44 citations · 218 across the 42 of their papers we have counts for
48 papers
Can Agents Design Libraries for Agents?
Gabriel Orlanski, Alex L. Zhang, Avi Trost +4
Agents increasingly build on code written by other agents, and they reimplement rather than reuse, growing the codebases later agents must work in. To measure how well agents desig…
U-Define: Designing User Workflows for Hard and Soft Constraints in LLM-Based Planning
Christine P Lee, Xinyu Jessica Wang, Aws Albarghouthi +2
LLMs are increasingly used for end-user task planning, yet their black-box nature limits users' ability to ensure reliability and control. While recent systems incorporate verifica…
Linear-Time T-Gate Optimization via Random Abstraction
Aws Albarghouthi
Quantum computers promise exponential speedups for problems in cryptography, chemistry, and optimization. Realizing this promise requires fault tolerance: physical qubits are noisy…
Test-Time Scaling Makes Overtraining Compute-Optimal
Nicholas Roberts, Sungjun Cho, Zhiqi Gao +7
Modern LLMs scale at test-time, e.g. via repeated sampling, where inference cost grows with model size and the number of samples. This creates a trade-off that pretraining scaling…
Analyzing Decoders for Quantum Error Correction
Abtin Molavi, Feras Saad, Aws Albarghouthi
Quantum error correction (QEC) enables reliable computation on noisy hardware by encoding logical information across many physical qubits and periodically measuring parities to det…
SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks
Gabriel Orlanski, Devjeet Roy, Alexander Yun +7
Software development is iterative, yet agentic coding benchmarks hide design issues through their single-shot setup. Recent iterative benchmarks attempt to remedy this but heavily…
SkillOrchestra: Learning to Route Agents via Skill Transfer
Jiayu Wang, Yifei Ming, Zixuan Ke +3
Compound AI systems promise capabilities beyond those of individual models, yet their success depends critically on effective orchestration. Existing routing approaches face two li…
LiveResearchBench: A Live Benchmark for User-Centric Deep Research in the Wild
Jiayu Wang, Yifei Ming, Riya Dulepet +7
Deep research -- producing comprehensive, citation-grounded reports by searching and synthesizing information from hundreds of live web sources -- marks an important frontier for a…
Generating Compilers for Qubit Mapping and Routing
Abtin Molavi, Amanda Xu, Ethan Cecchetti +2
To evaluate a quantum circuit on a quantum processor, one must find a mapping from circuit qubits to processor qubits and plan the instruction execution while satisfying the proces…
Pareto Optimal Code Generation
Gabriel Orlanski, Nicholas Roberts, Aws Albarghouthi +1
Generate-then-rank is the dominant test-time scaling (TTS) paradigm for code generation, but scaling accuracy by sampling and executing more candidates makes comprehensive verifica…
Beyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement Learning
Jiayu Wang, Yifei Ming, Zixuan Ke +4
Reinforcement learning (RL) has become the dominant paradigm for improving the performance of language models on complex reasoning tasks. Despite the substantial empirical gains de…
COSMOS: Predictable and Cost-Effective Adaptation of LLMs
Jiayu Wang, Aws Albarghouthi, Frederic Sala
Large language models (LLMs) achieve remarkable performance across numerous tasks by using a diverse array of adaptation strategies. However, optimally selecting a model and adapta…
Verified Foundations for Differential Privacy
Markus de Medeiros, Muhammad Naveed, Tancrède Lepoint +7
Differential privacy (DP) has become the gold standard for privacy-preserving data analysis, but implementing it correctly has proven challenging. Prior work has focused on verifyi…
Optimizing Quantum Circuits, Fast and Slow
Amanda Xu, Abtin Molavi, Swamit Tannu +1
Optimizing quantum circuits is critical: the number of quantum operations needs to be minimized for a successful evaluation of a circuit on a quantum processor. In this paper we un…
Perceptions of the Fairness Impacts of Multiplicity in Machine Learning
Anna P. Meyer, Yea-Seul Kim, Aws Albarghouthi +1
Machine learning (ML) is increasingly used in high-stakes settings, yet multiplicity - the existence of multiple good models - means that some predictions are essentially arbitrary…
Managing Classical Processing Requirements for Quantum Error Correction
Satvik Maurya, Abtin Molavi, Aws Albarghouthi +1
Large-scale quantum computers promise transformative speedups, but their viability hinges on fast and reliable quantum error correction (QEC). At the center of QEC are decoders-cla…
A One-Layer Decoder-Only Transformer is a Two-Layer RNN: With an Application to Certified Robustness
Yuhao Zhang, Aws Albarghouthi, Loris D'Antoni
This paper reveals a key insight that a one-layer decoder-only Transformer is equivalent to a two-layer Recurrent Neural Network (RNN). Building on this insight, we propose ARC-Tra…
Crowdsourcing Task Traces for Service Robotics
David Porfirio, Allison Sauppé, Maya Cakmak +2
Demonstration is an effective end-user development paradigm for teaching robots how to perform new tasks. In this paper, we posit that demonstration is useful not only as a teachin…
Verified Training for Counterfactual Explanation Robustness under Data Shift
Anna P. Meyer, Yuhao Zhang, Aws Albarghouthi +1
Counterfactual explanations (CEs) enhance the interpretability of machine learning models by describing what changes to an input are necessary to change its prediction to a desired…
Dependency-Aware Compilation for Surface Code Quantum Architectures
Abtin Molavi, Amanda Xu, Swamit Tannu +1
Practical applications of quantum computing depend on fault-tolerant devices with error correction. Today, the most promising approach is a class of error-correcting codes called s…
The Dataset Multiplicity Problem: How Unreliable Data Impacts Predictions
Anna P. Meyer, Aws Albarghouthi, Loris D'Antoni
We introduce dataset multiplicity, a way to study how inaccuracies, uncertainty, and social bias in training datasets impact test-time predictions. The dataset multiplicity framewo…
Sketching Robot Programs On the Fly
David Porfirio, Laura Stegner, Maya Cakmak +3
Service robots for personal use in the home and the workplace require end-user development solutions for swiftly scripting robot tasks as the need arises. Many existing solutions p…
PECAN: A Deterministic Certified Defense Against Backdoor Attacks
Yuhao Zhang, Aws Albarghouthi, Loris D'Antoni
Neural networks are vulnerable to backdoor poisoning attacks, where the attackers maliciously poison the training set and insert triggers into the test input to change the predicti…
Synthesizing Quantum-Circuit Optimizers
Amanda Xu, Abtin Molavi, Lauren Pick +2
Near-term quantum computers are expected to work in an environment where each operation is noisy, with no error correction. Therefore, quantum-circuit optimizers are applied to min…