The Eleventh International Conference on Knowing Representations (ICLR 2023) is being held today as a hybrid occasion in Kigali, Rwanda. We are happy to be a Diamond Sponsor of ICLR 2023, a leading conference on deep knowing, where Google scientists contribute at all levels. This year we exist over 100 documents and are actively associated with arranging and hosting a variety of various occasions, consisting of workshops and interactive sessions.
If you’re signed up for ICLR 2023, we hope you’ll check out the Google cubicle to find out more about the amazing work we’re doing throughout subjects covering representation and support knowing, theory and optimization, social effect, security and personal privacy, and applications from generative AI to speech and robotics. Continue listed below to discover the lots of methods which Google scientists are engaged at ICLR 2023, consisting of workshops, documents, posters and talks (Google associations in strong).
Board and Organizing Committee
Board Members consist of: Shakir Mohamed, Tara Sainath
Senior Program Chairs consist of: Been Kim
Workshop Chairs consist of: Aisha Walcott-Bryant, Rose Yu
Variety, Equity & & Addition Chairs consist of: Rosanne Liu
Impressive Paper awards
Development of Maps in the Memories of Blind Navigation Agents
Erik Wijmans, Manolis Savva, Irfan Essa, Stefan Lee, Ari S. Morcos, Dhruv Batra
DreamFusion: Text-to-3D Utilizing 2D Diffusion
Ben Poole, Ajay Jain, Jonathan T. Barron, Ben Mildenhall
Keynote speaker
Found Out Optimizers: Why They’re the Future, Why They’re Tough, and What They Can Do Now
Jascha Sohl-Dickstein.
Workshops
Kaggle@ICLR 2023: ML Solutions in Africa
Organizers consist of: Julia Elliott, Phil Culliton, Ray Harvey.
Facilitators: Julia Elliot, Walter Reade.
Reincarnating Support Knowing (Reincarnating RL).
Organizers consist of: Rishabh Agarwal, Ted Xiao, Max Schwarzer.
Speakers consist of: Sergey Levine.
Panelists consist of: Marc G. Bellemare, Sergey Levine.
Trustworthy and Reliable Large-Scale Artificial Intelligence Designs
Organizers consist of: Sanmi Koyejo.
Speakers consist of: Nicholas Carlini.
Physics for Artificial Intelligence (Physics4ML).
Speakers consist of: Yasaman Bahri.
AI for Agent-Based Modelling Neighborhood (AI4ABM).
Organizers consist of: Pablo Samuel Castro.
Mathematical and Empirical Comprehending of Structure Designs (ME-FoMo).
Organizers consist of: Mathilde Caron, Tengyu Ma, Hanie Sedghi.
Speakers consist of: Yasaman Bahri, Yann Dauphin.
Neurosymbolic Generative Designs 2023 (NeSy-GeMs).
Organizers consist of: Kevin Ellis.
Speakers consist of: Daniel Tarlow, Tuan Anh Le.
What Do We Required for Effective Domain Generalization?
Panelists consist of: Boqing Gong.
The fourth Workshop on Practical ML for Establishing Nations: Knowing Under Limited/Low Resource Settings
Keynote Speaker: Adji Bousso Dieng.
Artificial Intelligence for Remote Sensing
Speakers consist of: Abigail Annkah.
Multimodal Representation Knowing (MRL): Benefits and Risks
Organizers consist of: Petra Poklukar.
Speakers consist of: Arsha Nagrani.
Risks of Limited Data and Calculation for Trustworthy ML
Organizers consist of: Prateek Jain.
Speakers consist of: Nicholas Carlini, Praneeth Netrapalli.
Sparsity in Neural Networks: On Practical Limitations and Tradeoffs In Between Sustainability and Performance
Organizers consist of: Trevor Wind, Utku Evci.
Speakers consist of: Aakanksha Chowdhery, Jeff Dean.
Time Series Representation Knowing for Health
Speakers consist of: Katherine Heller.
Deep Knowing for Code (DL4C).
Organizers consist of: Gabriel Orlanski.
Speakers consist of: Alex Polozov, Daniel Tarlow.
