Suchergebnisse - Springer, Jacob

Understanding Catastrophic Forgetting in Language Models via Implicit Inference von Kotha, Suhas, Springer, Jacob Mitchell, Raghunathan, Aditi

Volltext

Sharpness-Aware Minimization Enhances Feature Quality via Balanced Learning von Springer, Jacob Mitchell, Nagarajan, Vaishnavh, Raghunathan, Aditi

Volltext

Mitigating Bias in RAG: Controlling the Embedder von Kim, Taeyoun, Springer, Jacob, Raghunathan, Aditi, Sap, Maarten

Volltext

Disentangling Geometry, Performance, and Training in Language Models von Kulkarni, Atharva, Springer, Jacob Mitchell, Subramonian, Arjun, Swayamdipta, Swabha

Volltext

Repetition Improves Language Model Embeddings von Springer, Jacob Mitchell, Kotha, Suhas, Fried, Daniel, Neubig, Graham, Raghunathan, Aditi

Volltext

Understanding the Influence of Synthetic Data for Text Embedders von Springer, Jacob Mitchell, Adlakha, Vaibhav, Reddy, Siva, Raghunathan, Aditi, Mosbach, Marius

Volltext

Sharpness-Aware Pretraining Mitigates Catastrophic Forgetting von Watts, Ishaan, Li, Catherine, Goyal, Sachin, Springer, Jacob Mitchell, Raghunathan, Aditi

Volltext

Early Data Exposure Improves Robustness to Subsequent Fine-Tuning von Feng, Lawrence, Ghosal, Gaurav R., Springer, Jacob Mitchell, Zhong, Ziqian, Raghunathan, Aditi

Volltext

Overtrained Language Models Are Harder to Fine-Tune von Springer, Jacob Mitchell, Goyal, Sachin, Wen, Kaiyue, Kumar, Tanishq, Yue, Xiang, Malladi, Sadhika, Neubig, Graham, Raghunathan, Aditi

Volltext

Annotations Mitigate Post-Training Mode Collapse von Springer, Jacob Mitchell, Advani, Madhu, Aichberger, Lukas, Bradley, Arwen, Malach, Eran, Saremi, Omid, Williamson, Sinead, Nakkiran, Preetum, Littwin, Etai, Raghunathan, Aditi

Volltext