| Self-Improving LLMs through Consistency-Based Self-Generated Demonstrations R Sun, X Wan, H Dai, SO Arik, T Pfister US Patent App. 18/128,450, 2024 | | 2024 |
| Matryoshka-Adaptor: Unsupervised and Supervised Tuning for Smaller Embedding Dimensions J Yoon, R Sinha, SO Arik, T Pfister arXiv preprint arXiv:2407.20243, 2024 | | 2024 |
| Distance-based learning confidence model SO Arik, C Xing, Z Zhang, TJ Pfister US Patent 12,039,443, 2024 | | 2024 |
| Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting Z Wang, Z Wang, L Le, HS Zheng, S Mishra, V Perot, Y Zhang, ... arXiv preprint arXiv:2407.08223, 2024 | | 2024 |
| Interpretable tabular data learning using sequential sparse attention SO Arik, TJ Pfister US Patent 12,026,614, 2024 | | 2024 |
| Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilization CY Hsieh, YS Chuang, CL Li, Z Wang, LT Le, A Kumar, J Glass, A Ratner, ... arXiv preprint arXiv:2406.16008, 2024 | | 2024 |
| CaLM: Contrasting Large and Small Language Models to Verify Grounded Generation I Hsu, Z Wang, LT Le, L Miculicich, N Peng, CY Lee, T Pfister arXiv preprint arXiv:2406.05365, 2024 | | 2024 |
| Generating Synthetic Heterogenous Time-Series Data J Yoon, MJ Mizrahi, NF Ghalaty, TDH Jarvinen, AS Ravi, PR Brune, ... US Patent App. 18/389,010, 2024 | | 2024 |
| Learned Feature Importance Scores for Automated Feature Engineering Y Dong, S Arik, N Yoder, T Pfister arXiv preprint arXiv:2406.04153, 2024 | | 2024 |
| Chain of Agents: Large Language Models Collaborating on Long-Context Tasks Y Zhang, R Sun, Y Chen, T Pfister, R Zhang, SÖ Arik arXiv preprint arXiv:2406.02818, 2024 | 1 | 2024 |
| Effective Large Language Model Adaptation for Improved Grounding and Citation Generation X Ye, R Sun, S Arik, T Pfister Proceedings of the 2024 Conference of the North American Chapter of the …, 2024 | 2 | 2024 |
| Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training M Chen, R Sun, SÖ Arık, T Pfister arXiv preprint arXiv:2406.00222, 2024 | | 2024 |
| Mitigating Object Hallucination via Data Augmented Contrastive Tuning P Sarkar, S Ebrahimi, A Etemad, A Beirami, SÖ Arık, T Pfister arXiv preprint arXiv:2405.18654, 2024 | 1 | 2024 |
| Training image-to-image translation neural networks R Zhang, J Li, TJ Pfister US Patent App. 18/418,197, 2024 | | 2024 |
| Zero-shot form entity query framework Z Zhang, Z Wang, V Perot, J Devlin, CY Lee, G Su, H Zhang, TJ Pfister US Patent App. 18/501,982, 2024 | | 2024 |
| Interpretable Tabular Data Learning Using Sequential Sparse Attention SO Arik, TJ Pfister US Patent App. 18/404,881, 2024 | | 2024 |
| Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learning S Han, J Yoon, SO Arik, T Pfister arXiv preprint arXiv:2404.09491, 2024 | | 2024 |
| CodecLM: Aligning Language Models with Tailored Synthetic Data Z Wang, CL Li, V Perot, LT Le, J Miao, Z Zhang, CY Lee, T Pfister arXiv preprint arXiv:2404.05875, 2024 | 1 | 2024 |
| Attention-based prototypical learning SO Arik, TJ Pfister US Patent 11,941,531, 2024 | | 2024 |
| Self-supervised learning for anomaly detection and localization K Sohn, CL Li, J Yoon, TJ Pfister US Patent 11,941,084, 2024 | 3 | 2024 |
Sercan O. ArikGoogleVerified email at google.com