Affinity Workshops
Tiny Documents Display Day (a DEI effort).
Organizers consist of: Rosanne Liu.
Documents
Evolve Efficiently, Fit Regularly: Knowing Smooth Hidden Characteristics for Advection-Dominated Systems
Zhong Yi Wan, Leonardo Zepeda-Nunez, Anudhyan Boral, Fei Sha.
Measuring Memorization Throughout Neural Language Designs
Nicholas Carlini, Daphne Ippolito, Matthew Jagielski, Katherine Lee, Florian Tramer, Chiyuan Zhang.
Development of Maps in the Memories of Blind Navigation Agents ( Impressive Paper Award).
Erik Wijmans, Manolis Savva, Irfan Essa, Stefan Lee, Ari S. Morcos, Dhruv Batra.
Offline Q-Learning on Diverse Multi-task Data Both Scales and Generalizes ( see post)
Aviral Kumar, Rishabh Agarwal, Xingyang Geng, George Tucker, Sergey Levine.
ReAct: Synergizing Thinking and Performing in Language Designs ( see post)
Shunyu Yao *, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik R. Narasimhan, Yuan Cao.
Prompt-to-Prompt Image Modifying with Cross-Attention Control
Amir Hertz, Ron Mokady, Jay Tenenbaum, Kfir Aberman, Yael Pritch, Daniel Cohen-Or.
DreamFusion: Text-to-3D Utilizing 2D Diffusion ( Impressive Paper Award).
Ben Poole, Ajay Jain, Jonathan T. Barron, Ben Mildenhall.
A System for Morphology-Task Generalization through Unified Representation and Habits Distillation
Hiroki Furuta, Yusuke Iwasawa, Yutaka Matsuo, Shixiang Shane Gu.
Sample-Efficient Support Knowing by Breaking the Replay Ratio Barrier
Pierluca D’Oro, Max Schwarzer, Evgenii Nikishin, Pierre-Luc Bacon, Marc G Bellemare, Aaron Courville.
Dichotomy of Control: Separating What You Can Manage from What You Can not
Sherry Yang, Dale Schuurmans, Pieter Abbeel, Ofir Nachum.
Quick and Exact: Changing Preparation Horizon with Adaptive Subgoal Browse
MichaÅ Zawalski, MichaÅ Tyrolski, Konrad Czechowski, Tomasz Odrzygóźdź, Damian Stachura, Piotr Piekos, Yuhuai Wu, Åukasz Kucinski, Piotr MiÅos.
The Compromise In Between Universality and Label Performance of Representations from Contrastive Knowing
Zhenmei Shi, Jiefeng Chen, Kunyang Li, Jayaram Raghuram, Xi Wu, Yingyu Liang, Somesh Jha.
Sparsity-Constrained Ideal Transportation
Tianlin Liu *, Joan Puigcerver, Mathieu Blondel.
Unmasking the Lottery Game Ticket Hypothesis: What’s Encoded in a Winning Ticket’s Mask?
Mansheej Paul, Feng Chen, Brett W. Larsen, Jonathan Frankle, Surya Ganguli, Gintare Karolina Dziugaite.
Severe Q-Learning: MaxEnt RL without Entropy
Divyansh Garg, Joey Hejna, Matthieu Geist, Stefano Ermon.
Draft, Sketch, and Prove: Assisting Official Theorem Provers with Casual Evidence
Albert Qiaochu Jiang, Sean Welleck, Jin Peng Zhou, Timothee Lacroix, Jiacheng Liu, Wenda Li, Mateja Jamnik, Guillaume Lample, Yuhuai Wu.
SimPer: Easy Self-Supervised Knowing of Periodic Targets
Yuzhe Yang, Xin Liu, Jiang Wu, Silviu Borac, Dina Katabi, Ming-Zher Poh, Daniel McDuff.
Socratic Designs: Making Up Zero-Shot Multimodal Thinking with Language
Andy Zeng, Maria Attarian, Brian Ichter, Krzysztof Marcin Choromanski, Adrian Wong, Stefan Welker, Federico Tombari, Aveek Purohit, Michael S. Ryoo, Vikas Sindhwani, Johnny Lee, Vincent Vanhoucke, Pete Florence.
