Ruslan Salakhutdinov

60

Papers

1,198

Total Citations

Papers (60)

Path-SGD: Path-Normalized Optimization in Deep Neural Networks

NeurIPS 2015arXiv

Stochastic Variational Deep Kernel Learning

NeurIPS 2016arXiv

Architectural Complexity Measures of Recurrent Neural Networks

NeurIPS 2016arXiv

On Multiplicative Integration with Recurrent Neural Networks

NeurIPS 2016arXiv

Review Networks for Caption Generation

NeurIPS 2016arXiv

Dissecting Adversarial Robustness of Multimodal LM Agents

Confronting Reward Model Overoptimization with Constrained RLHF

Path-Normalized Optimization of Recurrent Neural Networks with ReLU Activations

NeurIPS 2016arXiv

Iterative Refinement of the Approximate Posterior for Directed Belief Networks

NeurIPS 2016arXiv

Video Relationship Reasoning Using Gated Spatio-Temporal Energy Graph

Neural Topological SLAM for Visual Navigation

Aligning Books and Movies: Towards Story-Like Visual Explanations by Watching Movies and Reading Books

Deep Determinantal Point Process for Large-Scale Multi-Label Classification

Learning Robust Visual-Semantic Embeddings

Learning To Hallucinate Examples From Extrinsic and Intrinsic Supervision

PACS: A Dataset for Physical Audiovisual Commonsense Reasoning

Learning Wake-Sleep Recurrent Attention Models

NeurIPS 2015arXiv

Skip-Thought Vectors

NeurIPS 2015arXiv

segDeepM: Exploiting Segmentation and Context in Deep Neural Networks for Object Detection

Good Semi-supervised Learning That Requires a Bad GAN

NeurIPS 2017arXiv

Spatially Adaptive Computation Time for Residual Networks

The More You Know: Using Knowledge Graphs for Image Classification

SEAL: Self-supervised Embodied Active Learning using Exploration and 3D Consistency

Accelerating Robotic Reinforcement Learning via Parameterized Action Primitives

Robust Predictable Control

Imitating Past Successes can be Very Suboptimal

Paraphrasing Is All You Need for Novel Object Captioning

Mismatched No More: Joint Model-Policy Optimization for Model-Based RL

Zero-shot Transfer Learning within a Heterogeneous Graph via Knowledge Transfer Networks

Contrastive Learning as Goal-Conditioned Reinforcement Learning

Generating Images with Multimodal Language Models

SPRING: Studying Papers and Reasoning to play Games

Quantifying & Modeling Multimodal Interactions: An Information Decomposition Framework

Factorized Contrastive Learning: Going Beyond Multi-view Redundancy

Toward Controlled Generation of Text

Improved Variational Autoencoders for Text Modeling using Dilated Convolutions

Gated Path Planning Networks

Transformation Autoregressive Networks

Structured Control Nets for Deep Reinforcement Learning

How Many Samples are Needed to Estimate a Convolutional Neural Network?

GLoMo: Unsupervised Learning of Transferable Relational Graphs

Deep Generative Models with Learnable Knowledge Constraints

Deep Gamblers: Learning to Abstain with Portfolio Theory

Learning Neural Networks with Adaptive Regularization

Mixtape: Breaking the Softmax Bottleneck Efficiently

Search on the Replay Buffer: Bridging Planning and Reinforcement Learning

Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels

Learning Data Manipulation for Augmentation and Weighting

Multiple Futures Prediction

On Exact Computation with an Infinitely Wide Neural Net

XLNet: Generalized Autoregressive Pretraining for Language Understanding

Neural Methods for Point-wise Dependency Estimation

Weakly-Supervised Reinforcement Learning for Controllable Behavior

Object Goal Navigation using Goal-Oriented Semantic Exploration

Reinforcement Learning with General Value Function Approximation: Provably Efficient Approach via Bounded Eluder Dimension

A Closer Look at Accuracy vs. Robustness

Planning with General Objective Functions: Going Beyond Total Rewards

Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement

On Reward-Free Reinforcement Learning with Linear Function Approximation

Replacing Rewards with Examples: Example-Based Policy Search via Recursive Classification