Publications

2026

  1. setlur2026reuse.png
    Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes
    Amrith Setlur, Zijian Wang, Andrew Cohen, Paria Rashidinejad, and Sang Michael Xie
    arXiv, 2026
    arXiv
  2. zhuo2025cyberzero.png
    Cyber-Zero: Training Cybersecurity Agents without Runtime
    Terry Yue Zhuo, Dingmin Wang, Hantian Ding, Varun Kumar, and Zijian Wang
    ICLR, 2026
    Wins the first prize in the CSAW 2025 agentic automated CTF challenge
    arXiv Code

2025

  1. ding2025gtpo.png
    Empowering Multi-Turn Tool-Integrated Reasoning with Group Turn Policy Optimization
    Yifeng Ding, Hung Le, Songyang Han, Kangrui Ruan, Zhenghui Jin, Varun Kumar, Zijian Wang, and Anoop Deoras
    arXiv, 2025
    arXiv
  2. zhuo2025bigcodearena.png
    BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution
    The BigCodeArena Team
    arXiv, 2025
    arXiv Website Code
  3. saha2025breaking.png
    Breaking the Code: Security Assessment of AI Code Agents Through Systematic Jailbreaking Attacks
    Shoumik Saha, Jifan Chen, Sam Mayers, Sanjay Krishna Gouda, Zijian Wang, and Varun Kumar
    arXiv, 2025
    arXiv
  4. zhuo2025training.png
    Training Language Model Agents to Find Vulnerabilities with CTF-Dojo
    Terry Yue Zhuo, Dingmin Wang, Hantian Ding, Varun Kumar, and Zijian Wang
    arXiv, 2025
    arXiv
  5. zhuo2024bcb.png
    BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions
    The BigCodeBench Team
    ICLR (Oral), 2025
    arXiv Website Code
  6. ding2024horizon.png
    Planning-Aware Code Infilling via Horizon-Length Prediction
    Yifeng Ding, Hantian Ding, Shiqi Wang, Qing Sun, Varun Kumar, and Zijian Wang
    EMNLP, 2025
    arXiv
  7. kuhar2024lib.png
    LibEvolutionEval: A Benchmark and Study for Version-Specific Code Generation
    Sachit Kuhar, Wasi Uddin Ahmad, Zijian Wang, Nihal Jain, Haifeng Qian, Baishakhi Ray, Murali Krishna Ramanathan, Xiaofei Ma, and Anoop Deoras
    NAACL (Oral), 2025
    arXiv Website

2024

  1. liu2024learning.png
    Learning Code Preference via Synthetic Evolution
    Jiawei Liu, Thanh Nguyen, Mingyue Shang, Hantian Ding, Xiaopeng Li, Yu Yu, Varun Kumar, and Zijian Wang
    arXiv, 2024
    arXiv Website Code
  2. ding2024fewer.png
    Fewer Truncations Improve Language Modeling
    Hantian Ding, Zijian Wang, Giovanni Paolini, Varun Kumar, Anoop Deoras, Dan Roth, and Stefano Soatto
    ICML, 2024
    Adopted by leading models like DeepSeek-v3 and GLM-4.5, reported in 机器之心
    arXiv Website
  3. zhang2024codefort.png
    CodeFort: Robust Training for Code Generation Models
    Yuhao Zhang, Shiqi Wang, Haifeng Qian, Zijian Wang, Mingyue Shang, Linbo Liu, Sanjay Krishna Gouda, Baishakhi Ray, Murali Krishna Ramanathan, Xiaofei Ma, and Anoop Deoras
    Findings of EMNLP, 2024
    arXiv
  4. athiwaratkun2024token.png
    Token Alignment via Character Matching for Subword Completion
    Ben Athiwaratkun*, Shiqi Wang*, Mingyue Shang*, Yuchen Tian, Zijian Wang, Sujan Kumar Gonugondla, Sanjay Krishna Gouda, Rob Kwiatkowski, Ramesh Nallapati, and Bing Xiang
    Findings of ACL, 2024
    arXiv
  5. lozhkov2024starcoder2.png
    StarCoder 2 and The Stack v2: The Next Generation
    The StarCoder Team
    arXiv, 2024
    arXiv Website Code
  6. ding2022cocomic.png
    CoCoMIC: Code Completion By Jointly Modeling In-file and Cross-file Context
    Yangruibo Ding*, Zijian Wang*, Wasi Ahmad*, Murali Krishna Ramanathan, Ramesh Nallapati, Parminder Bhatia, Dan Roth, and Bing Xiang
    LREC-COLING, 2024
    arXiv

