Kumar, Ananya
- On the Opportunities and Risks of Foundation Models
2021/08/16 by Rishi Bommasani, Drew A. Hudson, Bommasani, Rishi +233 · 11 voices · 538 citations
Computer Science · #Domain Adaptation and Few-Shot Learning #Adversarial Robustness in Machine Learning #Topic Modeling
- GPT-4o System Card
2024/10/25 by OpenAI, :, A. M. Hurst +503 · 1187 citations
Medicine · #Cardiovascular Function and Risk Factors #Hyperglycemia and glycemic control in critically ill and hospitalized patients
- OpenAI o1 System Card
2024/12/21 by OpenAI, Aaron Jaech, : +347 · 501 citations
Computer Science · #Advanced Computational Techniques and Applications
- Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution
2022/02/21 by Kumar, Ananya, Raghunathan, Aditi, Jones, Robbie +2 · 55 citations
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG)
- Verified Uncertainty Calibration
2019/09/23 by Kumar, Ananya, Liang, Percy, Ma, Tengyu · 28 citations
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
- Surgical Fine-Tuning Improves Adaptation to Distribution Shifts
2022/10/20 by Lee, Yoonho, Chen, Annie S., Tajwar, Fahim +4 · 19 citations
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG)
- Finetune like you pretrain: Improved finetuning of zero-shot vision models
2022/12/01 by Sachin Goyal, Goyal, Sachin, Ananya Kumar +7 · 15 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · #Cancer-related molecular mechanisms research #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Multimodal Machine Learning Applications
- Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization?
2022/11/25 by Rishi Bommasani, Kathleen Creel, Bommasani, Rishi +7 · 11 citations
Social Sciences · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Computer Vision and Pattern Recognition (cs.CV) #Computers and Society (cs.CY) #Ethics and Social Impacts of AI #FOS: Computer and information sciences #Machine Learning (cs.LG)
- Understanding Self-Training for Gradual Domain Adaptation
2020/02/26 by Ananya Kumar, Kumar, Ananya, Tengyu Ma +3 · 6 citations
Computer Science · #Domain Adaptation and Few-Shot Learning #Machine Learning and ELM #Stochastic Gradient Optimization Techniques
- Extending the WILDS Benchmark for Unsupervised Adaptation
2021/12/09 by Sagawa, Shiori, Koh, Pang Wei, Lee, Tony +17 · 6 citations
#Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
- No True State-of-the-Art? OOD Detection Methods are Inconsistent across Datasets
2021/09/12 by Tajwar, Fahim, Kumar, Ananya, Xie, Sang Michael +1 · 4 citations
#FOS: Computer and information sciences #Machine Learning (cs.LG)
- Self-training Avoids Using Spurious Features Under Domain Shift
2020/06/17 by Yining Chen, Colin Wei, Chen, Yining +5 · 3 citations
Computer Science · #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and ELM #Multimodal Machine Learning Applications
- Rigorous Agent Evaluation: An Adversarial Approach to Uncover\n Catastrophic Failures
2018/12/04 by Jonathan Uesato, Ananya Kumar, Uesato, Jonathan +15 · 4 citations
Computer Science · #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #Explainable Artificial Intelligence (XAI)
- Llamas Know What GPTs Don't Show: Surrogate Models for Confidence Estimation
2023/11/15 by Vaishnavi Shrivastava, Percy Liang, Shrivastava, Vaishnavi +3 · 5 citations
Computer Science · Medicine · #Artificial Intelligence in Healthcare and Education #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Topic Modeling
- Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptation
2022/04/01 by Kendrick Shen, R. Jones, Shen, Kendrick +11 · 3 citations
Computer Science · Medicine · #COVID-19 diagnosis using AI #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Multimodal Machine Learning Applications
- Selective Classification Can Magnify Disparities Across Groups
2020/10/27 by Jones, Erik, Sagawa, Shiori, Koh, Pang Wei +2 · 2 citations
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
- Beyond Separability: Analyzing the Linear Transferability of Contrastive Representations to Related Subpopulations
2022/04/06 by HaoChen, Jeff Z., Wei, Colin, Kumar, Ananya +1 · 2 citations
#FOS: Computer and information sciences #Machine Learning (cs.LG)
- Language Models Prefer What They Know: Relative Confidence Estimation via Confidence Preferences
2025/02/03 by Vaishnavi Shrivastava, Shrivastava, Vaishnavi, Ananya Kumar +3 · 5 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Topic Modeling
- Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift
2022/07/18 by Kumar, Ananya, Ma, Tengyu, Liang, Percy +1 · 1 citation
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
- How to Fine-Tune Vision Models with SGD
2022/11/17 by Kumar, Ananya, Shen, Ruoqi, Bubeck, Sebastien +1 · 1 citation
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG)
- Evolving Domain Adaptation of Pretrained Language Models for Text Classification
2023/11/16 by Yun‐Shiuan Chuang, Chuang, Yun-Shiuan, Yi Wu +17 · 1 citation
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Topic Modeling
- In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness
2020/12/08 by Sang Michael Xie, Xie, Sang Michael, Ananya Kumar +9 · 2 citations
Computer Science · #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Data Classification #Multimodal Machine Learning Applications