K-LITE: Learning Transferable Visual Models with External Knowledge
Comments NeurIPS 2022 camera ready
期刊&会议
NeurIPS
Conference on Neural Information Processing Systems · 会议 · Machine Learning
Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Models
Comments NeurIPS 2022
Dynamic population-based meta-learning for multi-agent communication with natural language
Comments Accepted at NeurIPS 2021
Learning from Few Samples: Transformation-Invariant SVMs with Composition and Locality at Multiple Scales
Comments Will appear in NeurIPS 2022
Graph Few-shot Learning with Task-specific Structures
Comments Accepted to NeurIPS 2022
A Non-Asymptotic Moreau Envelope Theory for High-Dimensional Generalized Linear Models
Comments As published at NeurIPS 2022
Efficient Dataset Distillation Using Random Feature Approximation
Comments Accepted to the Conference on the Advances in Neural Information Processing Systems (NeurIPS) 2022
Evolution of Neural Tangent Kernels under Benign and Adversarial Training
Comments Accepted to the Conference on Advances in Neural Information Processing Systems (NeurIPS) 2022
Deep Reinforcement Learning for Inverse Inorganic Materials Design
Comments NeurIPS AI4Mat Workshop 2022
Diffusion Visual Counterfactual Explanations
Comments NeurIPS 2022
Structural Kernel Search via Bayesian Optimization and Symbolical Optimal Transport
Comments Accepted at NeurIPS 2022
PaCo: Parameter-Compositional Multi-Task Reinforcement Learning
Comments 19 pages
Journal ref 36th Conference on Neural Information Processing Systems (NeurIPS 2022)
Multitasking Models are Robust to Structural Failure: A Neural Model for Bilingual Cognitive Reserve
Comments Accepted at NeurIPS 2022. 22 pages, 11 Figures
Model-based Lifelong Reinforcement Learning with Bayesian Exploration
Comments Accepted to NeurIPS 2022
Global Convergence of Direct Policy Search for State-Feedback $\mathcal{H}_\infty$ Robust Control: A Revisit of Nonsmooth Synthesis with Goldstein Subdifferential
Comments Accepted to NeurIPS 2022
Theoretical analysis of deep neural networks for temporally dependent observations
Comments 23 pages, 18 pages, accepted for publication in Neural Information Processing Systems
Coordinates Are NOT Lonely -- Codebook Prior Helps Implicit Neural 3D Representations
Comments NeurIPS 2022
Monte Carlo Augmented Actor-Critic for Sparse Reward Deep Reinforcement Learning from Suboptimal Demonstrations
Comments To be published in the 36th Conference on Neural Information Processing Systems (NeurIPS 2022). 19 pages. 11 figures
Detecting Label Errors in Token Classification Data
Journal ref NeurIPS 2022 Workshop on Interactive Learning for Natural Language Processing (InterNLP)
Learning-Augmented Algorithms for Online Linear and Semidefinite Programming
Comments 44 pages, 3 figures. To appear in NeurIPS 2022
Optimizing the Performative Risk under Weak Convexity Assumptions
Comments Neurips 2022 Workshop on Optimization for Machine Learning
The Phenomenon of Policy Churn
Comments Published at NeurIPS 2022
Controllable Text Generation with Neurally-Decomposed Oracle
Comments Accepted by NeurIPS 2022
Interventions, Where and How? Experimental Design for Causal Models at Scale
Comments Presented at the thirty-sixth Conference on Neural Information Processing Systems (2022)
Transformer Memory as a Differentiable Search Index
Comments NeurIPS 2022
Normalizing Flows for Knockoff-free Controlled Feature Selection
Comments Accepted to 36th Conference on Neural Information Processing Systems (NeurIPS 2022). 21 pages, 9 figures, 3 tables
Self-Supervised Learning via Maximum Entropy Coding
Comments Accepted by NeurIPS 2022
Breaking Bad: A Dataset for Geometric Fracture and Reassembly
Comments NeurIPS 2022 Track on Datasets and Benchmarks. The first three authors contributed equally to this work. Project page: https://breaking-bad-dataset.github.io/ Code: https://github.com/Wuziyi616/multi_part_assembly Dataset: https://borealisdata.ca/dataset.xhtml?persistentId=doi:10.5683/SP3/LZNPKB
On Feature Learning in the Presence of Spurious Correlations
Comments NeurIPS 2022. Code available at https://github.com/izmailovpavel/spurious_feature_learning
MoCoDA: Model-based Counterfactual Data Augmentation
Comments In Proceedings of NeurIPS 2022. 10 pages (+3 references, +10 appendix). Code available at https://github.com/spitis/mocoda
