Towards out-of-distribution generalization in large-scale astronomical surveys: robust networks learn similar representations
Comments Accepted to Machine Learning and the Physical Sciences Workshop, NeurIPS 2023
期刊&会议
NeurIPS
Conference on Neural Information Processing Systems · 会议 · Machine Learning
Echoes in the Noise: Posterior Samples of Faint Galaxy Surface Brightness Profiles with Score-Based Likelihoods and Priors
Comments 5+5 pages, 10 figures, Machine Learning and the Physical Sciences Workshop, NeurIPS 2023
Discovering Galaxy Features via Dataset Distillation
Comments Accepted to NeurIPS Workshop on Machine Learning and the Physical Sciences, 2023
Unrolling Virtual Worlds for Immersive Experiences
Comments Accepted for NeurIPS 2023 Workshop on Machine Learning for Creativity and Design
Making Self-supervised Learning Robust to Spurious Correlation via Learning-speed Aware Sampling
Comments Accepted by NeurIPS 2023 Workshop Self-Supervised Learning - Theory and Practice, 18 pages, 7 figures, 7 tables
Diffusion-TTA: Test-time Adaptation of Discriminative Models via Generative Feedback
Comments Accepted at NeurIPS 2023 Webpage with Code: https://diffusion-tta.github.io/
Towards Responsible Governance of Biological Design Tools
Comments 10 pages + references, 1 figure, accepted at NeurIPS 2023 Workshop on Regulatable ML as oral presentation
Benchmarking Robustness of Text-Image Composed Retrieval
Comments Accepted by R0-FoMo: Workshop on Robustness of Few-shot and Zero-shot Learning in Foundation Models at NeurIPS 2023
Hierarchical Joint Graph Learning and Multivariate Time Series Forecasting
Comments Temporal Graph Learning Workshop @ NeurIPS 2023, New Orleans, United States
Unified Segment-to-Segment Framework for Simultaneous Sequence Generation
Comments Accepted at NeurIPS 2023
On Sparse Modern Hopfield Model
Comments 37 pages, accepted at NeurIPS 2023. [v2] updated to match with camera-ready version. Code is available at https://github.com/MAGICS-LAB/SparseModernHopfield
Focused Transformer: Contrastive Training for Context Scaling
Comments Accepted at 37th Conference on Neural Information Processing Systems (NeurIPS 2023). 28 pages, 10 figures, 11 tables
Fantastic Weights and How to Find Them: Where to Prune in Dynamic Sparse Training
Comments NeurIPS 2023
Operator Learning with Neural Fields: Tackling PDEs on General Geometries
Journal ref 37th Conference on Neural Information Processing Systems (NeurIPS 2023)
Extending Explainable Boosting Machines to Scientific Image Data
Comments 7 pages, 2 figures
Journal ref Proceedings of the Machine Learning and the Physical Sciences Workshop at NeurIPS 2023, New Orleans, LA
Self-Chained Image-Language Model for Video Localization and Question Answering
Comments NeurIPS 2023; Our code and checkpoints are available at: https://github.com/Yui010206/SeViLA
Reduced-order modeling for parameterized PDEs via implicit neural representations
Comments 9 pages, 5 figures, Machine Learning and the Physical Sciences Workshop, NeurIPS 2023
Guarantees for Self-Play in Multiplayer Games via Polymatrix Decomposability
Comments To appear at NeurIPS 2023
CoLA: Exploiting Compositional Structure for Automatic and Efficient Numerical Linear Algebra
Comments Code available at https://github.com/wilson-labs/cola. NeurIPS 2023
Mitigating Source Bias for Fairer Weak Supervision
Comments NeurIPS 2023
LibSignal: An Open Library for Traffic Signal Control
Comments 11 pages + 6 pages appendix. Accepted by Machine Learning Journal (2023). A short version is accepted by NeurIPS 2022 Workshop: Reinforcement Learning for Real Life. Website: https://darl-libsignal.github.io/
D-CIPHER: Discovery of Closed-form Partial Differential Equations
Comments To appear in the Proceedings of the 37th Conference on Neural Information Processing Systems (NeurIPS 2023)
Focus on Query: Adversarial Mining Transformer for Few-Shot Segmentation
Comments Accepted to NeurIPS 2023
Continual Learning with Low Rank Adaptation
Comments Accepted at Workshop on Distribution Shifts (DistShift), NeurIPS 2023
Towards Higher Ranks via Adversarial Weight Pruning
Comments NeurIPS 2023 Accepted
Privacy Measurement in Tabular Synthetic Data: State of the Art and Future Research Directions
Comments 20 pages, 4 tables, 8 figures; NeurIPS 2023 Workshop on Synthetic Data Generation with Generative AI
Journal ref NeurIPS 2023 Workshop on Synthetic Data Generation with Generative AI
Weakly-semi-supervised object detection in remotely sensed imagery
Comments Tackling Climate Change with Machine Learning at NeurIPS 2023
Extracting an Informative Latent Representation of High-Dimensional Galaxy Spectra
Comments 5 pages, 6 figures, accepted by NeurIPS 2023
Symbol-LLM: Leverage Language Models for Symbolic System in Visual Human Activity Reasoning
Comments Accepted by NeurIPS 2023
Improving Self-supervised Molecular Representation Learning using Persistent Homology
Comments NeurIPS 2023
