SatBird: Bird Species Distribution Modeling with Remote Sensing and Citizen Science Data
Comments 37th Conference on Neural Information Processing Systems (NeurIPS 2023) Track on Datasets and Benchmarks
作者
Yoshua Bengio
Machine Learning
Object-centric architectures enable efficient causal representation learning
Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Network
OC-NMN: Object-centric Compositional Neural Module Network for Generative Visual Analogical Reasoning
Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions
Contrastive Retrospection: honing in on critical steps for rapid learning and generalization in RL
Reusable Slotwise Mechanisms
Causal machine learning for single-cell genomics
Comments 35 pages, 7 figures, 3 tables, 1 box
Towards equilibrium molecular conformation generation with GFlowNets
Improving day-ahead Solar Irradiance Time Series Forecasting by Leveraging Spatio-Temporal Context
MixupE: Understanding and Improving Mixup from Directional Derivative Perspective
Comments 16 pages, Best Student Paper Award at UAI 2023
On the importance of catalyst-adsorbate 3D interactions for relaxed energy predictions
Stateful active facilitator: Coordination and Environmental Heterogeneity in Cooperative Multi-Agent Reinforcement Learning
Comments Published at ICLR 2023
Causal Inference in Gene Regulatory Networks with GFlowNet: Towards Scalability in Large Systems
Pre-Training and Fine-Tuning Generative Flow Networks
Trajectory balance: Improved credit assignment in GFlowNets
Comments NeurIPS 2022; see footnotes for code; v3 fixes minor errata
Model evaluation for extreme risks
Comments Fixed typos; added citation
Generalization in Deep Learning
Comments Published by Cambridge University Press. BibTeX of this paper is available at: https://people.csail.mit.edu/kawaguch/bibtex.html
Journal ref In Mathematical Aspects of Deep Learning. Cambridge University Press, 2022
Consciousness in Artificial Intelligence: Insights from the Science of Consciousness
Benchmarking Bayesian Causal Discovery Methods for Downstream Treatment Effect Estimation
Comments Peer-reviewed and Accepted to ICML 2023 Workshop on Structured Probabilistic Inference & Generative Modeling
Multi-Objective GFlowNets
Comments 23 pages, 8 figures. ICML 2023. Code at: https://github.com/GFNOrg/multi-objective-gfn
AI For Global Climate Cooperation 2023 Competition Proceedings
Attention Schema in Neural Agents
International Institutions for Advanced AI
Comments 19 pages, 2 figures, fixed rendering issues
Equivariance with Learned Canonicalization Functions
Comments 21 pages, 5 figures
Generative Flow Networks: a Markov Chain Perspective
Thompson sampling for improved exploration in GFlowNets
Comments Structured Probabilistic Inference and Generative Modeling (SPIGM) workshop @ ICML 2023
BatchGFN: Generative Flow Networks for Batch Active Learning
Comments Accepted at the Structured Probabilistic Inference & Generative Modeling workshop, ICML 2023
GFlowNets for AI-Driven Scientific Discovery
Comments 31 pages, 5 figures. Updated with camera-ready changes
Stochastic Generative Flow Networks
Comments UAI 2023
