


Остановите войну!
for scientists:


default search action
Ruslan Salakhutdinov
Russ Salakhutdinov
Person information

- affiliation: Carnegie Mellon University, Machine Learning Department, Pittsburgh, PA, USA
- affiliation: University of Toronto, Departments of Statistics and Computer Science, ON, Canada
- affiliation: Massachusetts Institute of Technology, Artificial Intelligence Lab, Cambridge, MA, USA
Refine list

refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2023
- [j12]Paul Pu Liang, Yiwei Lyu, Xiang Fan, Arav Agarwal, Yun Cheng, Louis-Philippe Morency, Ruslan Salakhutdinov:
MultiZoo and MultiBench: A Standardized Toolkit for Multimodal Deep Learning. J. Mach. Learn. Res. 24: 234:1-234:7 (2023) - [j11]Yao-Yuan Yang, Cyrus Rashtchian, Ruslan Salakhutdinov, Kamalika Chaudhuri:
Probing Predictions on OOD Images via Nearest Categories. Trans. Mach. Learn. Res. 2023 (2023) - [c218]Rohan Pandey, Rulin Shao, Paul Pu Liang, Ruslan Salakhutdinov, Louis-Philippe Morency:
Cross-modal Attention Congruence Regularization for Vision-Language Relation Alignment. ACL (1) 2023: 5444-5455 - [c217]Xiang Fan, Yiwei Lyu, Paul Pu Liang, Ruslan Salakhutdinov, Louis-Philippe Morency:
Nano: Nested Human-in-the-Loop Reward Learning for Few-shot Language Model Control. ACL (Findings) 2023: 11970-11992 - [c216]Paul Pu Liang
, Yiwei Lyu
, Gunjan Chhablani
, Nihal Jain
, Zihao Deng
, Xingbo Wang
, Louis-Philippe Morency
, Ruslan Salakhutdinov
:
MultiViz: Towards User-Centric Visualizations and Interpretations of Multimodal Models. CHI Extended Abstracts 2023: 214:1-214:21 - [c215]Raj Ghugare, Homanga Bharadhwaj, Benjamin Eysenbach, Sergey Levine, Russ Salakhutdinov:
Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective. ICLR 2023 - [c214]Paul Pu Liang, Yiwei Lyu, Gunjan Chhablani, Nihal Jain, Zihao Deng, Xingbo Wang, Louis-Philippe Morency, Ruslan Salakhutdinov:
MultiViz: Towards Visualizing and Understanding Multimodal Models. ICLR 2023 - [c213]Haitian Sun, William W. Cohen, Ruslan Salakhutdinov:
Scenario-based Question Answering with Interacting Contextual Properties. ICLR 2023 - [c212]Brandon Trabucco, Gunnar A. Sigurdsson, Robinson Piramuthu, Gaurav S. Sukhatme, Ruslan Salakhutdinov:
A Simple Approach for Visual Room Rearrangement: 3D Mapping and Semantic Search. ICLR 2023 - [c211]Paul Pu Liang
, Yun Cheng
, Ruslan Salakhutdinov
, Louis-Philippe Morency
:
Multimodal Fusion Interactions: A Study of Human and Automatic Quantification. ICMI 2023: 425-435 - [c210]Benjamin Eysenbach, Matthieu Geist, Sergey Levine, Ruslan Salakhutdinov:
A Connection between One-Step RL and Critic Regularization in Reinforcement Learning. ICML 2023: 9485-9507 - [c209]Jing Yu Koh, Ruslan Salakhutdinov, Daniel Fried:
Grounding Language Models to Images for Multimodal Inputs and Outputs. ICML 2023: 17283-17300 - [c208]Minji Yoon, Yue Wu, John Palowitch, Bryan Perozzi, Russ Salakhutdinov:
Graph Generative Model for Benchmarking Graph Neural Networks. ICML 2023: 40175-40198 - [c207]Kyle Beltran Hatch, Benjamin Eysenbach, Rafael Rafailov, Tianhe Yu, Ruslan Salakhutdinov, Sergey Levine, Chelsea Finn:
Contrastive Example-Based Control. L4DC 2023: 155-169 - [i215]Jing Yu Koh, Ruslan Salakhutdinov, Daniel Fried:
Grounding Language Models to Images for Multimodal Generation. CoRR abs/2301.13823 (2023) - [i214]Brandon Trabucco, Kyle Doherty, Max Gurinas, Ruslan Salakhutdinov:
Effective Data Augmentation With Diffusion Models. CoRR abs/2302.07944 (2023) - [i213]Paul Pu Liang, Yun Cheng, Xiang Fan, Chun Kai Ling, Suzanne Nie, Richard J. Chen, Zihao Deng, Faisal Mahmood, Ruslan Salakhutdinov, Louis-Philippe Morency:
Quantifying & Modeling Feature Interactions: An Information Decomposition Framework. CoRR abs/2302.12247 (2023) - [i212]Yue Wu, So Yeon Min, Yonatan Bisk, Ruslan Salakhutdinov, Amos Azaria, Yuanzhi Li, Tom M. Mitchell, Shrimai Prabhumoye:
Plan, Eliminate, and Track - Language Models are Good Teachers for Embodied Agents. CoRR abs/2305.02412 (2023) - [i211]Yue Wu, Shrimai Prabhumoye, So Yeon Min, Yonatan Bisk, Ruslan Salakhutdinov, Amos Azaria, Tom M. Mitchell, Yuanzhi Li:
SPRING: GPT-4 Out-performs RL Algorithms by Studying Papers and Reasoning. CoRR abs/2305.15486 (2023) - [i210]Murtaza Dalal, Ajay Mandlekar, Caelan Reed Garrett, Ankur Handa, Ruslan Salakhutdinov, Dieter Fox:
Imitating Task and Motion Planning with Visuomotor Transformers. CoRR abs/2305.16309 (2023) - [i209]Jing Yu Koh, Daniel Fried, Ruslan Salakhutdinov:
Generating Images with Multimodal Language Models. CoRR abs/2305.17216 (2023) - [i208]Chongyi Zheng, Benjamin Eysenbach, Homer Walke, Patrick Yin, Kuan Fang, Ruslan Salakhutdinov, Sergey Levine:
Stabilizing Contrastive RL: Techniques for Offline Goal Reaching. CoRR abs/2306.03346 (2023) - [i207]Paul Pu Liang, Yun Cheng, Ruslan Salakhutdinov, Louis-Philippe Morency:
Multimodal Fusion Interactions: A Study of Human and Automatic Quantification. CoRR abs/2306.04125 (2023) - [i206]Paul Pu Liang, Chun Kai Ling, Yun Cheng, Alex Obolenskiy, Yudong Liu, Rohan Pandey, Alex Wilf, Louis-Philippe Morency, Ruslan Salakhutdinov:
Multimodal Learning Without Labeled Multimodal Data: Guarantees and Applications. CoRR abs/2306.04539 (2023) - [i205]Paul Pu Liang, Zihao Deng, Martin Ma, James Zou, Louis-Philippe Morency, Ruslan Salakhutdinov:
Factorized Contrastive Learning: Going Beyond Multi-view Redundancy. CoRR abs/2306.05268 (2023) - [i204]Yutong He, Ruslan Salakhutdinov, J. Zico Kolter:
Localized Text-to-Image Generation for Free via Cross Attention Control. CoRR abs/2306.14636 (2023) - [i203]Paul Pu Liang, Yiwei Lyu, Xiang Fan, Arav Agarwal, Yun Cheng, Louis-Philippe Morency, Ruslan Salakhutdinov:
MultiZoo & MultiBench: A Standardized Toolkit for Multimodal Deep Learning. CoRR abs/2306.16413 (2023) - [i202]Benjamin Eysenbach, Matthieu Geist, Sergey Levine, Ruslan Salakhutdinov:
A Connection between One-Step Regularization and Critic Regularization in Reinforcement Learning. CoRR abs/2307.12968 (2023) - [i201]Kyle Hatch, Benjamin Eysenbach, Rafael Rafailov, Tianhe Yu, Ruslan Salakhutdinov, Sergey Levine, Chelsea Finn:
Contrastive Example-Based Control. CoRR abs/2307.13101 (2023) - [i200]Haitian Sun, William W. Cohen, Ruslan Salakhutdinov:
Answering Ambiguous Questions with a Database of Questions, Answers, and Revisions. CoRR abs/2308.08661 (2023) - [i199]Ted Moskovitz, Aaditya K. Singh, DJ Strouse, Tuomas Sandholm, Ruslan Salakhutdinov, Anca D. Dragan, Stephen McAleer:
Confronting Reward Model Overoptimization with Constrained RLHF. CoRR abs/2310.04373 (2023) - [i198]Minji Yoon, Jing Yu Koh, Bryan Hooi, Ruslan Salakhutdinov:
Multimodal Graph Learning for Generative Tasks. CoRR abs/2310.07478 (2023) - [i197]Chongyi Zheng, Ruslan Salakhutdinov, Benjamin Eysenbach:
Contrastive Difference Predictive Coding. CoRR abs/2310.20141 (2023) - [i196]Shentong Mo, Paul Pu Liang, Russ Salakhutdinov, Louis-Philippe Morency:
MultiIoT: Towards Large-scale Multisensory Learning for the Internet of Things. CoRR abs/2311.06217 (2023) - [i195]Haofei Yu, Paul Pu Liang, Ruslan Salakhutdinov, Louis-Philippe Morency:
MMOE: Mixture of Multimodal Interaction Experts. CoRR abs/2311.09580 (2023) - 2022
- [c206]Yanan Zheng, Jing Zhou, Yujie Qian, Ming Ding, Chonghua Liao, Li Jian, Ruslan Salakhutdinov, Jie Tang, Sebastian Ruder, Zhilin Yang:
FewNLU: Benchmarking State-of-the-Art Methods for Few-Shot Natural Language Understanding. ACL (1) 2022: 501-516 - [c205]Haitian Sun, William W. Cohen, Ruslan Salakhutdinov:
ConditionalQA: A Complex Reading Comprehension Dataset with Conditional Answers. ACL (1) 2022: 3627-3637 - [c204]Yiwei Lyu, Paul Pu Liang, Zihao Deng, Ruslan Salakhutdinov, Louis-Philippe Morency:
DIME: Fine-grained Interpretations of Multimodal Models via Disentangled Local Explanations. AIES 2022: 455-467 - [c203]Samuel Yu
, Peter Wu, Paul Pu Liang, Ruslan Salakhutdinov, Louis-Philippe Morency:
PACS: A Dataset for Physical Audiovisual CommonSense Reasoning. ECCV (37) 2022: 292-309 - [c202]Yuxin Xiao, Paul Pu Liang, Umang Bhatt, Willie Neiswanger, Ruslan Salakhutdinov, Louis-Philippe Morency:
Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysis. EMNLP (Findings) 2022: 7273-7284 - [c201]So Yeon Min, Hao Zhu, Ruslan Salakhutdinov, Yonatan Bisk:
Don't Copy the Teacher: Data and Model Challenges in Embodied Dialogue. EMNLP 2022: 9361-9368 - [c200]Benjamin Eysenbach, Ruslan Salakhutdinov, Sergey Levine:
The Information Geometry of Unsupervised Reinforcement Learning. ICLR 2022 - [c199]So Yeon Min, Devendra Singh Chaplot, Pradeep Kumar Ravikumar, Yonatan Bisk, Ruslan Salakhutdinov:
FILM: Following Instructions in Language with Modular Methods. ICLR 2022 - [c198]Yao-Hung Hubert Tsai, Tianqin Li, Weixin Liu, Peiyuan Liao
, Ruslan Salakhutdinov, Louis-Philippe Morency:
Learning Weakly-supervised Contrastive Representations. ICLR 2022 - [c197]Yao-Hung Hubert Tsai, Tianqin Li, Martin Q. Ma, Han Zhao, Kun Zhang, Louis-Philippe Morency, Ruslan Salakhutdinov:
Conditional Contrastive Learning with Kernel. ICLR 2022 - [c196]Tianjun Zhang, Benjamin Eysenbach, Ruslan Salakhutdinov, Sergey Levine, Joseph E. Gonzalez:
C-Planning: An Automatic Curriculum for Learning Goal-Reaching Tasks. ICLR 2022 - [c195]Tianwei Ni, Benjamin Eysenbach, Ruslan Salakhutdinov:
Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs. ICML 2022: 16691-16723 - [c194]Benjamin Eysenbach, Alexander Khazatsky, Sergey Levine, Ruslan Salakhutdinov:
Mismatched No More: Joint Model-Policy Optimization for Model-Based RL. NeurIPS 2022 - [c193]Benjamin Eysenbach, Soumith Udatha, Russ Salakhutdinov, Sergey Levine:
Imitating Past Successes can be Very Suboptimal. NeurIPS 2022 - [c192]Benjamin Eysenbach, Tianjun Zhang, Sergey Levine, Ruslan Salakhutdinov:
