Publications
2024
- Transformers Can Do Arithmetic with the Right EmbeddingsIn ICML 2024 Workshop on LLMs and Cognition 2024
- Just How Flexible are Neural Networks in Practice?arXiv preprint arXiv:2406.11463 2024
- Generating Potent Poisons and Backdoors from Scratch with Guided DiffusionIn ICML 2024 Next Generation of AI Safety Workshop 2024
- Universal Guidance for Diffusion ModelsIn The Twelfth International Conference on Learning Representations 2024
2023
- Cold Diffusion: Inverting Arbitrary Image Transforms Without NoiseIn Thirty-seventh Conference on Neural Information Processing Systems 2023
- Transfer Learning with Deep Tabular ModelsIn International Conference on Learning Representations 2023
- Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial QueriesIn International Conference on Learning Representations 2023
- Gradient-based optimization is not necessary for generalization in neural networksIn International Conference on Learning Representations 2023
2022
- End-to-end Algorithm Synthesis with Recurrent Networks: Extrapolation without OverthinkingIn Advances in Neural Information Processing Systems 2022
- Certified Neural Network Watermarks with Randomized SmoothingIn International Conference on Machine Learning 2022
- Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from the Decision Boundary PerspectiveIn Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2022
2021
- Preventing unauthorized use of proprietary data: Poisoning for secure dataset releasearXiv preprint arXiv:2103.02683 2021
- MetaBalance: High-Performance Neural Networks for Class-Imbalanced DataarXiv preprint arXiv:2106.09643 2021
2019
- Pag-net: Progressive attention guided depth super-resolution networkarXiv preprint arXiv:1911.09878 2019