PKD: General Distillation Framework for Object Detectors via Pearson Correlation Coefficient
Comments Accepted in NeurIPS 2022
期刊&会议
NeurIPS
Conference on Neural Information Processing Systems · 会议 · Machine Learning
Scalable and Efficient Training of Large Convolutional Neural Networks with Differential Privacy
Comments Accepted to NeurIPS 2022
Learning to Scaffold: Optimizing Model Explanations for Teaching
Comments 10 pages. NeurIPS 2022
Are Commercial Face Detection Models as Biased as Academic Models?
Comments This preprint and arXiv:2108.12508 were combined and a more rigorous analysis added to result in the NeurIPS Datasets & Benchmark 2022 paper arXiv:2211.15937
Finding Differences Between Transformers and ConvNets Using Counterfactual Simulation Testing
Comments Published at the Conference on Neural Information Processing Systems (NeurIPS) 2022
Exploring the Long-Term Generalization of Counting Behavior in RNNs
Comments Published in I Can't Believe It's Not Better: Understanding Deep Learning Through Empirical Falsification Workshop at NeurIPS 2022
Multi-Agent Reinforcement Learning for Microprocessor Design Space Exploration
Comments Workshop on ML for Systems at NeurIPS 2022
Outlier-Robust Sparse Mean Estimation for Heavy-Tailed Distributions
Comments To appear in NeurIPS 2022
A Contextual Bandit Approach for Learning to Plan in Environments with Probabilistic Goal Configurations
Comments Shorter version accepted at NeurIPS 2022 Workshop on Robot Learning: Trustworthy Robotics
Touch and Go: Learning from Human-Collected Vision and Touch
Comments Accepted by NeurIPS 2022 Track of Datasets and Benchmarks
On Learning Fairness and Accuracy on Multiple Subgroups
Comments NeurIPS-2022 Camera-ready
Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection
Comments Accepted at NeurIPS 2022
Preservation of the Global Knowledge by Not-True Distillation in Federated Learning
Comments 36th Conference on Neural Information Processing Systems (NeurIPS 2022)
Machine learning emulation of a local-scale UK climate model
Comments 8 pages, 5 figures, Tackling Climate Change with Machine Learning workshop at NeurIPS 2022
Robustness Disparities in Face Detection
Comments NeurIPS Datasets & Benchmarks Track 2022
Disentangling the Mechanisms Behind Implicit Regularization in SGD
Comments Accepted as Spotlight at the NeurIPS 2022 Workshop for Higher Order Optimization in Machine Learning
The Myth of Culturally Agnostic AI Models
Comments Accepted for "Cultures in AI/AI in Culture" NeurIPS 2022 Workshop
Elements of effective machine learning datasets in astronomy
Comments 5 pages, 1 figure, accepted to the peer-reviewed NeurIPS Machine Learning in the Physical Sciences Workshop, 2022
CASPR: Customer Activity Sequence-based Prediction and Representation
Comments Presented at the Table Representation Learning Workshop, NeurIPS 2022, New Orleans. Authors listed in random order
Posterior samples of source galaxies in strong gravitational lenses with score-based priors
Comments 5+6 pages, 3 figures, Accepted (poster + contributed talk) for the Machine Learning and the Physical Sciences Workshop at the 36th conference on Neural Information Processing Systems (NeurIPS 2022); Corrected style file and added authors checklist
Pile of Law: Learning Responsible Data Filtering from the Law and a 256GB Open-Source Legal Dataset
Comments Presented at NeurIPS Datasets & Benchmarks (2022)
BinauralGrad: A Two-Stage Conditional Diffusion Probabilistic Model for Binaural Audio Synthesis
Comments NeurIPS 2022 camera version
The Curse of Zero Task Diversity: On the Failure of Transfer Learning to Outperform MAML and their Empirical Equivalence
Comments An updated version with updated correction is at arXiv:2208.01545 and it's acompanying neurips submission is at https://brando90.github.io/brandomiranda/publications.html
Beyond Ads: Sequential Decision-Making Algorithms in Law and Public Policy
Comments Version 1 presented at Causal Inference Challenges in Sequential Decision Making: Bridging Theory and Practice (2021), a NeurIPS 2021 Workshop; Version 2 presented at the 2nd ACM Symposium on Computer Science and Law (2022) (DOI: https://dl.acm.org/doi/10.1145/3511265.3550439)
Logical Activation Functions: Logit-space equivalents of Probabilistic Boolean Operators
Journal ref Neural Information Processing Systems (2022)
FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognition
Comments NeurIPS 2021. Code URL: https://github.com/microsoft/NeuralSpeech
Hand-Object Interaction Image Generation
Comments Accepted by NeurIPS 2022 (Spotlight); Project Page: https://play-with-hoi-generation.github.io/
Investigating Prompt Engineering in Diffusion Models
Comments Paper submitted for Creativity and Design workshop at NeurIPS 2022. (4 pages including references + 7 page appendix). We would like to thank Google and the ML Developer Programs Team for their assistance and compute credits used in the experiments for this paper
Context-Adaptive Deep Neural Networks via Bridge-Mode Connectivity
Comments Accepted to the NeurIPS 2022 ML Safety Workshop
Dynamic Collaborative Multi-Agent Reinforcement Learning Communication for Autonomous Drone Reforestation
Comments Deep Reinforcement Learning Workshop at the 36th Conference on Neural Information Processing Systems (NeurIPS 2022)
