arXiv subjects

Zhi Zheng

Publications and source records attributed to Zhi Zheng.

98 records · Page 6Linked to original sources

arXiv2023

Generative Job Recommendations with Large Language Model

The rapid development of online recruitment services has encouraged the utilization of recommender systems to streamline the job seeking process. Predominantly, current job recommendations deploy either collaborative filtering or person-job matching strategies. However, these models tend to operate as "black-box" systems and lack the capacity to offer explainable guidance to job seekers. Moreover, conventional matching-based recommendation methods are limited to retrieving and ranking existing jobs in the database, restricting their potential as comprehensive career AI advisors. To this end, here we present GIRL (GeneratIve job Recommendation based on Large language models), a novel approach inspired by recent advancements in the field of Large Language Models (LLMs). We initially employ a Supervised Fine-Tuning (SFT) strategy to instruct the LLM-based generator in crafting suitable Job Descriptions (JDs) based on the Curriculum Vitae (CV) of a job seeker. Moreover, we propose to train a model which can evaluate the matching degree between CVs and JDs as a reward model, and we use Proximal Policy Optimization (PPO)-based Reinforcement Learning (RL) method to further fine-tine the generator. This aligns the generator with recruiter feedback, tailoring the output to better meet employer preferences. In particular, GIRL serves as a job seeker-centric generative model, providing job suggestions without the need of a candidate set. This capability also enhances the performance of existing job recommendation models by supplementing job seeking features with generated content. With extensive experiments on a large-scale real-world dataset, we demonstrate the substantial effectiveness of our approach. We believe that GIRL introduces a paradigm-shifting approach to job recommendation systems, fostering a more personalized and comprehensive job-seeking experience.

cs.IR↗

arXiv2023

Roller-Quadrotor: A Novel Hybrid Terrestrial/Aerial Quadrotor with Unicycle-Driven and Rotor-Assisted Turning

The Roller-Quadrotor is a novel quadrotor that combines the maneuverability of aerial drones with the endurance of ground vehicles. This work focuses on the design, modeling, and experimental validation of the Roller-Quadrotor. Flight capabilities are achieved through a quadrotor configuration, with four thrust-providing actuators. Additionally, rolling motion is facilitated by a unicycle-driven and rotor-assisted turning structure. By utilizing terrestrial locomotion, the vehicle can overcome rolling and turning resistance, thereby conserving energy compared to its flight mode. This innovative approach not only tackles the inherent challenges of traditional rotorcraft but also enables the vehicle to navigate through narrow gaps and overcome obstacles by taking advantage of its aerial mobility. We develop comprehensive models and controllers for the Roller-Quadrotor and validate their performance through experiments. The results demonstrate its seamless transition between aerial and terrestrial locomotion, as well as its ability to safely navigate through gaps half the size of its diameter. Moreover, the terrestrial range of the vehicle is approximately 2.8 times greater, while the operating time is about 41.2 times longer compared to its aerial capabilities. These findings underscore the feasibility and effectiveness of the proposed structure and control mechanisms for efficient navigation through challenging terrains while conserving energy.

cs.RO↗

arXiv2023

Catch Planner: Catching High-Speed Targets in the Flight

Catching high-speed targets in the flight is a complex and typical highly dynamic task. In this paper, we propose Catch Planner, a planning-with-decision scheme for catching. For sequential decision making, we propose a policy search method based on deep reinforcement learning. In order to make catching adaptive and flexible, we propose a trajectory optimization method to jointly optimize the highly coupled catching time and terminal state while considering the dynamic feasibility and safety. We also propose a flexible constraint transcription method to catch targets at any reasonable attitude and terminal position bias. The proposed Catch Planner provides a new paradigm for the combination of learning and planning and is integrated on the quadrotor designed by ourselves, which runs at 100hz on the onboard computer. Extensive experiments are carried out in real and simulated scenes to verify the robustness of the proposed method and its expansibility when facing a variety of high-speed flying targets.

cs.RO↗

arXiv2023

Enhancing Chat Language Models by Scaling High-quality Instructional Conversations

