Ruslan Salakhutdinov

Professor
Microsoft Faculty Fellow
Sloan Fellow
Carnegie Mellon University
rsalakhu[at]cs.cmu.edu
CV Google Scholar  

I am a UPMC professor of Computer Science in the Machine Learning Department, School of Computer Science at Carnegie Mellon University. I work in the field of statistical machine learning (See my CV.)

My research interests include Deep Learning, Probabilistic Graphical Models, and Large-scale Optimization.

Prospective students: Please read this to ensure that I read your email.

Recent Research Highlights:




Recent Papers:

  • Capsules with Inverted Dot-Product Attention Routing
    Yao-Hung Hubert Tsai, Nitish Srivastava, Hanlin Goh, Ruslan Salakhutdinov
    ICLR 2020, [arXiv]

  • Learning To Explore Using Active Neural Mapping
    Devendra Singh Chaplot, Saurabh Gupta, Dhiraj Gandhi, Abhinav Gupta, Ruslan Salakhutdinov
    ICLR 2020, [arXiv]

  • Differentiable Reasoning over a Virtual Knowledge Base
    Bhuwan Dhingra, Manzil Zaheer, Vidhisha Balachandran, Graham Neubig, Ruslan Salakhutdinov, William W. Cohen
    ICLR 2020, [arXiv]

  • Harnessing the Power of Infinitely Wide Deep Nets on Small-data Tasks
    Sanjeev Arora, Simon S. Du, Zhiyuan Li, Ruslan Salakhutdinov, Ruosong Wang, Dingli Yu
    ICLR 2020, [arXiv]

  • On Emergent Communication in Competitive Multi-Agent Teams
    Paul Pu Liang, Jeffrey Chen, Ruslan Salakhutdinov, Louis-Philippe Morency, Satwik Kottur
    AAMAS 2020.

  • Modular Visual Navigation using Active Neural Mapping
    Devendra Singh Chaplot, Saurabh Gupta, Abhinav Gupta, Ruslan Salakhutdinov
    [pdf] [Videos], Winner of the Habitat Navigation Challenge at CVPR 2019.

  • Concurrent Episodic Meta Reinforcement Learning
    Emilio Parisotto, Soham Ghosh, Sai Bhargav Yalamanchi, Varsha Chinnaobireddy, Yuhuai Wu, Ruslan Salakhutdinov
    [arXiv]

  • Efficient Exploration via State Marginal Matching
    Lisa Lee, Benjamin Eysenbach, Emilio Parisotto, Eric Xing, Sergey Levine, Ruslan Salakhutdinov
    [arXiv] [Code]

  • Worst cases policy gradients
    Charlie Tang, Jian Zhang, Ruslan Salakhutdinov
    CoRL 2019

  • Transformer Dissection: A Unified Understanding of Transformer Attention via the Lens of Kernel
    Yao-Hung Hubert Tsai, Shaojie Bai, Makoto Yamada, Louis-Philippe Morency, Ruslan Salakhutdinov
    EMNLP 2019, [arXiv]

  • Multiple Futures Prediction
    Charlie Tang, Ruslan Salakhutdinov
    NeurIPS 2019, [arXiv]

  • Search on the Replay Buffer: Bridging Planning and Reinforcement Learning
    Benjamin Eysenbach, Ruslan Salakhutdinov, Sergey Levine
    NeurIPS 2019, [arXiv] [Code]

  • Learning Data Manipulation for Augmentation and Weighting
    Zhiting Hu, Bowen Tan, Ruslan Salakhutdinov, Tom Mitchell, Eric P. Xing
    NeurIPS 2019

  • Mixtape: Breaking the Softmax Bottleneck Efficiently
    Zhilin Yang, Thang Luong, Ruslan Salakhutdinov, Quoc V Le
    NeurIPS 2019

  • XLNet: Generalized Autoregressive Pretraining for Language Understanding
    Zhilin Yang, Zihang Dai, Yiming Yang, Jaime Carbonell, Ruslan Salakhutdinov, Quoc V. Le
    NeurIPS 2019 [arXiv] [Code], oral,

  • Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels
    Simon S. Du, Kangcheng Hou, Barnabás Póczos, Ruslan Salakhutdinov, Ruosong Wang, Keyulu Xu
    NeurIPS 2019 [arXiv]

  • On Exact Computation with an Infinitely Wide Neural Net
    Sanjeev Arora, Simon S. Du, Wei Hu, Zhiyuan Li, Ruslan Salakhutdinov, Ruosong Wang
    NeurIPS 2019 [arXiv]

