Zero-shot Video Moment Retrieval With Off-the-Shelf Models
Comments Accepted to the NeurIPS 2022 Workshop on Transfer Learning for NLP (TL4NLP). 12 pages, 5 figures
期刊&会议
NeurIPS
Conference on Neural Information Processing Systems · 会议 · Machine Learning
Contrastive Value Learning: Implicit Models for Simple Offline RL
Comments Deep Reinforcement Learning Workshop, NeurIPS 2022
Overcoming Barriers to Skill Injection in Language Modeling: Case Study in Arithmetic
Comments NeurIPS 2022: Math-AI Workshop
Fairness in Federated Learning via Core-Stability
Comments NeurIPS 2022; code: https://openreview.net/attachment?id=lKULHf7oFDo&name=supplementary_material
Scaling Multimodal Pre-Training via Cross-Modality Gradient Harmonization
Comments Accepted at NeurIPS 2022
Digital Human Interactive Recommendation Decision-Making Based on Reinforcement Learning
Comments 9 pages, 1 figure, 1 table, the paper has been accepted and this is the final camera-ready for NeurIPS 2022 Workshop on Human in the Loop Learning, https://neurips-hill.github.io/
Predictive Querying for Autoregressive Neural Sequence Models
Comments Oral Presentation at the Intl. Conference on Neural Information Processing Systems (NeurIPS 2022)
When Privacy Meets Partial Information: A Refined Analysis of Differentially Private Bandits
Comments Appears in NeurIPS 2022. From v1, the minimax lower bound for linear bandits is changed to $O(\max(d \sqrt{T}, d/ε))$
Is one annotation enough? A data-centric image classification benchmark for noisy and ambiguous label estimation
Comments Accepted at NeurIPS 2022, Benchmark and Dataset Track, Code and Link to data available at https://github.com/Emprime/dcic
Hub-Pathway: Transfer Learning from A Hub of Pre-trained Models
Comments Accepted by NeurIPS 2022
Vision GNN: An Image is Worth Graph of Nodes
Comments NeurIPS 2022
The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games
Comments This paper has been accepted by NeurIPS 2022 Datasets and Benchmarks
Uncertainty Estimation Using Riemannian Model Dynamics for Offline Reinforcement Learning
Journal ref Neurips 2022
A Geometric Perspective on Variational Autoencoders
Comments Accepted to NeurIPS 2022
Fault-Tolerant Federated Reinforcement Learning with Theoretical Guarantee
Comments Published at NeurIPS 2021. Extended version with proofs and additional experimental details and results. New version changes: reduced file size of figures; added a diagram illustrating the problem setting; added link to code on GitHub; modified proof for Theorem 6 (highlighted in red)
Adaptive Stochastic Variance Reduction for Non-convex Finite-Sum Minimization
Comments 23 pages, 2 figures, accepted at NeurIPS 2022
Fine-Tuning Pre-Trained Language Models Effectively by Optimizing Subnetworks Adaptively
Comments NeurIPS 2022
Image-based Early Detection System for Wildfires
Comments Published in Tackling Climate Change with Machine Learning workshop, Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS 2022)
Embed and Emulate: Learning to estimate parameters of dynamical systems with uncertainty quantification
Comments Accepted at NeurIPS 2022
On the Safety of Interpretable Machine Learning: A Maximum Deviation Approach
Comments Published at NeurIPS 2022
The Need for Medically Aware Video Compression in Gastroenterology
Comments Medical Imaging Meets NeurIPS Workshop 2022, NeurIPS 2022
Dual Generator Offline Reinforcement Learning
Comments NeurIPS 2022
PI is back! Switching Acquisition Functions in Bayesian Optimization
Comments 2022 NeurIPS Workshop on Gaussian Processes, Spatiotemporal Modeling, and Decision-making Systems
TANGO: Text-driven Photorealistic and Robust 3D Stylization via Lighting Decomposition
Comments Accepted by NeurIPS 2022
A Practical, Progressively-Expressive GNN
Comments NeurIPS 2022
Model-Based Imitation Learning for Urban Driving
Comments NeurIPS 2022
Towards Learned Simulators for Cell Migration
Comments Accepted at NeurIPS 2022 AI for Science workshop
FedToken: Tokenized Incentives for Data Contribution in Federated Learning
Comments Accepted at Workshop on Federated Learning: Recent Advances and New Challenges, in Conjunction with NeurIPS 2022 (FL-NeurIPS'22). 9 Pages, 5 Figures
CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning
Comments An earlier version of the work was accepted to NeurIPS 2022
Manifold Interpolating Optimal-Transport Flows for Trajectory Inference
Comments Presented at NeurIPS 2022, 24 pages, 7 tables, 14 figures
