Ananya Kumar

发表论文 38 篇 · 总被引 11533 次 · h-index 20

代表论文

• On the Opportunities and Risks of Foundation Models (2021 · arXiv.org · 被引 7372)
• Holistic Evaluation of Language Models (2023 · Trans. Mach. Learn. Res. · 被引 2079)
• Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution (2022 · International Conference on Learning Representations · 被引 1022)
• Surgical Fine-Tuning Improves Adaptation to Distribution Shifts (2022 · International Conference on Learning Representations · 被引 308)
• Finetune like you pretrain: Improved finetuning of zero-shot vision models (2022 · Computer Vision and Pattern Recognition · 被引 218)
• Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization? (2022 · Neural Information Processing Systems · 被引 168)