Ameet Talwalkar

EditBench: Evaluating LLM Abilities to Perform Real-World Instructed Code Edits

FrontierCO: Real-World and Large-Scale Evaluation of Machine Learning Solvers for Combinatorial Optimization

CoMind: Towards Community-Driven Agents for Machine Learning Engineering

How can we assess human-agent interactions? Case studies in software agent design

Sample Complexity and Representation Ability of Test-time Scaling Paradigms

RECODE: Reasoning Through Code Generation for Visual Question Answering

Pre-Generating Multi-Difficulty PDE Data For Few-Shot Neural PDE Solvers

CodePDE: An Inference Framework for LLM-driven PDE Solver Generation

This Time is Different: An Observability Perspective on Time Series Foundation Models

Understanding Optimization in Deep Learning with Central Flows

Specialized Foundation Models Struggle to Beat Supervised Baselines

Thinking vs. Doing: Improving Agent Reasoning by Scaling Test-Time Interaction

Copilot Arena: A Platform for Code LLM Evaluation in the Wild

The Impact of Element Ordering on LM Agent Performance

Towards Specialized Web Agents Using Production-Scale Workflow Data