Alert button
Picture for Ameet Talwalkar

Ameet Talwalkar

Alert button

Everybody Prune Now: Structured Pruning of LLMs with only Forward Passes

Feb 09, 2024
Lucio Dery, Steven Kolawole, Jean-François Kagy, Virginia Smith, Graham Neubig, Ameet Talwalkar

Viaarxiv icon

Multitask Learning Can Improve Worst-Group Outcomes

Dec 05, 2023
Atharva Kulkarni, Lucio Dery, Amrith Setlur, Aditi Raghunathan, Ameet Talwalkar, Graham Neubig

Viaarxiv icon

Do LLMs exhibit human-like response biases? A case study in survey design

Nov 07, 2023
Lindia Tjuatja, Valerie Chen, Sherry Tongshuang Wu, Ameet Talwalkar, Graham Neubig

Viaarxiv icon

Learning to Relax: Setting Solver Parameters Across a Sequence of Linear System Instances

Oct 03, 2023
Mikhail Khodak, Edmond Chow, Maria-Florina Balcan, Ameet Talwalkar

Figure 1 for Learning to Relax: Setting Solver Parameters Across a Sequence of Linear System Instances
Figure 2 for Learning to Relax: Setting Solver Parameters Across a Sequence of Linear System Instances
Figure 3 for Learning to Relax: Setting Solver Parameters Across a Sequence of Linear System Instances
Figure 4 for Learning to Relax: Setting Solver Parameters Across a Sequence of Linear System Instances
Viaarxiv icon

FeedbackLogs: Recording and Incorporating Stakeholder Feedback into Machine Learning Pipelines

Jul 28, 2023
Matthew Barker, Emma Kallina, Dhananjay Ashok, Katherine M. Collins, Ashley Casovan, Adrian Weller, Ameet Talwalkar, Valerie Chen, Umang Bhatt

Figure 1 for FeedbackLogs: Recording and Incorporating Stakeholder Feedback into Machine Learning Pipelines
Figure 2 for FeedbackLogs: Recording and Incorporating Stakeholder Feedback into Machine Learning Pipelines
Figure 3 for FeedbackLogs: Recording and Incorporating Stakeholder Feedback into Machine Learning Pipelines
Figure 4 for FeedbackLogs: Recording and Incorporating Stakeholder Feedback into Machine Learning Pipelines
Viaarxiv icon

Where Does My Model Underperform? A Human Evaluation of Slice Discovery Algorithms

Jun 13, 2023
Nari Johnson, Ángel Alexander Cabrera, Gregory Plumb, Ameet Talwalkar

Figure 1 for Where Does My Model Underperform? A Human Evaluation of Slice Discovery Algorithms
Figure 2 for Where Does My Model Underperform? A Human Evaluation of Slice Discovery Algorithms
Figure 3 for Where Does My Model Underperform? A Human Evaluation of Slice Discovery Algorithms
Figure 4 for Where Does My Model Underperform? A Human Evaluation of Slice Discovery Algorithms
Viaarxiv icon

Learning Personalized Decision Support Policies

Apr 13, 2023
Umang Bhatt, Valerie Chen, Katherine M. Collins, Parameswaran Kamalaruban, Emma Kallina, Adrian Weller, Ameet Talwalkar

Figure 1 for Learning Personalized Decision Support Policies
Figure 2 for Learning Personalized Decision Support Policies
Figure 3 for Learning Personalized Decision Support Policies
Figure 4 for Learning Personalized Decision Support Policies
Viaarxiv icon

Assisting Human Decisions in Document Matching

Feb 16, 2023
Joon Sik Kim, Valerie Chen, Danish Pruthi, Nihar B. Shah, Ameet Talwalkar

Figure 1 for Assisting Human Decisions in Document Matching
Figure 2 for Assisting Human Decisions in Document Matching
Figure 3 for Assisting Human Decisions in Document Matching
Figure 4 for Assisting Human Decisions in Document Matching
Viaarxiv icon

Cross-Modal Fine-Tuning: Align then Refine

Feb 11, 2023
Junhong Shen, Liam Li, Lucio M. Dery, Corey Staten, Mikhail Khodak, Graham Neubig, Ameet Talwalkar

Figure 1 for Cross-Modal Fine-Tuning: Align then Refine
Figure 2 for Cross-Modal Fine-Tuning: Align then Refine
Figure 3 for Cross-Modal Fine-Tuning: Align then Refine
Figure 4 for Cross-Modal Fine-Tuning: Align then Refine
Viaarxiv icon