Publications

• Improving Faithfulness of Text-to-Image Diffusion Models through Inference Intervention
  Danfeng Guo, Sanchit Agarwal, Yu-Hsiang Lin, Jiun-Yu Kao, Tagyoung Chung, Nanyun Peng, Mohit Bansal
  WACV 2025
  [pdf]
  
  
• LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints
  Thomas Palmeira Ferraz, Kartik Mehta, Yu-Hsiang Lin, Haw-Shiuan Chang, Shereen Oraby, Sijia Liu, Vivek Subramanian, Tagyoung Chung, Mohit Bansal, Nanyun Peng
  NeurIPS 2024 Sys2-Reasoning Workshop, EMNLP 2024 Findings
  [pdf] [arXiv:2410.06458]
  
  
• Redefining Proactivity for Information Seeking Dialogue
  Jing Yang Lee, Seokhwan Kim, Kartik Mehta, Jiun-Yu Kao, Yu-Hsiang Lin, Arpit Gupta
  EMNLP 2024 SiCon Workshop
  [pdf] [arXiv:2410.15297]
  
  
• Mitigating bias for question answering models by tracking bias influence
  Mingyu Derek Ma, Jiun-Yu Kao, Arpit Gupta, Yu-Hsiang Lin, Wenbo Zhao, Tagyoung Chung, Wei Wang, Kai-Wei Chang, Nanyun Peng
  NAACL 2024
  [pdf] [arXiv:2310.08795]
  
  
• CLIPSynth: learning text-to-audio synthesis from videos using CLIP and diffusion models
  Hao-Wen Dong, Gunnar A. Sigurdsson, Chenyang Tao, Jiun-Yu Kao, Yu-Hsiang Lin, Anjali Narayan-Chen, Arpit Gupta, Tagyoung Chung, Jing Huang, Nanyun Peng, Wenbo Zhao
  CVPR 2023 Sight and Sound Workshop
  [pdf]
  
  
• Analysis of e-commerce ranking signals via signal temporal logic
  Tommaso Dreossi, Giorgio Ballardin, Parth Gupta, Jan Bakus, Yu-Hsiang Lin, Vamsi Salaka
  Proceedings 6th International Workshop on Symbolic-Numeric methods for Reasoning about CPS and IoT (SNR 2020), EPTCS 331, pages 33-42 (2021)
  [pdf] [arXiv:2101.05415]
  
  
• Generating queries for new ASINs in cold start
  Yu-Hsiang Lin, Jan Bakus, Jianhao Peng, Tommaso Dreossi, Parth Gupta, Vamsi Salaka
  Amazon Machine Learning Conference 2020
  
  
• Treating cold start in product search by priors
  Parth Gupta, Tommaso Dreossi, Jan Bakus, Yu-Hsiang Lin, Vamsi Salaka
  The Web Conference (WWW) 2020
  [pdf]
  
  
• Choosing transfer languages for cross-lingual learning
  Yu-Hsiang Lin, Chian-Yu Chen, Jean Lee, Zirui Li, Yuyan Zhang, Mengzhou Xia, Shruti Rijhwani, Junxian He, Zhisong Zhang, Xuezhe Ma, Antonios Anastasopoulos, Patrick Littell, Graham Neubig
  ACL 2019
  [pdf] [arXiv:1905.12688]
  
  
• Towards a general-purpose linguistic annotation backend
  Graham Neubig, Patrick Littell, Chian-Yu Chen, Jean Lee, Zirui Li, Yu-Hsiang Lin, Yuyan Zhang
  Proceedings of the Workshop on Computational Methods for Endangered Languages: Vol. 2, Article 1 (2019)
  [pdf] [arXiv:1812.05272]
  
  
• Distributed Newton methods for deep neural networks
  Chien-Chih Wang, Kent Loong Tan, Chun-Ting Chen, Yu-Hsiang Lin, S. Sathiya Keerthi, Dhruv Mahajan, S. Sundararajan, Chih-Jen Lin
  Neural Computation 30, 1673 (2018)
  [pdf] [arXiv:1802.00130] [suppl, code]
  
  
• Suppression of long-wavelength CMB spectrum from the no-boundary initial condition
  Pisin Chen, Yu-Hsiang Lin, and Dong-han Yeom (First-author. Authors in alphabetical order.)
  Eur. Phys. J. C 78, 930 (2018)
  [pdf] [arXiv:1707.01471]
  
  
• What initial condition of inflation would suppress the large-scale CMB spectrum?
  Pisin Chen and Yu-Hsiang Lin (First-author. Authors in alphabetical order.)
  Phys. Rev. D 93, 023503 (2016)
  [pdf] [arXiv:1505.05980] [code]
  
  
• Slow-roll inflation preceded by a topological defect phase a la Chaplygin gas
  Mariam Bouhmadi-Lopez, Pisin Chen, Yu-Chien Huang, and Yu-Hsiang Lin
  Phys. Rev. D 87, 103513 (2013)
  [pdf] [arXiv:1212.2641]