What Knowing Algorithm Is In-Context Knowing? Examinations with Linear Designs
Ekin Akyurek *, Dale Schuurmans, Jacob Andreas, Tengyu Ma *, Denny Zhou.
Choice Transformer: Designing Human Preferences Utilizing Transformers for RL
Changyeon Kim, Jongjin Park, Jinwoo Shin, Honglak Lee, Pieter Abbeel, Kimin Lee.
Iterative Spot Choice for High-Resolution Image Acknowledgment
Benjamin Bergner, Christoph Lippert, Aravindh Mahendran.
Open-Vocabulary Item Detection upon Frozen Vision and Language Designs
Weicheng Kuo, Yin Cui, Xiuye Gu, AJ Piergiovanni, Anelia Angelova.
( Licensed!!) Adversarial Effectiveness totally free!
Nicholas Carlini, Florian Tramér, Krishnamurthy (Dj) Dvijotham, Leslie Rice, Mingjie Sun, J. Zico Kolter.
REPAIR WORK: REnormalizing Permuted Activations for Interpolation Repair Work
Keller Jordan, Hanie Sedghi, Olga Saukh, Rahim Entezari, Behnam Neyshabur.
Discrete Predictor-Corrector Diffusion Designs for Image Synthesis
José Lezama, Tim Salimans, Lu Jiang, Huiwen Chang, Jonathan Ho, Irfan Essa.
Function Restoration From Outputs Can Reduce Simpleness Predisposition in Neural Networks
Sravanti Addepalli, Anshul Nasery, Praneeth Netrapalli, Venkatesh Babu R., Prateek Jain.
A Specific Poly-time Membership-Queries Algorithm for Drawing Out a Three-Layer ReLU Network
Amit Daniely, Elad Granot.
Language Designs Are Multilingual Chain-of-Thought Reasoners
Freda Shi, Mirac Suzgun, Markus Freitag, Xuezhi Wang, Suraj Srivats, Soroush Vosoughi, Hyung Won Chung, Yi Tay, Sebastian Ruder, Denny Zhou, Dipanjan Das, Jason Wei.
Scaling Forward Gradient with Regional Losses
Mengye Ren *, Simon Kornblith, Renjie Liao, Geoffrey Hinton.
Treeformer: Thick Gradient Trees for Effective Attention Calculation
Lovish Madaan, Srinadh Bhojanapalli, Himanshu Jain, Prateek Jain.
LilNetX: Lightweight Networks with EXtreme Design Compression and Structured Sparsification
Sharath Girish, Kamal Gupta, Saurabh Singh, Abhinav Shrivastava.
DiffusER: Diffusion through Edit-Based Restoration
Machel Reid, Vincent J. Hellendoorn, Graham Neubig.
Leveraging Unlabeled Data to Track Memorization
Mahsa Forouzesh, Hanie Sedghi, Patrick Thiran.
A Mixture-of-Expert Technique to RL-Based Discussion Management
Yinlam Chow, Aza Tulepbergenov, Ofir Nachum, Dhawal Gupta, Moonkyung Ryu, Mohammad Ghavamzadeh, Craig Boutilier.
Easy Differentially Personal Direct Regression
Kareem Amin, Matthew Joseph, Monica Ribero, Sergei Vassilvitskii.
KwikBucks: Connection Clustering with Cheap-Weak and Expensive-Strong Signals
Sandeep Silwal *, Sara Ahmadian, Andrew Nystrom, Andrew McCallum, Deepak Ramachandran, Mehran Kazemi.
Enormously Scaling Heteroscedastic Classifiers
Mark Collier, Rodolphe Jenatton, Basil Mustafa, Neil Houlsby, Jesse Berent, Effrosyni Kokiopoulou.
The Lazy Nerve Cell Phenomenon: On Development of Activation Sparsity in Transformers
Zonglin Li, Chong You, Srinadh Bhojanapalli, Daliang Li, Ankit Singh Rawat, Sashank J. Reddi, Ke Ye, Felix Chern, Felix Yu, Ruiqi Guo, Sanjiv Kumar.
