Hair-Trigger Alignment: Black-Box Evaluation Cannot Guarantee Post-Update Alignment
ICML 2026
Publications
60 papers. * denotes equal contribution. See Google Scholar for the latest.
2026
EPSVEC: Efficient and Private Synthetic Data Generation via Dataset Vectors
ICML 2026
Beyond the Trade-off: Unifying Fairness and Performance in Federated Learning
ICML 2026
Psychological Steering in LLMs: An Evaluation of Effectiveness and Trustworthiness
ACL 2026
OpaqueToolsBench: Learning Nuances of Tool Behavior Through Interaction
CAIS 2026
f-INE: A Hypothesis Testing Framework for Estimating Influence under Training Randomness
ICLR 2026
Beyond URLs: Metadata Diversity and Position for Efficient LLM Pretraining
ICLR 2026
Uncertainty as Feature Gaps: Epistemic Uncertainty Quantification of LLMs in Contextual Question-Answering
ICLR 2026
Online Learning in a Creator Economy
Artificial Intelligence Science and Engineering 2026
VoxGuard: Evaluating User and Attribute Privacy in Speech via Membership Inference Attacks
ICASSP 2026
Sparks of Rationality: Do Reasoning LLMs Align with Human Judgment and Choice?
arXiv 2026
2025
A Systematic Analysis of Base Model Choice for Reward Modeling
EMNLP Main 2025
The Surprising Effectiveness of Membership Inference with Simple N-Gram Coverage
COLM 2025
TruthTorchLM: A Comprehensive Library for Predicting Truthfulness in LLM Outputs
EMNLP Demo 2025
Reconsidering LLM Uncertainty Estimation Methods in the Wild
ACL Main 2025
Communication-Efficient Heterogeneous Federated Learning with Generalized Heavy-Ball Momentum
TMLR 2025
ContextLeak: Auditing Leakage in Private In-Context Learning Methods
ICML 2025 Workshop MemFM
LIA: Privacy-Preserving Data Quality Evaluation in Federated Learning Using a Lazy Influence Approximation
IEEE International Conference on Big Data 2025
The Price is Right? Making Data Valuations Incentive-Compatible
ICLR Workshop on Data Problems 2025
2024
DAVED: Data Acquisition via Experimental Design for Decentralized Data Markets
NeurIPS 2024
Conformal Prediction Adaptive to Unknown Subpopulation Shifts
NeurIPS SFLFM Workshop 2024
Defection-Free Collaboration between Competitors in a Learning System
NeurIPS FL@FM Workshop 2024
My-This-Your-That - Interpretable Identification of Systematic Bias in Federated Learning for Biomedical Images
NPJ Digital Medicine 2024
Collaborative Heterogeneous Causal Inference Beyond Meta-analysis
ICML 2024
Privacy Can Arise Endogenously in an Economic System with Learning Agents
FORC 2024
Optimization with Access to Auxiliary Information
TMLR 2024🏆 Invited for ICLR 2025 Oral
2023
Provably Personalized and Robust Federated Learning
TMLR 2023
Federated Conformal Predictors for Distributed Uncertainty Quantification
ICML 2023
Evaluating and Incentivizing Diverse Data Contributions in Collaborative Learning
ICML FL@FM Workshop 2023
Federated Learning Showdown: The Comparative Analysis of Federated Learning Frameworks
FMEC 2023
Agree to Disagree: Diversity through Disagreement for Better Transferability
ICLR 2023🏆 Notable Top 5%
2022
Mechanisms that Incentivize Data Sharing in Federated Learning
Arxiv 2022🏆 Best paper
Towards Provably Personalized Federated Learning via Threshold-Clustering of Similar Clients
FL NeurIPS workshop 2022
Byzantine-Robust Decentralized Learning via Self-Centered Clipping
FL NeurIPS workshop 2022
FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings
NeurIPS 2022
TCT: Convexifying Federated Learning using Bootstrapped Neural Tangent Kernels
NeurIPS 2022
Towards Model Agnostic Federated Learning using Knowledge Distillation
ICLR 2022
Byzantine-Robust Learning on Heterogeneous Datasets via Bucketing
ICLR 2022🏆 Spotlight
2021
A Field Guide to Federated Optimization
Arxiv
Mime: Mimicking Centralized Stochastic Algorithms in Federated Learning
NeurIPS 2021
RelaySum for Decentralized Deep Learning on Heterogeneous Data
NeurIPS 2021
Optimal Model Averaging: Towards Personalized Collaborative Learning
FL ICML workshop 2021🏆 Best paper
Learning from History for Byzantine Robust Optimization
ICML 2021🏆 Spotlight
Quasi-Global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data
ICML 2021
2020
Why Adaptive methods beat SGD for Attention Models
NeurIPS 2020
PowerGossip: Practical Communication Compression in Decentralized Deep Learning
NeurIPS 2020
Weight Erosion: An Update Aggregation Scheme for Personalized Collaborative Machine Learning
DART 2020
Secure Byzantine Machine Learning
SPICY-FL NeurIPS workshop 2020
Accelerated Gradient Boosted Machines
AISTATS 2020
The Error-Feedback Framework: Better Rates for SGD with Delayed Gradients and Compressed Communication
JMLR 2020
SCAFFOLD: Stochastic Controlled Averaging for Federated Learning
ICML 2020
2019
PowerSGD: Practical Low-rank Gradient Compression for Distributed Optimization
NeurIPS 2019
Global Convergence of Newton-type Methods without Strong-Convexity or Lipschitz Gradients
NeurIps OptML 2019
Efficient greedy coordinate descent for composite problems
AISTATS 2019
Error Feedback fixes SignSGD and other Gradient Compression Schemes
ICML 2019🏆 Long talk
2018
On Matching Pursuit and Coordinate Descent
ICML 2018
Adaptive Balancing of Gradient and Update Computation Times using Approximate Subproblem Solvers
AISTATS 2018🏆 Oral
2016
Assignment Techniques for Crowdsourcing Sensitive Tasks
CSCW 2016
Multi-Broadcasting under SINR Model
PODC 2016
Some results on a class of van der Waerden Numbers
Rocky Journal of Mathematics Vol. 48
No papers match that filter.