Picture for Ameet Talwalkar

Ameet Talwalkar

UC Berkeley

ScribeAgent: Towards Specialized Web Agents Using Production-Scale Workflow Data

Add code
Nov 22, 2024
Viaarxiv icon

Specialized Foundation Models Struggle to Beat Supervised Baselines

Add code
Nov 05, 2024
Viaarxiv icon

Understanding Optimization in Deep Learning with Central Flows

Add code
Oct 31, 2024
Viaarxiv icon

The Impact of Element Ordering on LM Agent Performance

Add code
Sep 19, 2024
Figure 1 for The Impact of Element Ordering on LM Agent Performance
Figure 2 for The Impact of Element Ordering on LM Agent Performance
Figure 3 for The Impact of Element Ordering on LM Agent Performance
Figure 4 for The Impact of Element Ordering on LM Agent Performance
Viaarxiv icon

Revisiting Cascaded Ensembles for Efficient Inference

Add code
Jul 02, 2024
Figure 1 for Revisiting Cascaded Ensembles for Efficient Inference
Figure 2 for Revisiting Cascaded Ensembles for Efficient Inference
Figure 3 for Revisiting Cascaded Ensembles for Efficient Inference
Figure 4 for Revisiting Cascaded Ensembles for Efficient Inference
Viaarxiv icon

The RealHumanEval: Evaluating Large Language Models' Abilities to Support Programmers

Add code
Apr 03, 2024
Viaarxiv icon

UPS: Towards Foundation Models for PDE Solving via Cross-Modal Adaptation

Add code
Mar 11, 2024
Viaarxiv icon

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

Add code
Feb 09, 2024
Viaarxiv icon

Multitask Learning Can Improve Worst-Group Outcomes

Add code
Dec 05, 2023
Viaarxiv icon

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

Add code
Nov 07, 2023
Viaarxiv icon