Compositional Semantic Parsing with Big Language Designs
Andrew Drozdov, Nathanael Scharli, Ekin Akyurek, Nathan Scales, Xinying Tune, Xinyun Chen, Olivier Bousquet, Denny Zhou.
Very Easy Activation Forming for Out-of-Distribution Detection
Andrija Djurisic, Nebojsa Bozanic, Arjun Ashok, Rosanne Liu.
Long Variety Language Modeling through Gated State Spaces
Extreme Mehta, Ankit Gupta, Ashok Cutkosky, Behnam Neyshabur.
Examining Multi-task Pretraining and Generalization in Support Knowing
Adrien Ali Taiga, Rishabh Agarwal, Jesse Farebrother, Aaron Courville, Marc G. Bellemare.
Knowing Low Dimensional State Spaces with Overparameterized Recurrent Neural Internet
Edo Cohen-Karlik, Itamar Menuhin-Gruman, Raja Giryes, Nadav Cohen, Amir Globerson.
Weighted Ensemble Self-Supervised Knowing
Yangjun Ruan *, Saurabh Singh, Warren Morningstar, Alexander A. Alemi, Sergey Ioffe, Ian Fischer, Joshua V. Dillon.
Adjusting Series Probability Enhances Conditional Language Generation
Yao Zhao, Misha Khalman, Rishabh Joshi, Shashi Narayan, Mohammad Saleh, Peter J. Liu.
SMART: Sentences as Standard Systems for Text Assessment
Reinald Kim Amplayo, Peter J. Liu, Yao Zhao, Shashi Narayan.
Leveraging Value Weights in Subset Choice
Gui Citovsky, Giulia DeSalvo, Sanjiv Kumar, Srikumar Ramalingam, Afshin Rostamizadeh, Yunjuan Wang *.
Proto-Value Networks: Scaling Representation Knowing with Auxiliary Tasks
Jesse Farebrother, Joshua Greaves, Rishabh Agarwal, Charline Le Lan, Ross Goroshin, Pablo Samuel Castro, Marc G. Bellemare.
An Extensible Multi-modal Multi-task Item Dataset with Products
Trevor Standley, Ruohan Gao, Dawn Chen, Jiajun Wu, Silvio Savarese.
Determining Forgetting of Remembered Training Examples
Matthew Jagielski, Om Thakkar, Florian Tramér, Daphne Ippolito, Katherine Lee, Nicholas Carlini, Eric Wallace, Shuang Tune, Abhradeep Thakurta, Nicolas Papernot, Chiyuan Zhang.
Bidirectional Language Designs Are Likewise Few-Shot Students
Ajay Patel, Bryan Li, Mohammad Sadegh Rasooli, Noah Continuous, Colin Raffel, Chris Callison-Burch.
Is Attention All That NeRF Requirements?
Mukund Varma T., Peihao Wang, Xuxi Chen, Tianlong Chen, Subhashini Venugopalan, Zhangyang Wang.
Automating Nearest Next-door Neighbor Browse Setup with Constrained Optimization
Philip Sun, Ruiqi Guo, Sanjiv Kumar.
Fixed Forecast of Runtime Mistakes by Discovering to Perform Programs with External Resource Descriptions
David Bieber, Rishab Goel, Daniel Zheng, Hugo Larochelle, Daniel Tarlow.
Making Up Ensembles of Pre-trained Designs through Iterative Agreement
Shuang Li, Yilun Du, Joshua B. Tenenbaum, Antonio Torralba, Igor Mordatch.
Î-DARTS: Reducing Efficiency Collapse by Balancing Operation Choice Amongst Cells
Sajad Movahedi, Melika Adabinejad, Ayyoob Imani, Arezou Keshavarz, Mostafa Dehghani, Azadeh Shakery, Babak N. Araabi.
Blurring Diffusion Designs
Emiel Hoogeboom, Tim Salimans.
Part-Based Designs Enhance Adversarial Effectiveness
Chawin Sitawarin, Kornrapat Pongmala, Yizheng Chen, Nicholas Carlini, David Wagner.
