@inproceedings{treeprompting,
  title = {{Tree Prompting: Efficient Task Adaptation without Fine-Tuning}},
  author = {Morris, John X. and Singh, Chandan and Rush, Alexander M. and Gao, Jianfeng and Deng, Yuntian},
  year = {2023},
  booktitle = {EMNLP 2023},
  url = {https://arxiv.org/html/2310.14034v1},
  eprint = {2310.14034},
  archivePrefix = {arXiv},
  doi = {10.18653/v1/2023.emnlp-main.384}
}

@article{augtree,
  title = {{Augmenting interpretable models with large language models during training}},
  author = {Singh, Chandan and Askari, Armin and Caruana, Rich and Gao, Jianfeng},
  year = {2023},
  journal = {Nature Communications},
  url = {https://www.nature.com/articles/s41467-023-43713-1},
  volume = {14},
  number = {1},
  pages = {7913},
  doi = {10.1038/s41467-023-43713-1}
}

@misc{gptree,
  title = {{GPTree: Towards Explainable Decision-Making via LLM-powered Decision Trees}},
  author = {Xiong, Sichao and Ihlamur, Yigit and Alican, Fuat and Yin, Aaron Ontoyin},
  year = {2024},
  url = {https://arxiv.org/html/2411.08257v1},
  eprint = {2411.08257},
  archivePrefix = {arXiv}
}

@misc{act,
  title = {{ACT: Agentic Classification Tree}},
  author = {Grari, Vincent and Arni, Tim and Laugel, Thibault and Lamprier, Sylvain and Zou, James and Detyniecki, Marcin},
  year = {2025},
  url = {https://arxiv.org/html/2509.26433v4},
  eprint = {2509.26433},
  archivePrefix = {arXiv}
}

@inproceedings{residualebm,
  title = {{Residual Energy-Based Models for Text Generation}},
  author = {Deng, Yuntian and Bakhtin, Anton and Ott, Myle and Szlam, Arthur and Ranzato, Marc’Aurelio},
  year = {2020},
  booktitle = {ICLR 2020},
  url = {https://arxiv.org/html/2004.11714v1},
  eprint = {2004.11714},
  archivePrefix = {arXiv}
}

@article{residualebmjmlr,
  title = {{Residual Energy-Based Models for Text}},
  author = {Bakhtin, Anton and Deng, Yuntian and Gross, Sam and Ott, Myle and Ranzato, Marc’Aurelio and Szlam, Arthur},
  year = {2021},
  journal = {Journal of Machine Learning Research},
  url = {https://www.jmlr.org/papers/v22/20-326.html},
  volume = {22},
  number = {40},
  pages = {1--41}
}

@inproceedings{edlm,
  title = {{Energy-Based Diffusion Language Models for Text Generation}},
  author = {Xu, Minkai and Geffner, Tomas and Kreis, Karsten and Nie, Weili and Xu, Yilun and Leskovec, Jure and Ermon, Stefano and Vahdat, Arash},
  year = {2025},
  booktitle = {ICLR 2025},
  url = {https://arxiv.org/html/2410.21357v4},
  eprint = {2410.21357},
  archivePrefix = {arXiv}
}

@misc{unifiedenergy,
  title = {{Unified Energy for Invariant and Independent Decoding in Diffusion Language Models}},
  author = {Yan, Yuchen and Xu, Minkai and Yang, Zaiquan and Bian, Yatao},
  year = {2026},
  url = {https://arxiv.org/html/2606.09159v1},
  eprint = {2606.09159},
  archivePrefix = {arXiv}
}

@inproceedings{neuraltrfnce,
  title = {{Learning Neural Trans-Dimensional Random Field Language Models with Noise-Contrastive Estimation}},
  author = {Wang, Bin and Ou, Zhijian},
  year = {2018},
  booktitle = {ICASSP 2018},
  url = {https://arxiv.org/abs/1710.10739},
  eprint = {1710.10739},
  archivePrefix = {arXiv}
}

@inproceedings{deng2020cascaded,
  title = {{Cascaded Text Generation with Markov Transformers}},
  author = {Deng, Yuntian and Rush, Alexander M.},
  year = {2020},
  booktitle = {NeurIPS 2020},
  url = {https://arxiv.org/abs/2006.01112},
  eprint = {2006.01112},
  archivePrefix = {arXiv}
}

@inproceedings{deng-rush-2021-sequence,
  title = {{Sequence-to-Lattice Models for Fast Translation}},
  author = {Deng, Yuntian and Rush, Alexander M.},
  year = {2021},
  booktitle = {Findings of EMNLP 2021},
  url = {https://aclanthology.org/2021.findings-emnlp.318/},
  doi = {10.18653/v1/2021.findings-emnlp.318}
}

