CINXE.COM
Ruslan Salakhutdinov
<html xmlns="http://www.w3.org/1999/xhtml"> <head> <meta http-equiv="Content-Type" content="text/html; charset=UTF-8" /> <title>Ruslan Salakhutdinov</title> <link href="defaultstyles_home.css" rel="stylesheet" media="screen" /> <script type="text/javascript" src="bbranding.js"></script> <script type="text/JavaScript" src="http://www.colorado.edu/templates/faculty-template/js/curvycorners.js"></script> </head> <body> <div id="container"> <div id="uucb"><script type="text/javascript">ucbheader();</script></div> <div id="wrapper"> <div id="banner"> <h1>Ruslan Salakhutdinov</h1> <p> Machine Learning Department </p> </div> <div id="nav"> <ul> <li><a href="index.html">Home</a></li> <li><a href="bio.html">Bio</a></li> <li><a href="publications.html">Publications</a></li> <li><a href="people.html">People</a></li> <li><a href="teaching.html">Teaching</a></li> <li><a href="software.html">Software</a></li> <li><a href="FAQ.html">FAQ</a></li> <li><a href="contact.html">Contact</a></li> </ul> </div> <div id="page"> <div id="content"> <div id="contentbar" class="contentbar1"> <img src="RS_pic.jpg" height="200" title="Ruslan Salakhutdinov" id="fac_photo"/> <h3>Ruslan Salakhutdinov</h3> <p> Professor<br /> <a href="http://research.microsoft.com/en-US/collaboration/awards/msrff.aspx#2013"> Microsoft Faculty Fellow </a><br /> <a href="http://www.sloan.org/sloan-research-fellowships/"> Sloan Fellow </a> <br /> Carnegie Mellon University <br /> rsalakhu[at]cs.cmu.edu<br /> <a href="cv_web.pdf">CV</a> <a href="http://scholar.google.ca/citations?user=ITZ1e7MAAAAJ&hl=en"> Google Scholar</a> <br> <a href="https://twitter.com/rsalakhu"> <img src="images/twitter.png" height="20"></a> <a href="https://plus.google.com/u/0/113287594837124162533/"> <img src="images/g_plus.png" height="20"></a> <a href="https://www.facebook.com/russ.salakhutdinov"> <img src="images/fb.jpg" height="20"></a> </div> <p> I am a UPMC professor of Computer Science in the <a href="http://www.ml.cmu.edu/"> Machine Learning Department</a>, <a href="https://www.scs.cmu.edu/"> School of Computer Science </a> at Carnegie Mellon University. I work in the field of statistical machine learning (See my <a href="cv_web.pdf">CV</a>.) <br> <p> My research interests include Deep Learning, Probabilistic Graphical Models, and Large-scale Optimization. <br> <p> <b> Prospective students:</b> Please <a href="FAQ.html"> read this </a> to ensure that I read your email. <br> <br> <h3> <b> Recent Research Highlights: </b> </h3> <ul> <li> 4 part Deep Learning Tutorial at the Simons Institute, Berkeley <br> Part 1:[<a href="talk_Simons_part1_pdf.pdf">Slides (pdf)</a>], Part 2:[<a href="talk_Simons_part2_pdf.pdf">Slides (pdf)</a>], Part 3:[<a href="talk_Simons_part3_pdf.pdf">Slides (pdf)</a>], Part 4:[<a href="talk_Simons_part4_pdf.pdf">Slides (pdf)</a>]. <br> <br> <li> Deep Learning Tutorial, MLSS, Tübingen, Germany <br> Part 1:[<a href="talk_MLSS_part1.pdf">Slides (pdf)</a>], Part 2:[<a href="talk_MLSS_part2.pdf">Slides (pdf)</a>]. <br> <br> <br> <br> <br> <br> <br> <br> <h3> <b> Recent Papers: </b> </h3> <ul> <li> <img src="images/newz.gif"> <b> VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks </b> <br> Jing Yu Koh, Robert Lo, Lawrence Jang, Vikram Duvvur, Ming Chong Lim, Po-Yu Huang, Graham Neubig, Shuyan Zhou, Ruslan Salakhutdinov, Daniel Fried <br> ACL 2014 [<a href="https://arxiv.org/abs/2401.13649/">arXiv</a>] [<a href="https://jykoh.com/vwa/">Code</a>] <p> <li> <img src="images/newz.gif"> <b> Plan-Seq-Learn: Language Model Guided RL for Solving Long Horizon Robotics Tasks, </b> <br> Murtaza Dalal, Tarun Chiruvolu, Devendra Chaplot, Ruslan Salakhutdinov <br> ICLR 2024 [<a href="https://mihdalal.github.io/planseqlearn/">arXiv</a>] [<a href="https://mihdalal.github.io/planseqlearn/">Code</a>] <p> <li> <img src="images/newz.gif"> <b> Effective Data Augmentation With Diffusion Models </b> <br> Brandon Trabucco, Kyle Doherty, Max Gurinas, Ruslan Salakhutdinov <br> ICLR 2024 [<a href="https://arxiv.org/abs/2302.07944">arXiv</a>] [<a href="https://github.com/brandontrabucco/da-fusion">code</a>] <p> <li> <img src="images/newz.gif"> <b> Multimodal Learning Without Labeled Multimodal Data: Guarantees and Applications </b> <br> Paul Pu Liang, Chun Kai Ling, Yun