  • Learning Neural Networks with Adaptive Regularization
    Han Zhao, Yao-Hung Hubert Tsai, Ruslan Salakhutdinov, Geoffrey J. Gordon
    NeurIPS 2019 [arXiv]

  • Deep Gamblers: Learning to Abstain with Portfolio Theory
    Liu Ziyin, Zhikang Wang, Paul Pu Liang, Ruslan Salakhutdinov, Louis-Philippe Morency, Masahito Ueda
    NeurIPS 2019 [arXiv]

  • MineRL: A Large-Scale Dataset of Minecraft Demonstrations
    William H. Guss, Brandon Houghton, Nicholay Topin, Phillip Wang, Cayden Codel, Manuela Veloso, Ruslan Salakhutdinov
    IJCAI 2019 [arXiv], [Web]

  • My Way of Telling a Story": Persona based Grounded Story Generation
    Shrimai Prabhumoye, Khyathi Chandu, Ruslan Salakhutdinov, Alan W Black.
    Storytelling Workshop at ACL 2019 [arXiv],

  • Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
    Zihang Dai, Zhilin Yang, Yiming Yang, Jaime Carbonell, Quoc V. Le, Ruslan Salakhutdinov
    ACL 2019 [arXiv], [Code]

  • Multimodal Transformer for Unaligned Multimodal Language Sequences
    Yao-Hung Hubert Tsai, Shaojie Bai, Paul Pu Liang, Zico Kolter, Louis-Philippe Morency, Ruslan Salakhutdinov
    ACL 2019 [arXiv], [Code]

  • Learning Representations from Imperfect Time Series Data via Tensor Rank Regularization
    Paul Pu Liang, Zhun Liu, Yao-Hung Hubert Tsai, Qibin Zhao, Ruslan Salakhutdinov, Louis-Philippe Morency
    ACL 2019 [arXiv]

  • The Omniglot Challenge: A 3-Year Progress Report
    Brenden M. Lake, Ruslan Salakhutdinov, Joshua B. Tenenbaum
    Current Opinion in Behavioral Sciences, 2019 [arXiv]

  • Embodied Multimodal Multitask Learning
    Devendra Singh Chaplot, Lisa Lee, Ruslan Salakhutdinov, Devi Parikh, Dhruv Batra
    [arXiv]

  • Video Relationship Reasoning using Gated Spatio-Temporal Energy Graph
    Yao-Hung Hubert Tsai, Santosh Kumar Divvala, Louis-Philippe Morency, Ruslan Salakhutdinov, Ali Farhadi
    CVPR 2019, [arXiv]

  • A Strong and Simple Baseline for Multimodal Utterance Embeddings
    Paul Pu Liang, Yao Chong Lim, Yao-Hung Hubert Tsai, Ruslan Salakhutdinov, Louis-Philippe Morency
    NAACL 2019, [arXiv] [Code]

  • Deep Neural Networks with Multi-Branch Architectures Are Intrinsically Less Non-Convex
    Hongyang Zhang, Junru Shao, Ruslan Salakhutdinov
    AIStats 2019, [arXiv]

  • Learning Factorized Multimodal Representations
    Yao Hung Tsai, Paul Pu Liang, Amir Ali Bagherzade, Louis-Philippe Morency, Ruslan Salakhutdinov
    ICLR 2019, [arXiv] [Code]

  • AutoLoss: Learning Discrete Schedule for Alternate Optimization
    Haowen Xu, Hao Zhang, Zhiting Hu, Xiaodan Liang, Ruslan Salakhutdinov, Eric Xing
    ICLR 2019, [arXiv]

  • Post Selection Inference with Incomplete Maximum Mean Discrepancy Estimator
    Makoto Yamada, Yi Wu, Yao Hung Tsai, Hirofumi Ohtai, Ruslan Salakhutdinov, Ichiro Takeeuchi, Kenji Fukumizu
    ICLR 2019, [arXiv]

  • Revisiting LSTM Networks for Semi-Supervised Text Classification via Mixed Objective Function
    Devendra Singh Sachan, Manzil Zaheer, Ruslan Salakhutdinov
    AAAI 2019, [pdf]

  • GLoMo: Unsupervisedly Learned Relational Graphs as Transferable Representations
    Zhilin Yang, Jake Zhao, Bhuwan Dhingra, Kaiming He, William Cohen, Ruslan Salakhutdinov, Yann LeCun
    NeurIPS 2018, [arXiv]

  • Deep Generative Models with Learnable Knowledge Constraints
    Zhiting Hu, Zichao Yang, Ruslan Salakhutdinov, Xiaodan Liang, Lianhui Qin, Haoye Dong, Eric Xing
    NeurIPS 2018, [arXiv]