Contrastive Learning as Goal-Conditioned Reinforcement Learning. NeurIPS 2022 - [c191]Minji Yoon, John Palowitch, Dustin Zelle, Ziniu Hu, Ruslan Salakhutdinov, Bryan Perozzi:
Zero-shot Transfer Learning within a Heterogeneous Graph via Knowledge Transfer Networks. NeurIPS 2022 - [c190]Mathis Petrovich, Chao Liang, Ryoma Sato, Yanbin Liu, Yao-Hung Hubert Tsai, Linchao Zhu, Yi Yang, Ruslan Salakhutdinov, Makoto Yamada
:
Feature-Robust Optimal Transport for High-Dimensional Data. ECML/PKDD (5) 2022: 291-307 - [i194]Yao-Hung Hubert Tsai, Tianqin Li, Martin Q. Ma, Han Zhao, Kun Zhang, Louis-Philippe Morency, Ruslan Salakhutdinov:
Conditional Contrastive Learning with Kernel. CoRR abs/2202.05458 (2022) - [i193]Yao-Hung Hubert Tsai, Tianqin Li, Weixin Liu, Peiyuan Liao, Ruslan Salakhutdinov, Louis-Philippe Morency:
Learning Weakly-Supervised Contrastive Representations. CoRR abs/2202.06670 (2022) - [i192]Paul Pu Liang, Yiwei Lyu, Xiang Fan
, Shentong Mo, Dani Yogatama, Louis-Philippe Morency, Ruslan Salakhutdinov:
HighMMT: Towards Modality and Task Generalization for High-Modality Representation Learning. CoRR abs/2203.01311 (2022) - [i191]Yiwei Lyu, Paul Pu Liang, Zihao Deng, Ruslan Salakhutdinov, Louis-Philippe Morency:
DIME: Fine-grained Interpretations of Multimodal Models via Disentangled Local Explanations. CoRR abs/2203.02013 (2022) - [i190]Minji Yoon, John Palowitch, Dustin Zelle, Ziniu Hu, Ruslan Salakhutdinov, Bryan Perozzi:
Zero-shot Domain Adaptation of Heterogeneous Graphs via Knowledge Transfer Networks. CoRR abs/2203.02018 (2022) - [i189]Samuel Yu, Peter Wu, Paul Pu Liang, Ruslan Salakhutdinov, Louis-Philippe Morency:
PACS: A Dataset for Physical Audiovisual CommonSense Reasoning. CoRR abs/2203.11130 (2022) - [i188]Haitian Sun, William W. Cohen, Ruslan Salakhutdinov:
Reasoning over Logically Interacted Conditions for Question Answering. CoRR abs/2205.12898 (2022) - [i187]Benjamin Eysenbach, Soumith Udatha, Sergey Levine, Ruslan Salakhutdinov:
Imitating Past Successes can be Very Suboptimal. CoRR abs/2206.03378 (2022) - [i186]Benjamin Eysenbach, Tianjun Zhang, Ruslan Salakhutdinov, Sergey Levine:
Contrastive Learning as Goal-Conditioned Reinforcement Learning. CoRR abs/2206.07568 (2022) - [i185]Brandon Trabucco, Gunnar A. Sigurdsson, Robinson Piramuthu, Gaurav S. Sukhatme, Ruslan Salakhutdinov:
A Simple Approach for Visual Rearrangement: 3D Mapping and Semantic Search. CoRR abs/2206.13396 (2022) - [i184]Paul Pu Liang, Yiwei Lyu, Gunjan Chhablani, Nihal Jain, Zihao Deng, Xingbo Wang, Louis-Philippe Morency, Ruslan Salakhutdinov:
MultiViz: An Analysis Benchmark for Visualizing and Understanding Multimodal Models. CoRR abs/2207.00056 (2022) - [i183]Minji Yoon, Yue Wu, John Palowitch, Bryan Perozzi, Ruslan Salakhutdinov:
Scalable Privacy-enhanced Benchmark Graph Generative Model for Graph Convolutional Networks. CoRR abs/2207.04396 (2022) - [i182]Raj Ghugare, Homanga Bharadhwaj, Benjamin Eysenbach, Sergey Levine, Ruslan Salakhutdinov:
Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective. CoRR abs/2209.08466 (2022) - [i181]Cheng-Fu Yang, Yao-Hung Hubert Tsai, Wan-Cyuan Fan, Ruslan Salakhutdinov, Louis-Philippe Morency, Yu-Chiang Frank Wang:
Paraphrasing Is All You Need for Novel Object Captioning. CoRR abs/2209.12343 (2022) - [i180]So Yeon Min, Hao Zhu, Ruslan Salakhutdinov, Yonatan Bisk:
Don't Copy the Teacher: Data and Model Challenges in Embodied Dialogue. CoRR abs/2210.04443 (2022) - [i179]Yuxin Xiao, Paul Pu Liang, Umang Bhatt, Willie Neiswanger, Ruslan Salakhutdinov, Louis-Philippe Morency:
Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysis. CoRR abs/2210.04714 (2022) - [i178]Xiang Fan
, Yiwei Lyu, Paul Pu Liang, Ruslan Salakhutdinov, Louis-Philippe Morency:
Nano: Nested Human-in-the-Loop Reward Learning for Few-shot Language Model Control. CoRR abs/2211.05750 (2022) - [i177]So Yeon Min, Yao-Hung Hubert Tsai, Wei Ding, Ali Farhadi, Ruslan Salakhutdinov, Yonatan Bisk, Jian Zhang:
Object Goal Navigation with End-to-End Self-Supervision. CoRR abs/2212.05923 (2022) - [i176]Rohan Pandey, Rulin Shao, Paul Pu Liang, Ruslan Salakhutdinov, Louis-Philippe Morency:
Cross-modal Attention Congruence Regularization for Vision-Language Relation Alignment. CoRR abs/2212.10549 (2022) - 2021
- [j10]Wei-Ning Hsu
, Benjamin Bolte, Yao-Hung Hubert Tsai, Kushal Lakhotia, Ruslan Salakhutdinov, Abdelrahman Mohamed:
HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units. IEEE ACM Trans. Audio Speech Lang. Process. 29: 3451-3460 (2021) - [c189]Ryan Mohr, Allan M. Avila, Soham Ghosh, Ananta Bhattarai, Muqiao Yang, Xintian Feng, Martin Head-Gordon, Ruslan Salakhutdinov, Maria Fonoberova, Igor Mezic:
Combining Programmable Potentials and Neural Networks for Materials Problems. AAAI Spring Symposium: MLPS 2021 - [c188]Paul Pu Liang, Terrance Liu, Anna Cai, Michal Muszynski, Ryo Ishii, Nicholas Allen, Randy Auerbach, David Brent, Ruslan Salakhutdinov, Louis-Philippe Morency:
Learning Language and Multimodal Privacy-Preserving Markers of Mood from Mobile Data. ACL/IJCNLP (1) 2021: 4170-4187 - [c187]Peter Wu, Paul Pu Liang, Jiatong Shi, Ruslan Salakhutdinov, Shinji Watanabe, Louis-Philippe Morency:
Understanding the Tradeoffs in Client-side Privacy for Downstream Speech Tasks. APSIPA ASC 2021: 841-848 - [c186]Wei-Ning Hsu, Yao-Hung Hubert Tsai, Benjamin Bolte, Ruslan Salakhutdinov, Abdelrahman Mohamed:
Hubert: How Much Can a Bad Teacher Benefit ASR Pre-Training? ICASSP 2021: 6533-6537 - [c185]Liangke Gui, Adrien Bardes, Ruslan Salakhutdinov, Alexander Hauptmann, Martial Hebert, Yu-Xiong Wang:
Learning to Hallucinate Examples from Extrinsic and Intrinsic Supervision. ICCV 2021: 8681-8691 - [c184]Benjamin Eysenbach, Shreyas Chaudhari, Swapnil Asawa, Sergey Levine, Ruslan Salakhutdinov:
Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers. ICLR 2021 - [c183]Benjamin Eysenbach, Ruslan Salakhutdinov, Sergey Levine:
C-Learning: Learning to Achieve Goals via Recursive Classification. ICLR 2021 - [c182]Emilio Parisotto, Ruslan Salakhutdinov:
Efficient Transformers in Reinforcement Learning using Actor-Learner Distillation. ICLR 2021 - [c181]Yao-Hung Hubert Tsai, Yue Wu, Ruslan Salakhutdinov, Louis-Philippe Morency:
Self-supervised Learning from a Multi-view Perspective. ICLR 2021 - [c180]Yao-Hung Hubert Tsai, Martin Q. Ma, Muqiao Yang, Han Zhao, Louis-Philippe Morency, Ruslan Salakhutdinov:
