Posterior Refinement Improves Sample Efficiency in Bayesian Neural Networks
Comments NeurIPS 2022
期刊&会议
NeurIPS
Conference on Neural Information Processing Systems · 会议 · Machine Learning
Domain Adaptation meets Individual Fairness. And they get along
Comments Published at NeurIPS 2022
Influencing Long-Term Behavior in Multiagent Reinforcement Learning
Comments Accepted to NeurIPS 2022. The earlier version was presented at the Gamification and Multiagent Solutions Workshop (ICLR 2022) with a spotlight. Code at https://github.com/dkkim93/further and videos at https://sites.google.com/view/further-marl
Sampling with Riemannian Hamiltonian Monte Carlo in a Constrained Space
Comments Mixing-rate proof added. To appear in NeurIPS 2022
Robust Binary Models by Pruning Randomly-initialized Networks
Comments Accepted as NeurIPS 2022 paper
The Stability-Efficiency Dilemma: Investigating Sequence Length Warmup for Training GPT Models
Comments Published in NeurIPS 2022. This paper was previously titled "Curriculum Learning: A Regularization Method for Efficient and Stable Billion-Scale GPT Model Pre-Training" in early arxiv preprint versions
Model Preserving Compression for Neural Networks
Comments 26 pages, 15 figures. To be published in Advances in Neural Information Processing Systems 35
InsNet: An Efficient, Flexible, and Performant Insertion-based Text Generation Model
Comments Accepted as a poster paper at NeurIPS 2022
RainNet: A Large-Scale Imagery Dataset and Benchmark for Spatial Precipitation Downscaling
Comments Accepted at NeurIPS 2022. Project page: https://neuralchen.github.io/RainNet/
Journal ref Conference on Neural Information Processing Systems (NeurIPS) 2022
Learnable Polyphase Sampling for Shift Invariant and Equivariant Convolutional Networks
Comments Accepted at the Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS 2022)
AVLEN: Audio-Visual-Language Embodied Navigation in 3D Environments
Comments Accepted at NeurIPS 2022
A Consistent and Differentiable Lp Canonical Calibration Error Estimator
Comments To appear at NeurIPS 2022
Object-Category Aware Reinforcement Learning
Comments This paper is to be published on NeurIPS 2022
Theory and Approximate Solvers for Branched Optimal Transport with Multiple Sources
Comments To be published in proceedings of NeurIPS 2022
DART: Articulated Hand Model with Diverse Accessories and Rich Textures
Comments Homepage: dart2022.github.io. Accepted by NeurIPS 2022 Datasets and Benchmarks Track
Revisiting Heterophily For Graph Neural Networks
Comments Published at 36th Conference on Neural Information Processing Systems (NeurIPS 2022). arXiv admin note: substantial text overlap with arXiv:2109.05641
Model-based Safe Deep Reinforcement Learning via a Constrained Proximal Policy Optimization Algorithm
Comments Proceedings of NeurIPS 2022
Mix and Reason: Reasoning over Semantic Topology with Data Mixing for Domain Generalization
Comments Accepted by NeurIPS 2022
TokenMixup: Efficient Attention-guided Token-level Data Augmentation for Transformers
Comments Accepted paper at NeurIPS 2022
Provable Subspace Identification Under Post-Nonlinear Mixtures
Comments Accepted to NeurIPS 2022, 21 pages, 2 figures
Counterfactual Neural Temporal Point Process for Estimating Causal Influence of Misinformation on Social Media
Comments 19 pages, 8 figures, already accepted by NeurIPS 2022
Weakly-Supervised Multi-Granularity Map Learning for Vision-and-Language Navigation
Comments Accepted by NeurIPS 2022
Learning Active Camera for Multi-Object Navigation
Comments Accepted by NeurIPS 2022
CaloDVAE : Discrete Variational Autoencoders for Fast Calorimeter Shower Simulation
Comments 11 pages, 4 figures, 5 tables, Accepted version at NeurIPS Workshop on Machine Learning and the Physical Sciences (ML4PS) 2021
Efficiently Computing Local Lipschitz Constants of Neural Networks via Bound Propagation
Comments NeurIPS 2022
Amortized Inference for Heterogeneous Reconstruction in Cryo-EM
Journal ref Neural Information Processing Systems (NeurIPS) 2022
SHINE: SubHypergraph Inductive Neural nEtwork
Comments 36th Conference on Neural Information Processing Systems (NeurIPS 2022)
AMP: Automatically Finding Model Parallel Strategies with Heterogeneity Awareness
Comments Accepted at NeurIPS 2022 (Paper ID: 12583)
BLOX: Macro Neural Architecture Search Benchmark and Algorithms
Comments Published in the Proceedings of the 36th Conference on Neural Information Processing Systems (NeurIPS 2022) Track on Datasets and Benchmarks
S4ND: Modeling Images and Videos as Multidimensional Signals Using State Spaces
Comments NeurIPS 2022