  • How Many Samples are Needed to Learn a Convolutional Neural Network?
    Simon Du, Yining Wang, Xiyu Zhai, Sivaraman Balakrishnani, Ruslan Salakhutdinov, Aarti Singh
    NeurIPS 2018, [arXiv]

  • HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
    Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William W. Cohen, Ruslan Salakhutdinov, Christopher Manning
    EMNLP, 2018, [arXiv], [Code, Data]

  • Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text
    Haitian Sun, Bhuwan Dhingra, Manzil Zaheer, Kathryn Mazaitis, Ruslan Salakhutdinov, William Cohen
    EMNLP, 2018, [arXiv], [Code]

  • Investigating the Working of Text Classifiers
    Devendra Singh Sachan, Manzil Zaheer, Ruslan Salakhutdinov
    COLING 2018, [arXiv]

  • Structured Control Nets for Deep Reinforcement Learning
    Mario Srouji, Jian Zhang, Ruslan Salakhutdinov
    ICML 2018, [arXiv]

  • Gated Path Planning Networks
    Lisa Lee, Emilio Parisotto, Devendra Singh Chaplot, Eric Xing, Ruslan Salakhutdinov
    ICML 2018, [arXiv], [Code].

  • Transformation Autoregressive Networks
    Junier B. Oliva, Avinava Dubey, Manzil Zaheer, BarnabásPoczos, Ruslan Salakhutdinov, Eric P. Xing, eff Schneider
    ICML 2018, [arXiv]

  • Learning Cognitive Models using Neural Networks,
    oral, Devendra Singh Chaplot, Christopher MacLellan, Ruslan Salakhutdinov, Kenneth Koedinger.
    [arXiv],, 19th International Conference on Artificial Intelligence in Education (AIED-18), London, UK

  • Style Transfer Through Back-Translation
    Shrimai Prabhumoye, Yulia Tsvetkov, Ruslan Salakhutdinov and Alan Black
    ACL 2018 [arXiv], [Code].

  • Neural Models for Reasoning over Multiple Mentions using Coreference
    Bhuwan Dhingra, Qiao Jin, Zhilin Yang, William W. Cohen, Ruslan Salakhutdinov
    NAACL, 2018 (Short Paper) [arXiv].

  • Global Pose Estimation with an Attention-based Recurrent Network
    Emilio Parisotto, Devendra Singh Chaplot, Jian Zhang, Ruslan Salakhutdinov
    CVPR 2018 workshop on Deep Learning for Visual SLAM [arXiv], 2018, best paper award .

  • On Characterizing the Capacity of Neural Networks using Algebraic Topology
    William H. Guss, Ruslan Salakhutdinov
    [arXiv], 2018.

  • Breaking the Softmax Bottleneck: A High-Rank RNN Language Model
    Zhilin Yang, Zihang Dai, Ruslan Salakhutdinov, William W. Cohen
    ICLR 2018, oral, [arXiv], [code].

  • Active Neural Localization
    Devendra Singh Chaplot, Emilio Parisotto, Ruslan Salakhutdinov
    ICLR 2018 [arXiv], [code].

  • Neural Map: Structured Memory for Deep Reinforcement Learning
    Emilio Parisotto, Ruslan Salakhutdinov
    ICLR 2018, [arXiv], ICLR 2018.

  • On Unifying Deep Generative Models
    Zhiting Hu, Zichao Yang, Ruslan Salakhutdinov, Eric P. Xing
    ICLR 2018 [arXiv].

  • Selecting the Best in GANs Family: a Post Selection Inference Framework
    Yao-Hung Hubert Tsai, Denny Wu, Makoto Yamada, Ruslan Salakhutdinov, Ichiro Takeuchi, Kenji Fukumizu
    [arXiv], ICLR workshop 2018.

  • A Generic Approach for Escaping Saddle Points
    Sashank J Reddi, Manzil Zaheer, Suvrit Sra, Barnabas Poczos, Francis Bach, Ruslan Salakhutdinov, Alexander J Smola
    [arXiv], AIStats 2018.

  • Gated-Attention Architectures for Task-Oriented Language Grounding
    Devendra Singh Chaplot, Kanthashree Mysore Sathyendra, Rama Kumar Pasumarthi, Dheeraj Rajagopal, Ruslan Salakhutdinov
    [arXiv], AAAI 2018, oral.

  • Knowledge-based Word Sense Disambiguation using Topic Models
    Devendra Singh Chaplot, Ruslan Salakhutdinov
    [pdf], AAAI 2018, oral.