Edward Raff

Bayesian Meta-Analyses Could Be More: A Case Study in Trial of Labor After a Cesarean-section Outcomes and Complications AAAI 2026 Intermediate N-Gramming: Deterministic and Fast N-Grams for Large N and Large Datasets AAAI 2026 Can LLMs Obfuscate Code? A Systematic Analysis of Large Language Models into Assembly Code Obfuscation AAAI 2025 Do LLMs Adhere to Label Definitions? Examining Their Receptivity to External Label Definitions EMNLP 2025 Stop Walking in Circles! Bailing Out Early in Projected Gradient Descent CVPR 2025 What Do Machine Learning Researchers Mean by “Reproducible”? AAAI 2025 Assemblage: Automatic Binary Dataset Construction for Machine Learning NeurIPS 2024 A Walsh Hadamard Derived Linear Vector Symbolic Architecture NeurIPS 2024 Holographic Global Convolutional Networks for Long-Range Prediction Tasks in Malware Detection AISTATS 2024 Is Function Similarity Over-Engineered? Building a Benchmark NeurIPS 2024 Stabilizing Linear Passive-Aggressive Online Learning with Weighted Reservoir Sampling NeurIPS 2024 WellDunn: On the Robustness and Explainability of Language Models and Large Language Models in Identifying Wellness Dimensions EMNLP 2024 A Coreset Learning Reality Check AAAI 2023 BLOOM+1: Adding Language Support to BLOOM for Zero-Shot Prompting ACL 2023 Crosslingual Generalization through Multitask Finetuning ACL 2023 Emergent and Predictable Memorization in Large Language Models NeurIPS 2023 LEACE: Perfect linear concept erasure in closed form NeurIPS 2023 Neural Bregman Divergences for Distance Learning ICLR 2023 Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling ICML 2023 Recasting Self-Attention with Holographic Reduced Representations ICML 2023 Reproducibility in Multiple Instance Learning: A Case For Algorithmic Unit Tests NeurIPS 2023 Scaling Up Differentially Private LASSO Regularized Logistic Regression via Faster Frank-Wolfe Iterations NeurIPS 2023 A General Framework for Auditing Differentially Private Machine Learning NeurIPS 2022 Bridging the Gap: Using Deep Acoustic Representations to Learn Grounded Language from Percepts and Raw Speech AAAI 2022 Deploying Convolutional Networks on Untrusted Platforms Using 2D Holographic Reduced Representations ICML 2022 Out of Distribution Data Detection Using Dropout Bayesian Neural Networks AAAI 2022 VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance ECCV 2022 Bringing UMAP Closer to the Speed of Light with GPU Acceleration AAAI 2021 Classifying Sequences of Extreme Length with Constant Memory Applied to Malware Detection AAAI 2021 Exact Acceleration of K-Means++ and K-Means|| IJCAI 2021 Learning with Holographic Reduced Representations NeurIPS 2021 Research Reproducibility as a Survival Analysis AAAI 2021 A New Burrows Wheeler Transform Markov Distance AAAI 2020 Robust Design of Deep Neural Networks Against Adversarial Attacks Based on Lyapunov Theory CVPR 2020 A Step Toward Quantifying Independently Reproducible Machine Learning Research NeurIPS 2019 Barrage of Random Transforms for Adversarially Robust Defense CVPR 2019 JSAT: Java Statistical Analysis Tool, a Library for Machine Learning JMLR 2017