Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox
Picture for Osbert Bastani

Osbert Bastani
Alert button

PAC Prediction Sets for Large Language Models of Code


Feb 17, 2023
Adam Khakhar, Stephen Mell, Osbert Bastani

Add code
Alert button

Figure 1 for PAC Prediction Sets for Large Language Models of Code
Figure 2 for PAC Prediction Sets for Large Language Models of Code
Figure 3 for PAC Prediction Sets for Large Language Models of Code
Figure 4 for PAC Prediction Sets for Large Language Models of Code

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Robust Subtask Learning for Compositional Generalization


Feb 06, 2023
Kishor Jothimurugan, Steve Hsu, Osbert Bastani, Rajeev Alur

Add code
Alert button

Figure 1 for Robust Subtask Learning for Compositional Generalization
Figure 2 for Robust Subtask Learning for Compositional Generalization
Figure 3 for Robust Subtask Learning for Compositional Generalization
Figure 4 for Robust Subtask Learning for Compositional Generalization

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

SPARLING: Learning Latent Representations with Extremely Sparse Activations


Feb 03, 2023
Kavi Gupta, Osbert Bastani, Armando Solar-Lezama

Add code
Alert button

Figure 1 for SPARLING: Learning Latent Representations with Extremely Sparse Activations
Figure 2 for SPARLING: Learning Latent Representations with Extremely Sparse Activations
Figure 3 for SPARLING: Learning Latent Representations with Extremely Sparse Activations
Figure 4 for SPARLING: Learning Latent Representations with Extremely Sparse Activations
* 8 pages, 10 figures 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

ACon$^2$: Adaptive Conformal Consensus for Provable Blockchain Oracles


Nov 17, 2022
Sangdon Park, Osbert Bastani, Taesoo Kim

Add code
Alert button

Figure 1 for ACon$^2$: Adaptive Conformal Consensus for Provable Blockchain Oracles
Figure 2 for ACon$^2$: Adaptive Conformal Consensus for Provable Blockchain Oracles
Figure 3 for ACon$^2$: Adaptive Conformal Consensus for Provable Blockchain Oracles
Figure 4 for ACon$^2$: Adaptive Conformal Consensus for Provable Blockchain Oracles

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Decision-Aware Learning for Optimizing Health Supply Chains


Nov 15, 2022
Tsai-Hsuan Chung, Vahid Rostami, Hamsa Bastani, Osbert Bastani

Add code
Alert button

Figure 1 for Decision-Aware Learning for Optimizing Health Supply Chains
Figure 2 for Decision-Aware Learning for Optimizing Health Supply Chains
Figure 3 for Decision-Aware Learning for Optimizing Health Supply Chains
Figure 4 for Decision-Aware Learning for Optimizing Health Supply Chains
* Extended Abstract presented at Machine Learning for Health (ML4H) symposium 2022, November 28th, 2022, New Orleans, United States & Virtual, http://www.ml4h.cc, 8 pages 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Bandits for Online Calibration: An Application to Content Moderation on Social Media Platforms


Nov 11, 2022
Vashist Avadhanula, Omar Abdul Baki, Hamsa Bastani, Osbert Bastani, Caner Gocmen, Daniel Haimovich, Darren Hwang, Dima Karamshuk, Thomas Leeper, Jiayuan Ma, Gregory Macnamara, Jake Mullett, Christopher Palow, Sung Park, Varun S Rajagopal, Kevin Schaeffer, Parikshit Shah, Deeksha Sinha, Nicolas Stier-Moses, Peng Xu

Add code
Alert button

Figure 1 for Bandits for Online Calibration: An Application to Content Moderation on Social Media Platforms
Figure 2 for Bandits for Online Calibration: An Application to Content Moderation on Social Media Platforms
Figure 3 for Bandits for Online Calibration: An Application to Content Moderation on Social Media Platforms

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training


Sep 30, 2022
Yecheng Jason Ma, Shagun Sodhani, Dinesh Jayaraman, Osbert Bastani, Vikash Kumar, Amy Zhang

Add code
Alert button

Figure 1 for VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training
Figure 2 for VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training
Figure 3 for VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training
Figure 4 for VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training
* Project website: https://sites.google.com/view/vip-rl 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

PAC Prediction Sets for Meta-Learning


Jul 06, 2022
Sangdon Park, Edgar Dobriban, Insup Lee, Osbert Bastani

Add code
Alert button

Figure 1 for PAC Prediction Sets for Meta-Learning
Figure 2 for PAC Prediction Sets for Meta-Learning
Figure 3 for PAC Prediction Sets for Meta-Learning
Figure 4 for PAC Prediction Sets for Meta-Learning

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

How Far I'll Go: Offline Goal-Conditioned Reinforcement Learning via $f$-Advantage Regression


Jun 07, 2022
Yecheng Jason Ma, Jason Yan, Dinesh Jayaraman, Osbert Bastani

Add code
Alert button

Figure 1 for How Far I'll Go: Offline Goal-Conditioned Reinforcement Learning via $f$-Advantage Regression
Figure 2 for How Far I'll Go: Offline Goal-Conditioned Reinforcement Learning via $f$-Advantage Regression
Figure 3 for How Far I'll Go: Offline Goal-Conditioned Reinforcement Learning via $f$-Advantage Regression
Figure 4 for How Far I'll Go: Offline Goal-Conditioned Reinforcement Learning via $f$-Advantage Regression
* Project website: https://jasonma2016.github.io/GoFAR/ 
   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Specification-Guided Learning of Nash Equilibria with High Social Welfare


Jun 06, 2022
Kishor Jothimurugan, Suguman Bansal, Osbert Bastani, Rajeev Alur

Add code
Alert button

Figure 1 for Specification-Guided Learning of Nash Equilibria with High Social Welfare
Figure 2 for Specification-Guided Learning of Nash Equilibria with High Social Welfare
Figure 3 for Specification-Guided Learning of Nash Equilibria with High Social Welfare

   Access Paper or Ask Questions
  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
3
4
5
6
>>