Learning to Navigate Wikipedia by Taking Random Walks
Journal ref NeurIPS 2022
期刊&会议
NeurIPS
Conference on Neural Information Processing Systems · 会议 · Machine Learning
Revisiting Neural Scaling Laws in Language and Vision
Journal ref Neural Information Processing Systems (NeurIPS), 2022
SCONE: Surface Coverage Optimization in Unknown Environments by Volumetric Integration
Comments NeurIPS 2022 Camera-Ready. Project Webpage: https://github.com/Anttwo/SCONE
VeriDark: A Large-Scale Benchmark for Authorship Verification on the Dark Web
Comments Accepted at the 36th Conference on Neural Information Processing Systems (NeurIPS 2022) Track on Datasets and Benchmarks. 21 pages, 4 figures, 11 tables
A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks
Comments NeurIPS 2022 Datasets & Benchmarks; Toolkits avaliable at https://github.com/thunlp/OpenBackdoor
Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning
Comments Accepted to Neural Information Processing Systems (NeurIPS) 2022
Clipped Stochastic Methods for Variational Inequalities with Heavy-Tailed Noise
Comments NeurIPS 2022. 74 pages, 18 figures. Changes in v2: few typos were fixed, new experiments with clipped-SEG were added. Code: https://github.com/busycalibrating/clipped-stochastic-methods
Neuron with Steady Response Leads to Better Generalization
Comments Accepted by NeurIPS'22
Adversarial Training with Complementary Labels: On the Benefit of Gradually Informative Attacks
Comments NeurIPS 2022
Discrete Factorial Representations as an Abstraction for Goal Conditioned Reinforcement Learning
Comments Neurips 2022
FL Games: A Federated Learning Framework for Distribution Shifts
Comments Accepted as ORAL at NeurIPS Workshop on Federated Learning: Recent Advances and New Challenges. arXiv admin note: text overlap with arXiv:2205.11101
Improving Fairness in Image Classification via Sketching
Comments 8 pages, 2 figures. To appear in 2022 Trustworthy and Socially Responsible Machine Learning (TSRML 2022) co-located with NeurIPS 2022
Improving Motion Forecasting for Autonomous Driving with the Cycle Consistency Loss
Comments Accepted at NeurIPS 2022 Machine Learning for Autonomous Driving Workshop
A new benchmark for group distribution shifts in hand grasp regression for object manipulation. Can meta-learning raise the bar?
Comments Workshop on Distribution Shifts, 36th Conference on Neural Information Processing Systems (NeurIPS 2022)
A Self-Supervised Approach to Reconstruction in Sparse X-Ray Computed Tomography
Comments NeurIPS 2022 Machine Learning and the Physical Sciences Workshop. arXiv admin note: text overlap with arXiv:2210.16709
Cooperative Distribution Alignment via JSD Upper Bound
Comments Accepted for publication in Advances in Neural Information Processing Systems 36 (NeurIPS 2022)
Towards Robust Blind Face Restoration with Codebook Lookup Transformer
Comments Accepted by NeurIPS 2022. Code: https://github.com/sczhou/CodeFormer
NaturalProver: Grounded Mathematical Proof Generation with Language Models
Comments NeurIPS 2022
Dynamical Wasserstein Barycenters for Time-series Modeling
Comments To appear at Neurips 2021
Learning Utilities and Equilibria in Non-Truthful Auctions
Comments A previous version of this paper has been accepted to NeurIPS 2020. This version fixes errors and updates references
MatKG: The Largest Knowledge Graph in Materials Science -- Entities, Relations, and Link Prediction through Graph Representation Learning
Comments Spotlighted paper for AI4Mat workshop in NeurIPS 2022
Deep Gaussian Process-based Multi-fidelity Bayesian Optimization for Simulated Chemical Reactors
Comments 4 pages, 2022 NeurIPS Workshop on Gaussian Processes, Spatiotemporal Modeling, and Decision-making Systems
DUEL: Adaptive Duplicate Elimination on Working Memory for Self-Supervised Learning
Comments 9 pages, 5 figures, submitted to NeurIPS 2022 Workshop on Self-supervised Learning: Theory and Practice.(Accepted, https://sslneurips22.github.io/)
Symbolic Distillation for Learned TCP Congestion Control
Comments Accepted in Advances in Neural Information Processing Systems (NeurIPS), 2022
A Simple Hypergraph Kernel Convolution based on Discounted Markov Diffusion Process
Comments Accepted by NeurIPS 2022 New Frontiers in Graph Learning Workshop
On Rate-Distortion Theory in Capacity-Limited Cognition & Reinforcement Learning
Comments Accepted to the NeurIPS Workshop on Information-Theoretic Principles in Cognitive Systems (InfoCog) 2022. arXiv admin note: text overlap with arXiv:2206.02072
Planning to the Information Horizon of BAMDPs via Epistemic State Abstraction
Comments Accepted to Neural Information Processing Systems (NeurIPS) 2022
Alleviating the Sample Selection Bias in Few-shot Learning by Removing Projection to the Centroid
Comments Accepted at NeurIPS 2022
Towards Versatile Embodied Navigation
Comments Accepted to NeurIPS 2022; Code: https://github.com/hanqingwangai/VXN
Dataset Distillation via Factorization
Comments NeurIPS 2022
