Aaron Courville
- Papers
- 30
Cite
Notes
Only stored in your browser.
Authored papers
30The Markovian Thinker
arXiv 2025
Learning Robust Social Strategies with Large Language Models
arXiv 2025
Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation
arXiv 2025
Adaptive Computation Pruning for the Forgetting Transformer
arXiv 2025
Modeling Caption Diversity in Contrastive Vision-Language Pretraining
arXiv 2024
GenRL: Multimodal-foundation world models for generalization in embodied agents
arXiv 2024
Scattered Mixture-of-Experts Implementation
arXiv 2024
VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment
arXiv 2024
Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models
arXiv 2024
Bigger, Better, Faster: Human-level Atari with human-level efficiency
arXiv 2023
Language Model Alignment with Elastic Reset
language-model-alignment-with-elastic-reset
Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNets
arXiv 2023
Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimization
arXiv 2023
Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels
arXiv 2022
Deep Reinforcement Learning at the Edge of the Statistical Precipice
NeurIPS 2021 12
Touch-based Curiosity for Sparse-Reward Tasks
arXiv 2021
MIDI-DDSP: Detailed Control of Musical Performance via Hierarchical Modeling
midi-ddsp-detailed-control-of-musical
StructFormer: Joint Unsupervised Induction of Dependency and Constituency Structure from Masked Language Modeling
structformer-joint-unsupervised-induction-of
Data-Efficient Reinforcement Learning with Self-Predictive Representations
data-efficient-reinforcement-learning-with-2
Generative Compositional Augmentations for Scene Graph Prediction
ICCV 2021 10
Gradient Starvation: A Learning Proclivity in Neural Networks
NeurIPS 2021 12
Pix2Shape: Towards Unsupervised Learning of 3D Scenes from Images using a View-based Representation
arXiv 2020
What Do Compressed Deep Neural Networks Forget?
arXiv 2019
MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis
melgan-generative-adversarial-networks-for-1
Manifold Mixup: Better Representations by Interpolating Hidden States
ICLR 2019 5
FiLM: Visual Reasoning with a General Conditioning Layer
arXiv 2017
Improved Training of Wasserstein GANs
improved-training-of-wasserstein-gans-1
SampleRNN: An Unconditional End-to-End Neural Audio Generation Model
arXiv 2016
Describing Videos by Exploiting Temporal Structure
describing-videos-by-exploiting-temporal-1
Generative Adversarial Networks
generative-adversarial-networks-1
Affiliations
Frequent co-authors
10from 30 papers
Yoshua Bengio
Sai Rajeswar
Max Schwarzer
Michael Noukhovitch
Milad Aghajohari
Rishabh Agarwal
Alessandro Sordoni
Amirhossein Kazemnejad
Bart Dhoedt
David Vazquez
researcher