Expressive Sign Equivariant Networks for Spectral Geometric Learning
Comments NeurIPS 2023 Spotlight
期刊&会议
NeurIPS
Conference on Neural Information Processing Systems · 会议 · Machine Learning
AdsorbRL: Deep Multi-Objective Reinforcement Learning for Inverse Catalysts Design
Comments 37th Conference on Neural Information Processing Systems (NeurIPS 2023), AI for Accelerated Materials Design Workshop
Hierarchical Cross-entropy Loss for Classification of Astrophysical Transients
Comments Accepted to Machine Learning and the Physical Sciences Workshop at NeurIPS 2023
Quality Diversity in the Amorphous Fortress (QD-AF): Evolving for Complexity in 0-Player Games
Comments 18 pages, 7 figures, ALOE workship at NeurIPS 2023
Training Chain-of-Thought via Latent-Variable Inference
Comments 23 pages, 37th Conference on Neural Information Processing Systems (NeurIPS 2023)
Can SAM recognize crops? Quantifying the zero-shot performance of a semantic segmentation foundation model on generating crop-type maps using satellite imagery for precision agriculture
Comments Accepted at NeurIPS 2023 AI for Science Workshop
Hardware Resilience Properties of Text-Guided Image Classifiers
Comments Accepted at NeurIPS 2023
From Classification to Generation: Insights into Crosslingual Retrieval Augmented ICL
Comments In The Workshop on Instruction Tuning and Instruction Following, held in conjunction with The Conference on NeurIPS 2023, December 2023. arXiv admin note: text overlap with arXiv:2311.00587
Out-of-distribution Detection Learning with Unreliable Out-of-distribution Sources
Comments Accepted by NeurIPS 2023
Pitfall of Optimism: Distributional Reinforcement Learning by Randomizing Risk Criterion
Comments NeurIPS 2023
Towards out-of-distribution generalizable predictions of chemical kinetics properties
Comments NeurIPS 2023 Workshop in AI for Scientific Discovery: From Theory to Practice. 11 pages, 1 figure, and 5 tables Data and code can be found in https://github.com/zihao-wang/ReactionOOD
GPT-Driver: Learning to Drive with GPT
Comments NeurIPS 2023 Foundation Models for Decision Making Workshop
A Multi-Task Perspective for Link Prediction with New Relation Types and Nodes
Comments Accepted to NeurIPS GLFrontiers 2023. 24 pages, 3 figures
Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models
Comments NeurIPS 2023. 53 pages, 29 figures, 12 tables. Code at https://github.com/layer6ai-labs/dgm-eval, reviews at https://openreview.net/forum?id=08zf7kTOoh
Journal ref Thirty-seventh Conference on Neural Information Processing Systems (2023)
Does a sparse ReLU network training problem always admit an optimum?
Comments NeurIPS 2023 - Thirty-seventh Conference on Neural Information Processing Systems, Dec 2023, New Orleans (Lousiane), United States
Primal-Attention: Self-attention through Asymmetric Kernel SVD in Primal Representation
Comments NeurIPS 2023. We provide a primal-dual representation for the asymmetric self-attention in transformer that allows to avoid explicit computation of the kernel matrix
Solving Inverse Physics Problems with Score Matching
Comments Accepted at NeurIPS 2023; code available at https://github.com/tum-pbs/SMDP
Grassmann Manifold Flows for Stable Shape Generation
Comments 35 pages, Accepted to NeurIPS 2023
Action Inference by Maximising Evidence: Zero-Shot Imitation from Observation with World Models
Comments NeurIPS 2023
AI ensemble for signal detection of higher order gravitational wave modes of quasi-circular, spinning, non-precessing binary black hole mergers
Comments 4 pages, 2 figures, 1 table; v2: 5 pages, 2 figures, 1 table, accepted to NeurIPS 2023 workshop on Machine Learning and the Physical Sciences
A Generative Self-Supervised Framework using Functional Connectivity in fMRI Data
Comments NeurIPS 2023 Temporal Graph Learning Workshop
Near-Optimal Algorithms for Gaussians with Huber Contamination: Mean Estimation and Linear Regression
Comments To appear in NeurIPS 2023
CalliPaint: Chinese Calligraphy Inpainting with Diffusion Model
Comments Accepted as a Machine Learning for Creativity and Design(ML4CD) workshop paper at NeruaIPS 2023. https://neurips.cc/virtual/2023/workshop/66545#wse-detail-75063
Effectively Fine-tune to Improve Large Multimodal Models for Radiology Report Generation
Comments Accepted to Deep Generative Models for Health Workshop at NeurIPS 2023
Regularity as Intrinsic Reward for Free Play
Comments NeurIPS 2023 camera-ready version. Project webpage at http://sites.google.com/view/rair-project
Marginal Density Ratio for Off-Policy Evaluation in Contextual Bandits
Comments Conference on Neural Information Processing Systems (NeurIPS 2023)
Compositional Policy Learning in Stochastic Control Systems with Formal Guarantees
Comments Accepted at NeurIPS 2023
Honesty Is the Best Policy: Defining and Mitigating AI Deception
Comments Accepted as a spotlight at the 37th Conference on Neural Information Processing Systems (NeurIPS 2023)
Continuous Convolutional Neural Networks for Disruption Prediction in Nuclear Fusion Plasmas
Comments Accepted at CCAI NeurIPS 2023
DDxT: Deep Generative Transformer Models for Differential Diagnosis
Comments Accepted at 1st Workshop on Deep Generative Models for Health at NeurIPS 2023
