Alert button
Picture for Yundi Qian

Yundi Qian

Alert button

Google, Inc

Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models

Add code
Bookmark button
Alert button
Dec 22, 2023
Avi Singh, John D. Co-Reyes, Rishabh Agarwal, Ankesh Anand, Piyush Patil, Xavier Garcia, Peter J. Liu, James Harrison, Jaehoon Lee, Kelvin Xu, Aaron Parisi, Abhishek Kumar, Alex Alemi, Alex Rizkowsky, Azade Nova, Ben Adlam, Bernd Bohnet, Gamaleldin Elsayed, Hanie Sedghi, Igor Mordatch, Isabelle Simpson, Izzeddin Gur, Jasper Snoek, Jeffrey Pennington, Jiri Hron, Kathleen Kenealy, Kevin Swersky, Kshiteej Mahajan, Laura Culp, Lechao Xiao, Maxwell L. Bileschi, Noah Constant, Roman Novak, Rosanne Liu, Tris Warkentin, Yundi Qian, Yamini Bansal, Ethan Dyer, Behnam Neyshabur, Jascha Sohl-Dickstein, Noah Fiedel

Figure 1 for Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models
Figure 2 for Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models
Figure 3 for Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models
Figure 4 for Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models
Viaarxiv icon

Frontier Language Models are not Robust to Adversarial Arithmetic, or "What do I need to say so you agree 2+2=5?

Add code
Bookmark button
Alert button
Nov 15, 2023
C. Daniel Freeman, Laura Culp, Aaron Parisi, Maxwell L Bileschi, Gamaleldin F Elsayed, Alex Rizkowsky, Isabelle Simpson, Alex Alemi, Azade Nova, Ben Adlam, Bernd Bohnet, Gaurav Mishra, Hanie Sedghi, Igor Mordatch, Izzeddin Gur, Jaehoon Lee, JD Co-Reyes, Jeffrey Pennington, Kelvin Xu, Kevin Swersky, Kshiteej Mahajan, Lechao Xiao, Rosanne Liu, Simon Kornblith, Noah Constant, Peter J. Liu, Roman Novak, Yundi Qian, Noah Fiedel, Jascha Sohl-Dickstein

Figure 1 for Frontier Language Models are not Robust to Adversarial Arithmetic, or "What do I need to say so you agree 2+2=5?
Figure 2 for Frontier Language Models are not Robust to Adversarial Arithmetic, or "What do I need to say so you agree 2+2=5?
Figure 3 for Frontier Language Models are not Robust to Adversarial Arithmetic, or "What do I need to say so you agree 2+2=5?
Figure 4 for Frontier Language Models are not Robust to Adversarial Arithmetic, or "What do I need to say so you agree 2+2=5?
Viaarxiv icon

MLGO: a Machine Learning Guided Compiler Optimizations Framework

Add code
Bookmark button
Alert button
Jan 13, 2021
Mircea Trofin, Yundi Qian, Eugene Brevdo, Zinan Lin, Krzysztof Choromanski, David Li

Figure 1 for MLGO: a Machine Learning Guided Compiler Optimizations Framework
Figure 2 for MLGO: a Machine Learning Guided Compiler Optimizations Framework
Figure 3 for MLGO: a Machine Learning Guided Compiler Optimizations Framework
Figure 4 for MLGO: a Machine Learning Guided Compiler Optimizations Framework
Viaarxiv icon