Title |
|---|
 Convergence of flow-based generative models via proximal gradient
descent in Wasserstein spaceIEEE Transactions on Information Theory (IEEE Trans. Inf. Theory), 2023 |
 Transformer Fusion with Optimal TransportInternational Conference on Learning Representations (ICLR), 2023 |
 FlashAttention-2: Faster Attention with Better Parallelism and Work
PartitioningInternational Conference on Learning Representations (ICLR), 2023 |
 A Brief Review of Hypernetworks in Deep LearningArtificial Intelligence Review (AIR), 2023 |
 Flow Matching for Generative ModelingInternational Conference on Learning Representations (ICLR), 2022 |
 GeONet: a neural operator for learning the Wasserstein geodesicConference on Uncertainty in Artificial Intelligence (UAI), 2022 |
 Flow Straight and Fast: Learning to Generate and Transfer Data with
Rectified FlowInternational Conference on Learning Representations (ICLR), 2022 |
 Supervised Training of Conditional Monge MapsNeural Information Processing Systems (NeurIPS), 2022 |
 Meta Optimal TransportInternational Conference on Machine Learning (ICML), 2022 |
 FlashAttention: Fast and Memory-Efficient Exact Attention with
IO-AwarenessNeural Information Processing Systems (NeurIPS), 2022 |
 Skyformer: Remodel Self-Attention with Gaussian Kernel and Nyström
MethodNeural Information Processing Systems (NeurIPS), 2021 |
 Do Neural Optimal Transport Solvers Work? A Continuous Wasserstein-2
BenchmarkNeural Information Processing Systems (NeurIPS), 2021 |
 Prefix-Tuning: Optimizing Continuous Prompts for GenerationAnnual Meeting of the Association for Computational Linguistics (ACL), 2021 Xiang Lisa Li Abigail Z. Jacobs |
 Distances between probability distributions of different dimensionsIEEE Transactions on Information Theory (IEEE Trans. Inf. Theory), 2020 |
 Decision-Making with Auto-Encoding Variational BayesNeural Information Processing Systems (NeurIPS), 2020 Romain Lopez Pierre Boyeau Nir Yosef Michael I. Jordan Jeffrey Regier |
 Unsupervised Multilingual Alignment using Wasserstein BarycenterInternational Joint Conference on Artificial Intelligence (IJCAI), 2020 |
 Are Transformers universal approximators of sequence-to-sequence
functions?International Conference on Learning Representations (ICLR), 2019 |
 Model Fusion via Optimal TransportNeural Information Processing Systems (NeurIPS), 2019 |
 Wasserstein-2 Generative NetworksInternational Conference on Learning Representations (ICLR), 2019 |
 Optimal transport mapping via input convex neural networksInternational Conference on Machine Learning (ICML), 2019 |
 Style Transfer by Relaxed Optimal Transport and Self-SimilarityComputer Vision and Pattern Recognition (CVPR), 2019 |
 Parameter-Efficient Transfer Learning for NLPInternational Conference on Machine Learning (ICML), 2019 |
 Improving GANs Using Optimal TransportInternational Conference on Learning Representations (ICLR), 2018 |
 Attention Is All You NeedNeural Information Processing Systems (NeurIPS), 2017 |
 |
 |
