Tom Goldstein

Efficient Fine-Tuning and Concept Suppression for Pruned Diffusion Models CVPR 2025 ARGUS: Hallucination and Omission Evaluation in Video-LLMs ICCV 2025 Zero-Shot Vision Encoder Grafting via LLM Surrogates ICCV 2025 Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives CVPR 2025 LLM-Generated Passphrases That Are Secure and Easy to Remember NAACL 2025 Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement NAACL 2025 PUP 3D-GS: Principled Uncertainty Pruning for 3D Gaussian Splatting CVPR 2025 LiveBench: A Challenging, Contamination-Limited LLM Benchmark ICLR 2025 Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data? AAAI 2025 InstructZero: Efficient Instruction Optimization for Black-Box Large Language Models ICML 2024 WAVES: Benchmarking the Robustness of Image Watermarks ICML 2024 Object Recognition as Next Token Prediction CVPR 2024 NEFTune: Noisy Embeddings Improve Instruction Finetuning ICLR 2024 Universal Guidance for Diffusion Models ICLR 2024 On the Reliability of Watermarks for Large Language Models ICLR 2024 CALVIN: Improved Contextual Video Captioning via Instruction Tuning NIPS 2024 Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text ICML 2024 ODIN: Disentangled Reward Mitigates Hacking in RLHF ICML 2024 Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs NIPS 2024 Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization NIPS 2024 Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models NIPS 2024 Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models NIPS 2024 Investigating Style Similarity in Diffusion Models ECCV 2024 Transformers Can Do Arithmetic with the Right Embeddings NIPS 2024 Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks NIPS 2023 Panning for Gold in Federated Learning: Targeted Text Extraction under Arbitrarily Large-Scale Aggregation ICLR 2023 How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularization ICLR 2023 Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models ICLR 2023 GOAT: A Global Transformer on Large-scale Graphs ICML 2023 A Watermark for Large Language Models ICML 2023 Provable Robustness against Wasserstein Distribution Shifts via Input Randomization 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 Tree-Rings Watermarks: Invisible Fingerprints for Diffusion Images NIPS 2023 On the Exploitability of Instruction Tuning NIPS 2023 What Can We Learn from Unlearnable Datasets? NIPS 2023 Cramming: Training a Language Model on a single GPU in one day. ICML 2023 Loss Landscapes are All You Need: Neural Network Generalization Can Be Explained Without the Implicit Bias of Gradient Descent ICLR 2023 Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models CVPR 2023 Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries ICLR 2023 Exploring and Exploiting Decision Boundary Dynamics for Adversarial Robustness ICLR 2023 Transfer Learning with Deep Tabular Models ICLR 2023 Autoregressive Perturbations for Data Poisoning NIPS 2022 End-to-end Algorithm Synthesis with Recurrent Networks: Extrapolation without Overthinking NIPS 2022 Learning Revenue-Maximizing Auctions With Differentiable Matching AISTATS 2022 Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch NIPS 2022 Where do Models go Wrong? Parameter-Space Saliency Maps for Explainability NIPS 2022 The Uncanny Similarity of Recurrence and Depth ICLR 2022 Robust Optimization As Data Augmentation for Large-Scale Graphs CVPR 2022 Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent From the Decision Boundary Perspective CVPR 2022 The Close Relationship Between Contrastive Learning and Meta-Learning ICLR 2022 Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models NIPS 2022 Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Models ICLR 2022 Diurnal or Nocturnal? Federated Learning of Multi-branch Networks from Periodically Shifting Distributions ICLR 2022 Stochastic Training is Not Necessary for Generalization ICLR 2022 Fishing for User Data in Large-Batch Federated Learning via Gradient Magnification ICML 2022 Plug-In Inversion: Model-Agnostic Inversion for Vision with Data Augmentations ICML 2022 Does your graph need a confidence boost? Convergent boosted smoothing on