Micah Goldblum

LiveBench: A Challenging, Contamination-Limited LLM Benchmark ICLR 2025 Adaptive Retention & Correction: Test-Time Training for Continual Learning ICLR 2025 Hidden No More: Attacking and Defending Private Third-Party LLM Inference ICML 2025 Style Outweighs Substance: Failure Modes of LLM Judges in Alignment Benchmarking ICLR 2025 LLM-Generated Passphrases That Are Secure and Easy to Remember NAACL 2025 Large Language Models Must Be Taught to Know What They Don’t Know NIPS 2024 Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text ICML 2024 Non-Vacuous Generalization Bounds for Large Language Models ICML 2024 Calibration-Tuning: Teaching Large Language Models to Know What They Don’t Know EACL 2024 Investigating Style Similarity in Diffusion Models ECCV 2024 Position: The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning ICML 2024 Compute Better Spent: Replacing Dense Layers with Structured Matrices ICML 2024 Universal Guidance for Diffusion Models ICLR 2024 NEFTune: Noisy Embeddings Improve Instruction Finetuning ICLR 2024 On the Reliability of Watermarks for Large Language Models ICLR 2024 Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices NIPS 2024 Unlocking Tokens as Data Points for Generalization Bounds on Larger Language Models NIPS 2024 TuneTables: Context Optimization for Scalable Prior-Data Fitted Networks NIPS 2024 Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks NIPS 2023 Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models ICLR 2023 How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularization ICLR 2023 Panning for Gold in Federated Learning: Targeted Text Extraction under Arbitrarily Large-Scale Aggregation ICLR 2023 Transfer Learning with Deep Tabular Models ICLR 2023 Exploring and Exploiting Decision Boundary Dynamics for Adversarial Robustness ICLR 2023 The Lie Derivative for Measuring Learned Equivariance ICLR 2023 Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries ICLR 2023 Loss Landscapes are All You Need: Neural Network Generalization Can Be Explained Without the Implicit Bias of Gradient Descent ICLR 2023 Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise NIPS 2023 A Performance-Driven Benchmark for Feature Selection in Tabular Deep Learning NIPS 2023 Understanding and Mitigating Copying in Diffusion Models NIPS 2023 Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery NIPS 2023 Rethinking Bias Mitigation: Fairer Architectures Make for Fairer Face Recognition NIPS 2023 What Can We Learn from Unlearnable Datasets? NIPS 2023 When Do Neural Nets Outperform Boosted Trees on Tabular Data? NIPS 2023 Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models CVPR 2023 Simplifying Neural Network Training Under Class Imbalance NIPS 2023 Chroma-VAE: Mitigating Shortcut Learning with Generative Classifiers NIPS 2022 Where do Models go Wrong? Parameter-Space Saliency Maps for Explainability NIPS 2022 Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch NIPS 2022 End-to-end Algorithm Synthesis with Recurrent Networks: Extrapolation without Overthinking NIPS 2022 Autoregressive Perturbations for Data Poisoning NIPS 2022 Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors NIPS 2022 PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization NIPS 2022 Towards Transferable Adversarial Attacks on Vision Transformers AAAI 2022 Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent From the Decision Boundary Perspective CVPR 2022 Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Models ICLR 2022 Stochastic Training is Not Necessary for Generalization ICLR 2022 The Close Relationship Between Contrastive Learning and Meta-Learning ICLR 2022 The Uncanny Similarity of Recurrence and Depth ICLR 2022 Plug-In Inversion: Model-Agnostic Inversion for Vision with Data Augmentations ICML 2022 Bayesian Model Selection, the Marginal Likelihood, and Generalization ICML 2022 Fishing for User Data in Large-Batch Federated Learning via Gradient Magnification ICML 2022 Encoding Robustness to Image Style via Adversarial Feature Perturbations NIPS 2021 The Intrinsic Dimension of Images and Its Impact on Learning ICLR 2021 LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognition ICLR 2021 Data Augmentation for Meta-Learning ICML 2021 Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks NIPS 2021 Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attacks ICML 2021 Adversarial Examples Make Strong Poisons NIPS 2021 Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Tasks ICML 2020 Truth or backpropaganda? An empirical investigation of deep learning theory ICLR 2020 Adversarially Robust Distillation AAAI 2020 Adversarially Robust Few-Shot Learning: A Meta-Learning Approach NIPS 2020