Self-supervised Representation Learning with Relative Predictive Coding. ICLR 2021 - [c179]Russ Salakhutdinov:
From Differentiable Reasoning to Self-supervised Embodied Active Learning. ICMI 2021: 5 - [c178]Saurabh Garg, Joshua Zhanson, Emilio Parisotto, Adarsh Prasad, J. Zico Kolter, Zachary C. Lipton, Sivaraman Balakrishnan, Ruslan Salakhutdinov, Pradeep Ravikumar:
On Proximal Policy Optimization's Heavy-tailed Gradients. ICML 2021: 3610-3619 - [c177]Paul Pu Liang, Chiyu Wu, Louis-Philippe Morency, Ruslan Salakhutdinov:
Towards Understanding and Mitigating Social Biases in Language Models. ICML 2021: 6565-6576 - [c176]Peiyuan Liao, Han Zhao, Keyulu Xu, Tommi S. Jaakkola, Geoffrey J. Gordon, Stefanie Jegelka, Ruslan Salakhutdinov:
Information Obfuscation of Graph Neural Networks. ICML 2021: 6600-6610 - [c175]Haitian Sun, Patrick Verga, Bhuwan Dhingra, Ruslan Salakhutdinov, William W. Cohen:
Reasoning Over Virtual Knowledge Bases With Open Predicate Relations. ICML 2021: 9966-9977 - [c174]Ruosong Wang, Yifan Wu, Ruslan Salakhutdinov, Sham M. Kakade:
Instabilities of Offline RL with Pre-Trained Neural Representation. ICML 2021: 10948-10960 - [c173]Yue Wu, Shuangfei Zhai, Nitish Srivastava, Joshua M. Susskind, Jian Zhang, Ruslan Salakhutdinov, Hanlin Goh:
Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning. ICML 2021: 11319-11328 - [c172]Shruti Palaskar, Ruslan Salakhutdinov, Alan W. Black, Florian Metze:
Multimodal Speech Summarization Through Semantic Concept Learning. Interspeech 2021: 791-795 - [c171]Paul Pu Liang, Peter Wu, Ziyin Liu, Louis-Philippe Morency, Ruslan Salakhutdinov:
Cross-Modal Generalization: Learning in Low Resource Modalities via Meta-Alignment. ACM Multimedia 2021: 2680-2689 - [c170]Yiwei Lyu, Paul Pu Liang, Hai Pham, Eduard H. Hovy, Barnabás Póczos, Ruslan Salakhutdinov, Louis-Philippe Morency:
StylePTB: A Compositional Benchmark for Fine-grained Controllable Text Style Transfer. NAACL-HLT 2021: 2116-2138 - [c169]Shrimai Prabhumoye, Brendon Boldt, Ruslan Salakhutdinov, Alan W. Black:
Case Study: Deontological Ethics in NLP. NAACL-HLT 2021: 3784-3798 - [c168]Shrimai Prabhumoye, Kazuma Hashimoto, Yingbo Zhou, Alan W. Black, Ruslan Salakhutdinov:
Focused Attention Improves Document-Grounded Generation. NAACL-HLT 2021: 4274-4287 - [c167]Ben Eysenbach, Sergey Levine, Ruslan Salakhutdinov:
Replacing Rewards with Examples: Example-Based Policy Search via Recursive Classification. NeurIPS 2021: 11541-11552 - [c166]Devendra Singh Chaplot, Murtaza Dalal, Saurabh Gupta, Jitendra Malik, Ruslan Salakhutdinov:
SEAL: Self-supervised Embodied Active Learning using Exploration and 3D Consistency. NeurIPS 2021: 13086-13098 - [c165]Murtaza Dalal, Deepak Pathak, Ruslan Salakhutdinov:
Accelerating Robotic Reinforcement Learning via Parameterized Action Primitives. NeurIPS 2021: 21847-21859 - [c164]Ben Eysenbach, Ruslan Salakhutdinov, Sergey Levine:
Robust Predictable Control. NeurIPS 2021: 27813-27825 - [c163]Paul Pu Liang, Yiwei Lyu, Xiang Fan, Zetian Wu, Yun Cheng, Jason Wu, Leslie Chen, Peter Wu, Michelle A. Lee, Yuke Zhu, Ruslan Salakhutdinov, Louis-Philippe Morency:
