| Approximate nearest neighbor negative contrastive learning for dense text retrieval L Xiong, C Xiong, Y Li, KF Tang, J Liu, P Bennett, J Ahmed, A Overwijk International Conference on Learning Representations (ICLR), 2021 | 1608 | 2021 |
| Less is more: Pre-train a strong text encoder for dense retrieval using a weak decoder S Lu, D He, C Xiong, G Ke, W Malik, Z Dou, P Bennett, T Liu, A Overwijk arXiv preprint arXiv:2102.09206, 2021 | 100 | 2021 |
| Open domain web keyphrase extraction beyond language modeling L Xiong, C Hu, C Xiong, D Campos, A Overwijk arXiv preprint arXiv:1911.02671, 2019 | 80 | 2019 |
| Coco-dr: Combating distribution shifts in zero-shot dense retrieval with contrastive and distributionally robust learning Y Yu, C Xiong, S Sun, C Zhang, A Overwijk arXiv preprint arXiv:2210.15212, 2022 | 77 | 2022 |
| WikiTranslate: query translation for cross-lingual information retrieval using only Wikipedia D Nguyen, A Overwijk, C Hauff, DRB Trieschnigg, D Hiemstra, F De Jong Workshop of the Cross-Language Evaluation Forum for European Languages, 58-65, 2008 | 77 | 2008 |
| ClueWeb22: 10 billion web documents with rich information A Overwijk, C Xiong, J Callan Proceedings of the 45th international ACM SIGIR conference on research and …, 2022 | 71 | 2022 |
| Keyphrase extraction beyond language modeling L Xiong, C Hu, A OVERWIJK, J Ahmed, DF CAMPOS, C XIONG US Patent 11,250,214, 2022 | 37 | 2022 |
| Informedia@ trecvid 2011 L Bao, SI Yu, Z Lan, A Overwijk, Q Jin, B Langner, M Garbus, S Burger, ... Carnegie Mellon University, 2011 | 37 | 2011 |
| Clueweb22: 10 billion web documents with visual and semantic information A Overwijk, C Xiong, X Liu, C VandenBerg, J Callan arXiv preprint arXiv:2211.15848, 2022 | 26 | 2022 |
| Informedia@ trecvid 2010 H Li, L Bao, A Overwijk, W Liu, LF Zhang, SI Yu, MY Chen, F Metze, ... Carnegie Mellon University, 2010 | 20 | 2010 |
| Less is more: Pre-training a strong siamese encoder using a weak decoder S Lu, C Xiong, GK Di He, W Malik, Z Dou, P Bennett, T Liu, A Overwijk arXiv preprint arXiv:2102.09206, 2021 | 18 | 2021 |
| Generating a graph data structure that identifies relationships among topics expressed in web documents LI Ziliu, J Ahmed, A OVERWIJK, L Xiong, X Liu US Patent 11,361,028, 2022 | 13 | 2022 |
| Augmenting Zero-Shot Dense Retrievers with Plug-in Mixture-of-Memories S Ge, C Xiong, C Rosset, A Overwijk, J Han, P Bennett arXiv preprint arXiv:2302.03754, 2023 | 12 | 2023 |
| Multi-layer document structural info extraction framework LI Ziliu, CT Milos, J Ahmed, A OVERWIJK, C Lu, T KwokFung, M Hurst US Patent App. 16/542,845, 2021 | 12 | 2021 |
| Performing targeted searching based on a user profile J Ahmed, W MALIK, A OVERWIJK US Patent 11,921,728, 2024 | 9 | 2024 |
| Reduce catastrophic forgetting of dense retrieval training with teleportation negatives S Sun, C Xiong, Y Yu, A Overwijk, Z Liu, J Bao arXiv preprint arXiv:2210.17167, 2022 | 8 | 2022 |
| A local search algorithm for branchwidth A Overwijk, E Penninkx, HL Bodlaender International Conference on Current Trends in Theory and Practice of …, 2011 | 8 | 2011 |
| Scalable and Resource-Efficient Extraction of Data from Network-Accessible Documents LI Ziliu, J Ahmed, A OVERWIJK US Patent App. 16/713,515, 2021 | 7 | 2021 |
| Improving multitask retrieval by promoting task specialization W Zhang, C Xiong, K Stratos, A Overwijk Transactions of the Association for Computational Linguistics 11, 1201-1212, 2023 | 6 | 2023 |
| Data-efficient pretraining with group-level data influence modeling Z Yu, F Peng, J Lei, A Overwijk, W Yih, C Xiong arXiv preprint arXiv:2502.14709, 2025 | 5 | 2025 |