graphs with tabular node features ICLR 2022 Towards Transferable Adversarial Attacks on Vision Transformers AAAI 2022 Robustness Disparities in Face Detection NIPS 2022 Certified Neural Network Watermarks with Randomized Smoothing ICML 2022 WrapNet: Neural Net Inference with Ultra-Low-Precision Arithmetic ICLR 2021 Center Smoothing: Certified Robustness for Networks with Structured Outputs NIPS 2021 Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks NIPS 2021 VQ-GNN: A Universal Framework to Scale up Graph Neural Networks using Vector Quantization NIPS 2021 GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training NIPS 2021 Long-Short Transformer: Efficient Transformers for Language and Vision NIPS 2021 Gradient-Free Adversarial Training Against Image Corruption for Learning-based Steering NIPS 2021 Encoding Robustness to Image Style via Adversarial Feature Perturbations NIPS 2021 Adversarial Examples Make Strong Poisons NIPS 2021 Are Adversarial Examples Created Equal? A Learnable Weighted Minimax Risk for Robustness under Non-uniform Attacks AAAI 2021 Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching ICLR 2021 LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognition ICLR 2021 The Intrinsic Dimension of Images and Its Impact on Learning ICLR 2021 Data Augmentation for Meta-Learning ICML 2021 Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attacks ICML 2021 Network Deconvolution ICLR 2020 FreeLB: Enhanced Adversarial Training for Natural Language Understanding ICLR 2020 Certified Defenses for Adversarial Patches ICLR 2020 Truth or backpropaganda? An empirical investigation of deep learning theory ICLR 2020 BREAKING CERTIFIED DEFENSES: SEMANTIC ADVERSARIAL EXAMPLES WITH SPOOFED ROBUSTNESS CERTIFICATES ICLR 2020 Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectors ECCV 2020 Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Tasks ICML 2020 Certified Data Removal from Machine Learning Models ICML 2020 Curse of Dimensionality on Randomized Smoothing for Certifiable Robustness ICML 2020 Adversarial Attacks on Copyright Detection Systems ICML 2020 The Impact of Neural Network Overparameterization on Gradient Confusion and Stochastic Gradient Descent ICML 2020 Universal Adversarial Training AAAI 2020 Adversarially Robust Distillation AAAI 2020 Adversarially Robust Few-Shot Learning: A Meta-Learning Approach NIPS 2020 MetaPoison: Practical General-purpose Clean-label Data Poisoning NIPS 2020 Certifying Confidence via Randomized Smoothing NIPS 2020 Certifying Strategyproof Auction Networks NIPS 2020 Detection as Regression: Certified Object Detection with Median Smoothing NIPS 2020 Adversarially robust transfer learning ICLR 2020 Adversarial training for free! NIPS 2019 Transferable Clean-Label Poisoning Attacks on Deep Neural Nets ICML 2019 ACE: Adapting to Changing Environments for Semantic Segmentation ICCV 2019 Are adversarial examples inevitable? ICLR 2019 Linear Spectral Estimators and an Application to Phase Retrieval ICML 2018 Visualizing the Loss Landscape of Neural Nets NIPS 2018 Stabilizing Adversarial Nets with Prediction Methods ICLR 2018 Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks NIPS 2018 DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptation ECCV 2018 Training Quantized Nets: A Deeper Understanding NIPS 2017 Convex Phase Retrieval without Lifting via PhaseMax ICML 2017 Adaptive Consensus ADMM for Distributed Optimization ICML 2017 Adaptive Relaxed ADMM: Convergence Theory and Practical Implementation CVPR 2017 A New Rank Constraint on Multi-View Fundamental Matrices, and Its Application to Camera Location Recovery CVPR 2017 Automated Inference with Adaptive Batches AISTATS 2017 Adaptive ADMM with Spectral Penalty Parameter Selection AISTATS 2017 Training Neural Networks Without Gradients: A Scalable ADMM Approach ICML 2016 Dealbreaker: A Nonlinear Latent Variable Model for Educational Data ICML 2016 Estimating Sparse Signals With Smooth Support via Convex Programming and Block Sparsity CVPR 2016 Unwrapping ADMM: Efficient Distributed Computing via Transpose Reduction AISTATS 2016 Adaptive Primal-Dual Splitting Methods for Statistical Learning and Image Processing NIPS 2015