Yoshua Bengio
- Papers
- 56
Cite
Notes
Only stored in your browser.
Authored papers
56General Multimodal Protein Design Enables DNA-Encoding of Chemistry
arXiv 2026
When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents
arXiv 2026
AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Understanding
arXiv 2025
VCR: A Task for Pixel-Level Complex Reasoning in Vision Language Models via Restoring Occluded Text
arXiv 2024
Efficient Causal Graph Discovery Using Large Language Models
arXiv 2024
Improved off-policy training of diffusion samplers
arXiv 2024
HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models
arXiv 2024
MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic Approximation
arXiv 2024
Learning diverse attacks on large language models for robust red-teaming and safety tuning
arXiv 2024
AI-Assisted Generation of Difficult Math Questions
arXiv 2024
Causal Discovery in Astrophysics: Unraveling Supermassive Black Hole and Galaxy Coevolution
arXiv 2024
HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution
NeurIPS 2023 11
Crystal-GFN: sampling crystals with desirable properties and constraints
arXiv 2023
Hyena Hierarchy: Towards Larger Convolutional Language Models
arXiv 2023
torchgfn: A PyTorch GFlowNet library
arXiv 2023
Amortizing intractable inference in large language models
arXiv 2023
Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNets
arXiv 2023
GFlowNet-EM for learning compositional latent variable models
arXiv 2023
A theory of continuous generative flow networks
arXiv 2023
Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning
arXiv 2023
Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimization
arXiv 2023
Local Search GFlowNets
arXiv 2023
Expected flow networks in stochastic environments and two-player zero-sum games
arXiv 2023
FAENet: Frame Averaging Equivariant GNN for Materials Modeling
arXiv 2023
Better Training of GFlowNets with Local Credit and Incomplete Trajectories
arXiv 2023
Tree Cross Attention
arXiv 2023
PhyloGFN: Phylogenetic inference with generative flow networks
arXiv 2023
Object-centric architectures enable efficient causal representation learning
arXiv 2023
Learning GFlowNets from partial episodes for improved convergence and stability
arXiv 2022
Combining Modular Skills in Multitask Learning
arXiv 2022
Interventional Causal Representation Learning
arXiv 2022
Multi-Objective GFlowNets
arXiv 2022
Discrete Key-Value Bottleneck
arXiv 2022
Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning
arXiv 2022
Learning Neural Causal Models with Active Interventions
learning-neural-causal-models-with-active-1
ClimateGAN: Raising Climate Change Awareness by Generating Images of Floods
climategan-raising-climate-change-awareness-1
DEUP: Direct Epistemic Uncertainty Prediction
deup-direct-epistemic-uncertainty-prediction-1
Multi-task self-supervised learning for Robust Speech Recognition
arXiv 2020
Benchmarking Graph Neural Networks
arXiv 2020
Gradient Starvation: A Learning Proclivity in Neural Networks
NeurIPS 2021 12
Mastering Rate based Curriculum Learning
arXiv 2020
MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis
melgan-generative-adversarial-networks-for-1
Unsupervised State Representation Learning in Atari
unsupervised-state-representation-learning-in-1
Speaker Recognition from Raw Waveform with SincNet
arXiv 2018
HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
hotpotqa-a-dataset-for-diverse-explainable-1
Manifold Mixup: Better Representations by Interpolating Hidden States
ICLR 2019 5
An Empirical Study of Example Forgetting during Deep Neural Network Learning
an-empirical-study-of-example-forgetting-1
Graph Attention Networks
graph-attention-networks-1
FigureQA: An Annotated Figure Dataset for Visual Reasoning
figureqa-an-annotated-figure-dataset-for-1
Twin Networks: Matching the Future for Sequence Generation
twin-networks-matching-the-future-for-1
SampleRNN: An Unconditional End-to-End Neural Audio Generation Model
arXiv 2016
BinaryConnect: Training Deep Neural Networks with binary weights during propagations
binaryconnect-training-deep-neural-networks-1
A Hierarchical Recurrent Encoder-Decoder For Generative Context-Aware Query Suggestion
arXiv 2015
Generative Adversarial Networks
generative-adversarial-networks-1
Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
arXiv 2014
FitNets: Hints for Thin Deep Nets
arXiv 2014
Affiliations
Frequent co-authors
10from 56 papers
Nikolay Malkin
Aaron Courville
Moksh Jain
Dinghuai Zhang
Alex Hernandez-Garcia
Jarrid Rector-Brooks
Tianyu Zhang
Alessandro Sordoni
Salem Lahlou
Victor Schmidt