2023

  1. ding2023cross.png
    CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion
    Yangruibo Ding*, Zijian Wang*, Wasi Ahmad*, Hantian Ding, Ming Tan, Nihal Jain, Murali Krishna Ramanathan, Ramesh Nallapati, Parminder Bhatia, Dan Roth, and Bing Xiang
    NeurIPS Datasets and Benchmarks, 2023
    Adopted by DeepSeek-Coder, Qwen2.5-Coder, StarCoder, and Augment Code
    arXiv Website Code
  2. ben2022mbxp.png
    Multi-lingual Evaluation of Code Generation Models
    Ben Athiwaratkun, Sanjay Krishna Gouda, Zijian Wang, Xiaopeng Li, Yuchen Tian, Ming Tan, Wasi Ahmad, Shiqi Wang, Qing Sun, Mingyue Shang, Sujan Gonugondla, and 14 more authors
    ICLR, 2023
    arXiv Code
  3. wang2022recode.png
    ReCode: Robustness Evaluation of Code Generation Models
    Shiqi Wang*, Zheng Li*, Haifeng Qian, Chenghao Yang, Zijian Wang, Varun Kumar, Mingyue Shang, Samson Tan, Baishakhi Ray, Parminder Bhatia, Ramesh Nallapati, and 3 more authors
    ACL, 2023
    arXiv Code
  4. jain2022contragen.png
    ContraCLM: Effective Contrastive Learning For Causal Language Model
    Nihal Jain*, Dejiao Zhang*, Wasi Ahmad*, Zijian Wang, Feng Nan, Xiaopeng Li, Ming Tan, Ramesh Nallapati, Baishakhi Ray, Parminder Bhatia, Xiaofei Ma, and 1 more author
    ACL, 2023
    arXiv
  5. ding2023static.png
    A Static Evaluation of Code Completion by Large Language Models
    Hantian Ding, Varun Kumar, Yuchen Tian, Zijian Wang, Rob Kwiatkowski, Xiaopeng Li, Murali Krishna Ramanathan, Baishakhi Ray, Parminder Bhatia, Sudipta Sengupta, Dan Roth, and 1 more author
    ACL Industry Track, 2023
    arXiv
  6. wei2023towards.png
    Towards Greener Yet Powerful Code Generation via Quantization: An Empirical Study
    Xiaokai Wei, Sujan Gonugondla, Wasi Ahmad, Shiqi Wang, Baishakhi Ray, Haifeng Qian, Xiaopeng Li, Varun Kumar, Zijian Wang, Yuchen Tian, Qing Sun, and 5 more authors
    ESEC/FSE, 2023
    arXiv

2022

  1. li2022debiasing.png
    Debiasing Neural Retrieval via In-batch Balancing Regularization
    Yuantong Li, Xiaokai Wei*, Zijian Wang*, Shen Wang*, Xiaofei Ma, Parminder Bhatia, and Andrew Arnold
    GeBNLP Workshop, 2022
    arXiv
  2. bombari2022towards.png
    Towards Differential Relational Privacy and its use in Question Answering
    Simone Bombari, Alessandro Achille, Zijian Wang, Yu-Xiang Wang, Yusheng Xie, Kunwar Yashraj Singh, Srikar Appalaraju, Vijay Mahadevan, and Stefano Soatto
    arXiv, 2022
    arXiv
  3. li2022dqbart.png
    DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and Quantization
    Zheng Li*, Zijian Wang*, Ming Tan, Ramesh Nallapati, Parminder Bhatia, Andrew Arnold, Bing Xiang, and Dan Roth
    ACL, 2022
    arXiv Code

2021

  1. dhole2021nl.png
    NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation
    The NL-Augmenter Team
    arXiv, 2021
    arXiv Code

2020

  1. kreiss2020modeling.png
    Modeling Subjective Assessments of Guilt in Newspaper Crime Narratives
    Elisa Kreiss*, Zijian Wang*, and Christopher Potts
    CoNLL, 2020
    arXiv Code

2019

  1. wang2019talkdown.png
    TalkDown: A Corpus for Condescension Detection in Context
    Zijian Wang and Christopher Potts
    EMNLP-IJCNLP, 2019
    arXiv Code
  2. qi2019answering.png
    Answering Complex Open-Domain Questions Through Iterative Query Generation
    Peng Qi, Xianwen Lin*, Leo Mehr*, Zijian Wang*, and Christopher D. Manning
    EMNLP-IJCNLP, 2019
    arXiv Code
  3. wang2019demographic.png
    Demographic Inference and Representative Population Estimates from Social Media Data
    Zijian Wang, Scott A. Hale, David Adelani, Przemyslaw A. Grabowicz, Timo Hartmann, Fabian Flöck, and David Jurgens
    WWW, 2019
    Best Poster Award
    arXiv Website Code PyPI

2018

  1. wang2018its.png
    It’s going to be okay: Measuring Access to Support in Online Communities
    Zijian Wang and David Jurgens
    EMNLP, 2018
    arXiv Website PyPI

2017

  1. choi2017social.png
    Social work in the classroom? A tool to evaluate topical relevance in student writing
    Heeryung Choi, Zijian Wang, Christopher Brooks, Kevyn Collins-Thompson, Beth Glover Reed, and Dale Fitch
    EDM, 2017
    arXiv