@inproceedings{sun2019fast,
  title = {{Fast Structured Decoding for Sequence Models}},
  author = {Sun, Zhiqing and Li, Zhuohan and Wang, Haoqing and He, Di and Lin, Zi and Deng, Zhi-Hong},
  year = {2019},
  booktitle = {NeurIPS 2019},
  url = {https://proceedings.neurips.cc/paper_files/paper/2019/hash/74563ba21a90da13dacf2a73e3ddefa7-Abstract.html},
  eprint = {1910.11555},
  archivePrefix = {arXiv}
}

@inproceedings{li2026factorization,
  title = {{Breaking the Factorization Barrier in Diffusion Language Models}},
  author = {Li, Ian and Shao, Zilei and Wang, Benjie and Yu, Rose and Van den Broeck, Guy and Liu, Anji},
  year = {2026},
  booktitle = {ICML 2026},
  url = {https://proceedings.mlr.press/v306/li26fd.html},
  eprint = {2603.00045},
  archivePrefix = {arXiv}
}

@inproceedings{ji2026dadlm,
  title = {{DA-DLM: Explicitly Modeling Token Dependencies in Diffusion Language Models}},
  author = {Ji, Pengyu and Zhang, Zichen and Hu, Xiang and Tu, Kewei},
  year = {2026},
  booktitle = {EMNLP 2026},
  url = {https://aclanthology.org/2026.emnlp-main.2094/},
  eprint = {2609.15070},
  archivePrefix = {arXiv},
  doi = {10.18653/2026.emnlp-main.2094}
}

@misc{rusanovsky2026lilicorr,
  title = {{LiLiCorr: Lightweight Likelihood Correlation of Parallel Drafts for Speculative Decoding}},
  author = {Rusanovsky, Matan and Miron, Yoav and Uziel, Roy and Belhasin, Omer and Guo, Hao and Zilberstein, Ran and Ashkenazi, Maor and Elad, Michael},
  year = {2026},
  url = {https://arxiv.org/abs/2608.20530},
  eprint = {2608.20530},
  archivePrefix = {arXiv}
}

@inproceedings{li2026diffuspec,
  title = {{DiffuSpec: Unlocking Diffusion Language Models for Speculative Decoding}},
  author = {Li, Guanghao and Fu, Zhihui and Fang, Min and Zhao, Qibin and Tang, Ming and Yuan, Chun and Wang, Jun},
  year = {2026},
  booktitle = {Findings of ACL 2026},
  url = {https://aclanthology.org/2026.findings-acl.1048/},
  doi = {10.18653/v1/2026.findings-acl.1048}
}

@inproceedings{deng2018latent,
  title = {{Latent Alignment and Variational Attention}},
  author = {Deng, Yuntian and Kim, Yoon and Chiu, Justin and Guo, Demi and Rush, Alexander M.},
  year = {2018},
  booktitle = {NeurIPS 2018},
  url = {https://arxiv.org/abs/1807.03756},
  eprint = {1807.03756},
  archivePrefix = {arXiv}
}

@inproceedings{xu2015show,
  title = {{Show, Attend and Tell: Neural Image Caption Generation with Visual Attention}},
  author = {Xu, Kelvin and Ba, Jimmy Lei and Kiros, Ryan and Cho, Kyunghyun and Courville, Aaron and Salakhutdinov, Ruslan and Zemel, Richard S. and Bengio, Yoshua},
  year = {2015},
  booktitle = {ICML 2015},
  url = {https://proceedings.mlr.press/v37/xuc15.html},
  eprint = {1502.03044},
  archivePrefix = {arXiv}
}

@inproceedings{kim2017structured,
  title = {{Structured Attention Networks}},
  author = {Kim, Yoon and Denton, Carl and Hoang, Luong and Rush, Alexander M.},
  year = {2017},
  booktitle = {ICLR 2017},
  url = {https://arxiv.org/abs/1702.00887},
  eprint = {1702.00887},
  archivePrefix = {arXiv}
}

@inproceedings{bahuleyan2018variational,
  title = {{Variational Attention for Sequence-to-Sequence Models}},
  author = {Bahuleyan, Hareesh and Mou, Lili and Vechtomova, Olga and Poupart, Pascal},
  year = {2018},
  booktitle = {COLING 2018},
  url = {https://aclanthology.org/C18-1142/},
  eprint = {1712.08207},
  archivePrefix = {arXiv}
}