Knowing in Temporally Structured Environments
Matt Jones, Tyler R. Scott, Mengye Ren, Gamaleldin ElSayed, Katherine Hermann, David Mayo, Michael C. Mozer.
SlotFormer: Not Being Watched Visual Characteristics Simulation with Object-Centric Designs
Ziyi Wu, Nikita Dvornik, Klaus Greff, Thomas Kipf, Animesh Garg.
Robust Algorithms on Adaptive Inputs from Bounded Foes
Yeshwanth Cherapanamjeri, Sandeep Silwal, David P. Woodruff, Fred Zhang, Qiuyi (Richard) Zhang, Samson Zhou.
Agnostic Knowing of General ReLU Activation Utilizing Gradient Descent
Pranjal Awasthi, Alex Tang, Aravindan Vijayaraghavan.
Analog Bits: Getting Discrete Data Utilizing Diffusion Designs with Self-Conditioning
Ting Chen, Ruixiang Zhang, Geoffrey Hinton.
Any-Scale Balanced Samplers for Discrete Area
Haoran Sun *, Bo Dai, Charles Sutton, Dale Schuurmans, Hanjun Dai.
Enhancement with Forecast: Towards an Efficient and Effective Information Enhancement Paradigm for Distillation
Ziqi Wang *, Yuexin Wu, Frederick Liu, Daogao Liu, Le Hou, Hongkun Yu, Jing Li, Heng Ji.
Beyond Lipschitz: Sharp Generalization and Excess Danger Bounds for Full-Batch GD
Konstantinos E. Nikolakakis, Farzin Haddadpour, Amin Karbasi, Dionysios S. Kalogerias.
Causal Evaluation for Text Information with (Obvious) Overlap Infractions
Lin Gui, Victor Veitch.
Contrastive Knowing Can Discover an Ideal Basis for Around View-Invariant Functions
Daniel D. Johnson, Ayoub El Hanchi, Chris J. Maddison.
Differentially Personal Adaptive Optimization with Postponed Preconditioners
Tian Li, Manzil Zaheer, Ziyu Liu, Sashank Reddi, Brendan McMahan, Virginia Smith.
Distributionally Robust Post-hoc Classifiers Under Previous Shifts
Jiaheng Wei *, Harikrishna Narasimhan, Ehsan Amidst, Wen-Sheng Chu, Yang Liu, Abhishek Kumar.
Human Positioning of Neural Network Representations
Lukas Muttenthaler, Jonas Dippel, Lorenz Linhardt, Robert A. Vandermeulen, Simon Kornblith.
Implicit Predisposition in Leaky ReLU Networks Trained on High-Dimensional Data
Spencer Frei, Gal Vardi, Peter Bartlett, Nathan Srebro, Wei Hu.
Koopman Neural Operator Forecaster for Time-Series with Temporal Distributional Shifts
Rui Wang *, Yihe Dong, Sercan Ã. Arik, Rose Yu.
Hidden Variable Representation for Support Knowing
Tongzheng Ren, Chenjun Xiao, Tianjun Zhang, Na Li, Zhaoran Wang, Sujay Sanghavi, Dale Schuurmans, Bo Dai.
Least-to-Most Prompting Makes It Possible For Complex Thinking in Big Language Designs
Denny Zhou, Nathanael Scharli, Le Hou, Jason Wei, Nathan Scales, Xuezhi Wang, Dale Schuurmans, Claire Cui, Olivier Bousquet, Quoc Le, Ed Chi.
Mind’s Eye: Grounded Language Design Thinking Through Simulation
Ruibo Liu, Jason Wei, Shixiang Shane Gu, Te-Yen Wu, Soroush Vosoughi, Claire Cui, Denny Zhou, Andrew M. Dai.
MOAT: Rotating Mobile Convolution and Attention Brings Strong Vision Designs
Chenglin Yang *, Siyuan Qiao, Qihang Yu, Xiaoding Yuan, Yukun Zhu, Alan Yuille, Hartwig Adam, Liang-Chieh Chen.
