Author name cluster

Feng Yao

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

2 author rows

ICML Conference 2025 Conference Paper

ProDiff: Prototype-Guided Diffusion for Minimal Information Trajectory Imputation

Tianci Bu
Le Zhou
Wenchuan Yang
Jianhong Mou
Kang Yang
Suoyi Tan
Feng Yao
Jingyuan Wang

Trajectory data is crucial for various applications but often suffers from incompleteness due to device limitations and diverse collection scenarios. Existing imputation methods rely on sparse trajectory or travel information, such as velocity, to infer missing points. However, these approaches assume that sparse trajectories retain essential behavioral patterns, which place significant demands on data acquisition and overlook the potential of large-scale human trajectory embeddings. To address this, we propose ProDiff, a trajectory imputation framework that uses only two endpoints as minimal information. It integrates prototype learning to embed human movement patterns and a denoising diffusion probabilistic model for robust spatiotemporal reconstruction. Joint training with a tailored loss function ensures effective imputation. ProDiff outperforms state-of-the-art methods, improving accuracy by 6. 28% on FourSquare and 2. 52% on WuXi. Further analysis shows a 0. 927 correlation between generated and real trajectories, demonstrating the effectiveness of our approach.

Details

NeurIPS Conference 2025 Conference Paper

Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective

Jorge (Zhoujun) Cheng
Shibo Hao
Tianyang Liu
Fan Zhou
Yutao Xie
Feng Yao
Yuexin Bian
Nilabjo Dey

Reinforcement learning (RL) has shown promise in enhancing large language model (LLM) reasoning, yet progress towards broader capabilities is limited by the availability of high-quality, multi-domain datasets. This work introduces \ours, a 92K RL-for-reasoning dataset designed to address this gap, covering six reasoning domains: Math, Code, Science, Logic, Simulation, and Tabular, each with corresponding verifiers. We build \ours via a careful data-curation pipeline, including sourcing, deduplication, reward design, and domain-specific and difficulty-based filtering, to facilitate the systematic investigation of cross-domain RL generalization. Our study using \ours suggests the efficacy of a simple mixed-domain RL training approach and reveals several key aspects affecting cross-domain transferability. We further train two models {\ours}-7B and {\ours}-32B purely with RL on our curated data and observe largely improved performance over leading open RL reasoning model baselines, with gains of 7. 3\% and 7. 8\% respectively on an extensive 17-task, six-domain evaluation suite. We are releasing our dataset, code, and evaluation suite to the community, aiming to support further research and development of more general RL-enhanced reasoning models.

PDF Details

NeurIPS Conference 2025 Conference Paper

Training Language Models to Generate Quality Code with Program Analysis Feedback

Feng Yao
Zilong Wang
Liyuan Liu
Junxia Cui
Li Zhong
Xiaohan Fu
Haohui Mai
Viswanathan Krishnan

Code generation with large language models (LLMs), often termed vibe coding, is increasingly adopted in production but fails to ensure code quality, particularly in security (e. g. , SQL injection vulnerabilities) and maintainability (e. g. , missing type annotations). Existing methods, such as supervised fine-tuning and rule-based post-processing, rely on labor-intensive annotations or brittle heuristics, limiting their scalability and effectiveness. We propose REAL (Reinforcement rEwards from Automated anaLysis), a reinforcement learning framework that trains LLMs to generate production-quality code using program analysis–guided feedback. Specifically, REAL integrates two automated signals: (1) static analyzers detecting security and maintainability defects and (2) unit tests ensuring functional correctness. Unlike prior work, our framework is prompt-agnostic and reference-free, enabling scalable supervision without manual intervention. Experiments across multiple datasets and model scales demonstrate that REAL outperforms state-of-the-art methods in simultaneous assessments of functionality and code quality. Our work bridges the gap between rapid prototyping and production-ready code, enabling LLMs to deliver both speed and quality.

PDF Details

EAAI Journal 2024 Journal Article

Assessing growth potential of careers with occupational mobility network and ensemble framework

Jiamin Liu
Tao Wang
Feng Yao
Witold Pedrycz
Yanjie Song
Renjie He

The growth potential of a career reflects its future prospects and is an important consideration for individuals and organizations when career planning. There is still a lack of quantitative assessment tools for growth potential of careers. In this study, considering the key role of human capital in human resource management, as well as the excellent performance of complex network and machine learning in big data analysis and prediction, a career growth potential assessment model with human capital ensemble is proposed through human capital-based occupational mobility network and ensemble learning. First, an occupational mobility network is constructed based on online professional dataset to associate occupations with each other. Then, five dimensions of human capital measurements are designed to quantify human capital in terms of education, experience, social capital, occupational size, and concentration. These are then combined with the occupational mobility network to create a new network that depicts human capital flows among occupations. Finally, an ensemble framework for assessing career growth potential is constructed to integrate multidimensional human capital information in the network and obtain quantitative scores of growth potential. This study is the original attempt to adopt a data-driven idea and an intelligent approach to understand career growth potential. The experimental results show that it also makes a useful exploration for modeling human capital flows and intelligent assessment of career prospects.

Details DOI

AAAI Conference 2023 Conference Paper

Unsupervised Legal Evidence Retrieval via Contrastive Learning with Approximate Aggregated Positive

Feng Yao
Jingyuan Zhang
Yating Zhang
Xiaozhong Liu
Changlong Sun
Yun Liu
Weixing Shen

Verifying the facts alleged by the prosecutors before the trial requires the judges to retrieve evidence within the massive materials accompanied. Existing Legal AI applications often assume the facts are already determined and fail to notice the difficulty of reconstructing them. To build a practical Legal AI application and free the judges from the manually searching work, we introduce the task of Legal Evidence Retrieval, which aims at automatically retrieving the precise fact-related verbal evidence within a single case. We formulate the task in a dense retrieval paradigm, and jointly learn the constrastive representations and alignments between facts and evidence. To get rid of the tedious annotations, we construct an approximated positive vector for a given fact by aggregating a set of evidence from the same case. An entropy-based denoise technique is further applied to mitigate the impact of false positive samples. We train our models on tens of thousands of unlabeled cases and evaluate them on a labeled dataset containing 919 cases and 4,336 queries. Experimental results indicate that our approach is effective and outperforms other state-of-the-art representation and retrieval models. The dataset and code are available at https://github.com/yaof20/LER.

PDF Details DOI