, validating the robustness and real-world effectiveness of the proposed framework.

cs.AI↗

arXiv2022

Shortcomings of Class-level Documentation: A Survey

To better understand the shortcomings of class-level documentation, we conducted a survey of 167 experienced software developers. The survey focused on the participants' programming-related information needs and how often class-level documentation satisfies such needs.

cs.SE↗

arXiv2021

Preliminary Study on Forced Oscillation of Power System with Quadratic Nonlinearity

Forced oscillation (FO) is a significant concern threating the power system stability. Its mechanisms are mostly studied via linear models. However, FO amplitude is increasing, e.g., Nordic and Western American FOs, which can stimulate power system nonlinearity. Hence, this paper incorporates nonlinearity in FO mechanism analysis. The multi-scale technique is employed in solving the forced oscillation equation to handle the quadratic nonlinearity. The amplitude-frequency characteristic curves and first-order approximate expressions are derived. The frequency deviation and jumping phenomenon caused by nonlinearity are discovered and further analyzed by comparing with linear models. This paper provides a preliminary research for nonlinear FOs of power system, and more characteristics should be further analysis in the near future.

eess.SY↗

arXiv2020

A Pattern-based Approach to Detect and Improve Non-descriptive Test Names

Unit tests are an important artifact that supports the software development process in several ways. For example, when a test fails, its name can provide the first step towards understanding the purpose of the test. Unfortunately, unit tests often lack descriptive names. In this paper, we propose a new, pattern-based approach that can help developers improve the quality of test names of JUnit tests by making them more descriptive. It does this by detecting non-descriptive test names and in some cases, providing additional information about how the name can be improved. Our approach was assessed using an empirical evaluation on 34352 JUnit tests. The results of the evaluation show that the approach is feasible, accurate, and useful at discriminating descriptive and non-descriptive names with a 95% true-positive rate.

cs.SE↗

arXiv2019

Combinatorial Keyword Recommendations for Sponsored Search with Deep Reinforcement Learning

In sponsored search, keyword recommendations help advertisers to achieve much better performance within limited budget. Many works have been done to mine numerous candidate keywords from search logs or landing pages. However, the strategy to select from given candidates remains to be improved. The existing relevance-based, popularity-based and regular combinatorial strategies fail to take the internal or external competitions among keywords into consideration. In this paper, we regard keyword recommendations as a combinatorial optimization problem and solve it with a modified pointer network structure. The model is trained on an actor-critic based deep reinforcement learning framework. A pre-clustering method called Equal Size K-Means is proposed to accelerate the training and testing procedure on the framework by reducing the action space. The performance of framework is evaluated both in offline and online environments, and remarkable improvements can be observed.

cs.IR↗

arXiv2017

AdaDNNs: Adaptive Ensemble of Deep Neural Networks for Scene Text Recognition

Recognizing text in the wild is a really challenging task because of complex backgrounds, various illuminations and diverse distortions, even with deep neural networks (convolutional neural networks and recurrent neural networks). In the end-to-end training procedure for scene text recognition, the outputs of deep neural networks at different iterations are always demonstrated with diversity and complementarity for the target object (text). Here, a simple but effective deep learning method, an adaptive ensemble of deep neural networks (AdaDNNs), is proposed to simply select and adaptively combine classifier components at different iterations from the whole learning system. Furthermore, the ensemble is formulated as a Bayesian framework for classifier weighting and combination. A variety of experiments on several typical acknowledged benchmarks, i.e., ICDAR Robust Reading Competition (Challenge 1, 2 and 4) datasets, verify the surprised improvement from the baseline DNNs, and the effectiveness of AdaDNNs compared with the recent state-of-the-art methods.

cs.CV↗