Fine-tuning on instruction data has been widely validated as an effective practice for implementing chat language models like ChatGPT. Scaling the diversity and quality of such data, although straightforward, stands a great chance of leading to improved performance. This paper aims to improve the upper bound of open-source models further. We first provide a systematically designed, diverse, informative, large-scale dataset of instructional conversations, UltraChat, which does not involve human queries. Our objective is to capture the breadth of interactions that a human might have with an AI assistant and employs a comprehensive framework to generate multi-turn conversation iteratively. UltraChat contains 1.5 million high-quality multi-turn dialogues and covers a wide range of topics and instructions. Our statistical analysis of UltraChat reveals its superiority in various key metrics, including scale, average length, diversity, coherence, etc., solidifying its position as a leading open-source dataset. Building upon UltraChat, we fine-tune a LLaMA model to create a powerful conversational model, UltraLLaMA. Our evaluations indicate that UltraLLaMA consistently outperforms other open-source models, including Vicuna, the previously recognized state-of-the-art open-source model. The dataset and the model will be publicly released\footnote{\url{https://github.com/thunlp/UltraChat}}.

cs.CL↗

arXiv2021

Drug Package Recommendation via Interaction-aware Graph Induction

Recent years have witnessed the rapid accumulation of massive electronic medical records (EMRs), which highly support the intelligent medical services such as drug recommendation. However, prior arts mainly follow the traditional recommendation strategies like collaborative filtering, which usually treat individual drugs as mutually independent, while the latent interactions among drugs, e.g., synergistic or antagonistic effect, have been largely ignored. To that end, in this paper, we target at developing a new paradigm for drug package recommendation with considering the interaction effect within drugs, in which the interaction effects could be affected by patient conditions. Specifically, we first design a pre-training method based on neural collaborative filtering to get the initial embedding of patients and drugs. Then, the drug interaction graph will be initialized based on medical records and domain knowledge. Along this line, we propose a new Drug Package Recommendation (DPR) framework with two variants, respectively DPR on Weighted Graph (DPR-WG) and DPR on Attributed Graph (DPR-AG) to solve the problem, in which each the interactions will be described as signed weights or attribute vectors. In detail, a mask layer is utilized to capture the impact of patient condition, and graph neural networks (GNNs) are leveraged for the final graph induction task to embed the package. Extensive experiments on a real-world data set from a first-rate hospital demonstrate the effectiveness of our DPR framework compared with several competitive baseline methods, and further support the heuristic study for the drug package generation task with adequate performance.

cs.IR↗

arXiv2020

BERT-QE: Contextualized Query Expansion for Document Re-ranking

Query expansion aims to mitigate the mismatch between the language used in a query and in a document. However, query expansion methods can suffer from introducing non-relevant information when expanding the query. To bridge this gap, inspired by recent advances in applying contextualized models like BERT to the document retrieval task, this paper proposes a novel query expansion model that leverages the strength of the BERT model to select relevant document chunks for expansion. In evaluation on the standard TREC Robust04 and GOV2 test collections, the proposed BERT-QE model significantly outperforms BERT-Large models.

cs.IR↗

arXiv2012

Stochastic Stefan Problems Driven By Standard Brownian Sheets

In this paper we study the effect of stochastic perturbations on a common type of moving boundary value PDE's which endorse Stefan boundary conditions, or Stefan problems, and show the existence and uniqueness of the solutions to a number of stochastic equations of this kind. Moreover we also derive the space and time regularities of the solutions and the associated boundaries via Kolmogorov's Continuity Theorem in an appropriately defined normed space. The paper first conveys our previous results where randomness is smoothly correlated in space and Brownian in time, then introduces a new methodology that enables us to prove the existence and uniqueness of the solution to the standard heat equation driven by a space-time Brownian sheet as well as its boundary regularity, and finally extends it to the stochastic moving boundary partial PDE's driven by the same type of randomness.

math.PR↗

arXiv2012

A Model of Market Limit Orders By Stochastic PDE's, Parameter Estimation, and Investment Optimization

In this paper we introduce a completely continuous and time-variate model of the evolution of market limit orders based on the existence, uniqueness, and regularity of the solutions to a type of stochastic partial differential equations obtained in Zheng and Sowers (2012). In contrary to several models proposed and researched in literature, this model provides complete continuity in both time and price inherited from the stochastic PDE, and thus is particularly suitable for the cases where transactions happen in an extremely fast pace, such as those delivered by high frequency traders (HFT's). We first elaborate the precise definition of the model with its associated parameters, and show its existence and uniqueness from the related mathematical results given a fixed set of parameters. Then we statistically derive parameter estimation schemes of the model using maximum likelihood and least mean-square-errors estimation methods under certain criteria such as AIC to accommodate to variant number of parameters . Finally as a typical economics and finance use case of the model we settle the investment optimization problem in both static and dynamic sense by analysing the stochastic (Itô) evolution of the utility function of an investor or trader who takes the model and its parameters as exogenous. Two theorems are proved which provide criteria for determining the best (limit) price and time point to make the transaction.

q-fin.TR↗