@inproceedings{fan2020bayesian,
  title = {{Bayesian Attention Modules}},
  author = {Fan, Xinjie and Zhang, Shujian and Chen, Bo and Zhou, Mingyuan},
  year = {2020},
  booktitle = {NeurIPS 2020},
  url = {https://arxiv.org/abs/2010.10604},
  eprint = {2010.10604},
  archivePrefix = {arXiv}
}

@inproceedings{deng-etal-2022-model,
  title = {{Model Criticism for Long-Form Text Generation}},
  author = {Deng, Yuntian and Kuleshov, Volodymyr and Rush, Alexander M.},
  year = {2022},
  booktitle = {EMNLP 2022},
  url = {https://aclanthology.org/2022.emnlp-main.815/},
  eprint = {2210.08444},
  archivePrefix = {arXiv},
  doi = {10.18653/v1/2022.emnlp-main.815}
}

@inproceedings{guan-etal-2021-openmeva,
  title = {{OpenMEVA: A Benchmark for Evaluating Open-ended Story Generation Metrics}},
  author = {Guan, Jian and Zhang, Zhexin and Feng, Zhuoer and Liu, Zitao and Ding, Wenbiao and Mao, Xiaoxi and Fan, Changjie and Huang, Minlie},
  year = {2021},
  booktitle = {ACL-IJCNLP 2021},
  url = {https://aclanthology.org/2021.acl-long.500/},
  doi = {10.18653/v1/2021.acl-long.500}
}

@misc{yang2024goodstory,
  title = {{What Makes a Good Story and How Can We Measure It? A Comprehensive Survey of Story Evaluation}},
  author = {Yang, Dingyi and Jin, Qin},
  year = {2024},
  url = {https://arxiv.org/abs/2408.14622},
  eprint = {2408.14622},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2408.14622}
}

@inproceedings{deng2023markuptoimage,
  title = {{Markup-to-Image Diffusion Models with Scheduled Sampling}},
  author = {Deng, Yuntian and Kojima, Noriyuki and Rush, Alexander M.},
  year = {2023},
  booktitle = {ICLR 2023},
  url = {https://arxiv.org/abs/2210.05147},
  eprint = {2210.05147},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2210.05147}
}

@inproceedings{zhong2023contrastaugmented,
  title = {{Contrast-augmented Diffusion Model with Fine-grained Sequence Alignment for Markup-to-Image Generation}},
  author = {Zhong, Guojin and Yuan, Jin and Wang, Pan and Yang, Kailun and Guan, Weili and Li, Zhiyong},
  year = {2023},
  booktitle = {ACM Multimedia 2023},
  url = {https://arxiv.org/abs/2308.01147},
  eprint = {2308.01147},
  archivePrefix = {arXiv}
}

@inproceedings{pmlr-v202-ning23a,
  title = {{Input Perturbation Reduces Exposure Bias in Diffusion Models}},
  author = {Ning, Mang and Sangineto, Enver and Porrello, Angelo and Calderara, Simone and Cucchiara, Rita},
  year = {2023},
  booktitle = {ICML 2023},
  url = {https://proceedings.mlr.press/v202/ning23a.html}
}

@inproceedings{zhang-etal-2025-interactive,
  title = {{Interactive Training: Feedback-Driven Neural Network Optimization}},
  author = {Zhang, Wentao and Lu, Yang Young and Deng, Yuntian},
  year = {2025},
  booktitle = {EMNLP 2025 System Demonstrations},
  url = {https://aclanthology.org/2025.emnlp-demos.65/},
  eprint = {2510.02297},
  archivePrefix = {arXiv},
  doi = {10.18653/v1/2025.emnlp-demos.65}
}

@misc{zhang2026interactivetraining2,
  title = {{Interactive Training 2: Auditable Control Plane for Live Model Training}},
  author = {Zhang, Wentao and Pan, Xuanhe and Zhou, Han and Lu, Yang and Deng, Yuntian},
  year = {2026},
  url = {https://arxiv.org/abs/2607.18314},
  eprint = {2607.18314},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2607.18314}
}

@misc{shabgahi2023livetune,
  title = {{LiveTune: Dynamic Parameter Tuning for Feedback-Driven Optimization}},
  author = {Shabgahi, Soheil Zibakhsh and Sheybani, Nojan and Tabrizi, Aiden and Koushanfar, Farinaz},
  year = {2023},
  url = {https://arxiv.org/abs/2311.17279},
  eprint = {2311.17279},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2311.17279}
}

@misc{rao2026aitrainingmanager,
  title = {{AI Training Manager: Bounded Closed-Loop Control of Adaptive Training Recipes}},
  author = {Rao, Anjali and Advani, Nikhil Kamalkumar},
  year = {2026},
  url = {https://arxiv.org/abs/2606.29871},
  eprint = {2606.29871},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2606.29871}
}