Cheng, Alex Obolenskiy, Yudong Liu, Rohan Pandey, Alex Wilf, Louis-Philippe Morency, Ruslan Salakhutdinov <br> ICLR 2024 [<a href="https://arxiv.org/abs/2306.04539">arXiv</a>] [<a href="https://github.com/pliang279/PID">code</a>] <p> <li> <img src="images/newz.gif"> <b> Contrastive Difference Predictive Coding </b> <br> Chongyi Zheng, Ruslan Salakhutdinov, Benjamin Eysenbach <br> ICLR 2024 [<a href="https://arxiv.org/abs/2310.20141">arXiv</a>] [<a href="https://chongyi-zheng.github.io/td_infonce/">code</a>] <p> <li> <img src="images/newz.gif"> <b> Manifold Preserving Guided Diffusion </b> <br> Yutong He, Naoki Murata, Chieh-Hsin Lai, Yuhta Takida, Toshimitsu Uesaka, Dongjun Kim♨, Wei-Hsiang Liao, Yuki Mitsufuji, Zico Kolter, Ruslan Salakhutdinov, Stefano Ermon <br> ICLR 2024 [<a href="https://arxiv.org/abs//2311.16424">arXiv</a>] [<a href="https://kellyyutonghe.github.io/mpgd/">code</a>] <p> <li> <img src="images/newz.gif"> <b> Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Data </b> <br> Chongyi Zheng, Benjamin Eysenbach, Homer Walke, Patrick Yin, Kuan Fang, Ruslan Salakhutdinov, Sergey Levine <br> ICLR 2024 [<a href="https://arxiv.org/abs/2306.03346">arXiv</a>] [<a href="https://chongyi-zheng.github.io/stable_contrastive_rl/">code</a>] <p> <li> <img src="images/newz.gif"> <b> Confronting Reward Model Overoptimization with Constrained RLHF </b> <br> Ted Moskovitz, Aaditya K. Singh, DJ Strouse, Tuomas Sandholm, Ruslan Salakhutdinov, Anca D. Dragan, Stephen McAleer <br> ICLR 2024 [<a href="https://arxiv.org/abs/2310.04373">arXiv</a>] <p> <li> <img src="images/newz.gif"> <b> Generating Images with Multimodal Language Models </b> <br> Jing Yu Koh, Daniel Fried, Ruslan Salakhutdinov <br> NeurIPS 2023, [<a href="https://arxiv.org/abs/2305.17216">arXiv</a>] [<a href="https://jykoh.com/gill">code</a>] <p> <li> <img src="images/newz.gif"> <b> Factorized Contrastive Learning: Going Beyond Multi-view Redundancy </b> <br> Paul Pu Liang*, Zihao Deng*, Martin Ma*, James Zou, Louis-Philippe Morency, Ruslan Salakhutdinov <br> NeurIPS 2023, [<a href="https://arxiv.org/abs/2306.05268">arXiv</a>] [<a href="https://github.com/pliang279/FactorCL">code</a>] <p> <li> <img src="images/newz.gif"> <b> Quantifying & Modeling Feature Interactions: An Information Decomposition Framework </b> <br> Paul Pu Liang, Yun Cheng, Xiang Fan, Chun Kai Ling, Suzanne Nie, Richard Chen, Zihao Deng, Nicholas Allen, Randy Auerbach, Faisal Mahmood, Ruslan Salakhutdinov, Louis-Philippe Morency <br> NeurIPS 2023, [<a href="https://arxiv.org/abs/2302.12247">arXiv</a>] [<a href="https://github.com/pliang279/PID">code</a>] <p> <li> <img src="images/newz.gif"> <b> Imitating Task and Motion Planning with Visuomotor Transformers </b> <br> Murtaza Dalal*, Ajay Mandlekar, Caelan Garrett, Ankur Handa, Ruslan Salakhutdinov, Dieter Fox <br> CoRL 2023, [<a href="https://arxiv.org/abs/2305.16309">arXiv</a>] [<a href="https://mihdalal.github.io/optimus/">code</a>] <p> <li> <img src="images/newz.gif"> <b> Graph Generative Model for Benchmarking Graph Neural Networks </b> <br> Minji Yoon, Yue Wu, John Palowitch, Bryan Perozzi, Russ Salakhutdinov <br> ICML 2023 [<a href="https://arxiv.org/abs/2207.04396">arXiv</a>] <p> <li> <img src="images/newz.gif"> <b> A Connection between One-Step RL and Critic Regularization in Reinforcement Learning </b> <br> Benjamin Eysenbach, Matthieu Geist, Sergey Levine, and Ruslan Salakhutdinov <br> ICML 2023 [<a href="https://proceedings.mlr.press/v202/eysenbach23a.html">arXiv</a>] <p> <li> <img src="images/newz.gif"> <b> Grounding Language Models to Images for Multimodal Inputs and Outputs </b> <br> Jing Yu Koh, Ruslan Salakhutdinov, Daniel Fried <br> ICML 2023 [<a href="https://arxiv.org/abs/2301.13823">arXiv</a>] [<a href="https://jykoh.com/fromage">code</a>] <p> <li> <img src="images/newz.gif"> <b> Multimodal Fusion Interactions: A Study of Human and Automatic Quantification </b> <br> Paul Pu Liang, Yun Cheng, Ruslan Salakhutdinov, Louis-Philippe Morency <br> ICMI 2023 [<a href="https://arxiv.org/abs/2306.04125">arXiv</a>] [<a href="https://github.com/pliang279/PID">code</a>] <p> <p> </ul> </div> </div> </div> <div id="footer"> <script type="text/javascript">ucbfooter();</script> © Carnegie Mellon University </div> </div> </body> </html>