MultiBench: Multiscale Benchmarks for Multimodal Representation Learning. NeurIPS Datasets and Benchmarks 2021 - [c162]Yanbin Liu, Makoto Yamada
, Yao-Hung Hubert Tsai, Tam Le, Ruslan Salakhutdinov, Yi Yang:
LSMI-Sinkhorn: Semi-supervised Mutual Information Estimation with Optimal Transport. ECML/PKDD (1) 2021: 655-670 - [i175]Peter Wu, Paul Pu Liang, Ruslan Salakhutdinov, Louis-Philippe Morency:
Understanding the Tradeoffs in Client-Side Privacy for Speech Recognition. CoRR abs/2101.08919 (2021) - [i174]William H. Guss, Mario Ynocente Castro, Sam Devlin, Brandon Houghton, Noboru Sean Kuno, Crissman Loomis, Stephanie Milani, Sharada P. Mohanty, Keisuke Nakata, Ruslan Salakhutdinov, John Schulman, Shinya Shiroshita, Nicholay Topin, Avinash Ummadisingu, Oriol Vinyals:
The MineRL 2020 Competition on Sample Efficient Reinforcement Learning using Human Priors. CoRR abs/2101.11071 (2021) - [i173]Haitian Sun, Pat Verga, Bhuwan Dhingra, Ruslan Salakhutdinov, William W. Cohen:
Reasoning Over Virtual Knowledge Bases With Open Predicate Relations. CoRR abs/2102.07043 (2021) - [i172]Saurabh Garg, Joshua Zhanson, Emilio Parisotto, Adarsh Prasad, J. Zico Kolter, Sivaraman Balakrishnan, Zachary C. Lipton, Ruslan Salakhutdinov, Pradeep Ravikumar:
On Proximal Policy Optimization's Heavy-tailed Gradients. CoRR abs/2102.10264 (2021) - [i171]Ruosong Wang, Yifan Wu, Ruslan Salakhutdinov, Sham M. Kakade:
Instabilities of Offline RL with Pre-Trained Neural Representation. CoRR abs/2103.04947 (2021) - [i170]Yao-Hung Hubert Tsai, Martin Q. Ma, Muqiao Yang, Han Zhao, Louis-Philippe Morency, Ruslan Salakhutdinov:
Self-supervised Representation Learning with Relative Predictive Coding. CoRR abs/2103.11275 (2021) - [i169]Benjamin Eysenbach, Sergey Levine, Ruslan Salakhutdinov:
Replacing Rewards with Examples: Example-Based Policy Search via Recursive Classification. CoRR abs/2103.12656 (2021) - [i168]Emilio Parisotto, Ruslan Salakhutdinov:
Efficient Transformers in Reinforcement Learning using Actor-Learner Distillation. CoRR abs/2104.01655 (2021) - [i167]Yiwei Lyu, Paul Pu Liang, Hai Pham, Eduard H. Hovy, Barnabás Póczos, Ruslan Salakhutdinov, Louis-Philippe Morency:
StylePTB: A Compositional Benchmark for Fine-grained Controllable Text Style Transfer. CoRR abs/2104.05196 (2021) - [i166]Shrimai Prabhumoye, Kazuma Hashimoto, Yingbo Zhou, Alan W. Black, Ruslan Salakhutdinov:
Focused Attention Improves Document-Grounded Generation. CoRR abs/2104.12714 (2021) - [i165]Yao-Hung Hubert Tsai, Shaojie Bai, Louis-Philippe Morency, Ruslan Salakhutdinov:
A Note on Connecting Barlow Twins with Negative-Sample-Free Contrastive Learning. CoRR abs/2104.13712 (2021) - [i164]Yue Wu, Shuangfei Zhai, Nitish Srivastava, Joshua M. Susskind, Jian Zhang, Ruslan Salakhutdinov, Hanlin Goh:
Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning. CoRR abs/2105.08140 (2021) - [i163]Haitian Sun, William W. Cohen, Ruslan Salakhutdinov:
End-to-End Multihop Retrieval for Compositional Question Answering over Long Documents. CoRR abs/2106.00200 (2021) - [i162]Yao-Hung Hubert Tsai, Martin Q. Ma, Han Zhao, Kun Zhang, Louis-Philippe Morency, Ruslan Salakhutdinov:
Conditional Contrastive Learning: Removing Undesirable Information in Self-Supervised Representations. CoRR abs/2106.02866 (2021) - [i161]