Samy Bengio

23

Papers

2,886

Total Citations

Papers (23)

Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks

NeurIPS 2015arXiv

Reward Augmented Maximum Likelihood for Neural Structured Prediction

NeurIPS 2016arXiv

The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity

Learning Semantic Relationships for Better Action Retrieval in Images

Can Active Memory Replace Attention?

NeurIPS 2016arXiv

Show and Tell: A Neural Image Caption Generator

Context-Aware Captions From Context-Agnostic Supervision

You Look Twice: GaterNet for Dynamic Filter Selection in CNNs

An Online Sequence-to-Sequence Model Using Partial Conditioning

Transformers learn through gradual rank increase

ADIOS: Architectures Deep In Output Space

Sharp Minima Can Generalize For Deep Nets

Device Placement Optimization with Reinforcement Learning

Fast Decoding in Sequence Models Using Discrete Latent Variables

Area Attention

Large Margin Deep Networks for Classification

Content preserving text generation with attribute controls

Insights on representational similarity in neural networks with canonical correlation

Transfusion: Understanding Transfer Learning for Medical Imaging

Memory Based Trajectory-conditioned Policies for Learning from Sparse Rewards

Learnable Fourier Features for Multi-dimensional Spatial Positional Encoding

Improving Anytime Prediction with Parallel Cascaded Networks and a Temporal-Difference Loss

Learning to Reason with Neural Networks: Generalization, Unseen Data and Boolean Measures