Unique View Synthesis with Diffusion Designs
Daniel Watson, William Chan, Ricardo Martin-Brualla, Jonathan Ho, Andrea Tagliasacchi, Mohammad Norouzi
On Accelerated Perceptrons and Beyond
Guanghui Wang, Rafael Hanashiro, Etash Guha, Jacob Abernethy.
On Compositional Unpredictability Metrology for Seq2seq Chart Parsing
Zi Lin *, Du Phan, Panupong Pasupat, Jeremiah Liu, Jingbo Shang.
On the Effectiveness of Safe Support Knowing Under Observational Perturbations
Zuxin Liu, Zijian Guo, Zhepeng Cen, Huan Zhang, Jie Tan, Bo Li, Ding Zhao.
Online Low Rank Matrix Conclusion
Prateek Jain, Soumyabrata Buddy.
Out-of-Distribution Detection and Selective Generation for Conditional Language Designs
Jie Ren, Jiaming Luo, Yao Zhao, Kundan Krishna *, Mohammad Saleh, Balaji Lakshminarayanan, Peter J. Liu.
PaLI: A Jointly-Scaled Multilingual Language-Image Design
Xi Chen, Xiao Wang, Soravit Changpinyo, AJ Piergiovanni, Piotr Padlewski, Daniel Salz, Sebastian Goodman, Adam Grycner, Basil Mustafa, Lucas Beyer, Alexander Kolesnikov, Joan Puigcerver, Nan Ding, Keran Rong, Hassan Akbari, Gaurav Mishra, Linting Xue, Ashish V. Thapliyal, James Bradbury, Weicheng Kuo, Mojtaba Seyedhosseini, Chao Jia, Burcu Karagol Ayan, Carlos Riquelme Ruiz, Andreas Peter Steiner, Anelia Angelova, Xiaohua Zhai, Neil Houlsby, Radu Soricut.
Phenaki: Variable Length Video Generation from Open Domain Textual Descriptions
Ruben Villegas, Mohammad Babaeizadeh, Pieter-Jan Kindermans, Hernan Moraldo, Han Zhang, Mohammad Taghi Saffar, Santiago Castro *, Julius Kunze *, Dumitru Erhan.
Promptagator: Few-Shot Dense Retrieval from 8 Examples
Zhuyun Dai, Vincent Y. Zhao, Ji Ma, Yi Luan, Jianmo Ni, Jing Lu, Anton Bakalov, Kelvin Guu, Keith B. Hall, Ming-Wei Chang.
Pressing the Accuracy-Group Effectiveness Frontier with Reflective Self-Play
Jeremiah Zhe Liu, Krishnamurthy Dj Dvijotham, Jihyeon Lee, Quan Yuan, Balaji Lakshminarayanan, Deepak Ramachandran.
Re-Imagen: Retrieval-Augmented Text-to-Image Generator
Wenhu Chen, Hexiang Hu, Chitwan Saharia, William W. Cohen.
Recitation-Augmented Language Designs
Zhiqing Sun, Xuezhi Wang, Yi Tay, Yiming Yang, Denny Zhou.
Regression with Label Differential Personal Privacy
Badih Ghazi, Pritish Kamath, Ravi Kumar, Ethan Leeman, Pasin Manurangsi, Avinash Varadarajan, Chiyuan Zhang.
Reviewing the Entropy Semiring for Neural Speech Acknowledgment
Oscar Chang, Dongseong Hwang, Olivier Siohan.
Robust Active Distillation
Cenk Baykal, Khoa Trinh, Fotis Iliopoulos, Gaurav Menghani, Erik Vee.
Score-Based Continuous-Time Discrete Diffusion Designs
Haoran Sun *, Lijun Yu, Bo Dai, Dale Schuurmans, Hanjun Dai.
Self-Consistency Enhances Chain of Idea Thinking in Language Designs
Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed H. Chi, Sharan Narang, Aakanksha Chowdhery, Denny Zhou.
Self-Supervision Through Random Sections with Autoregressive Coding (RandSAC)
Tianyu Hua, Yonglong Tian, Sucheng Ren, Michalis Raptis, Hang Zhao, Leonid Sigal.
Serving Chart Compression for Chart Neural Networks
Si Si, Felix Yu, Ankit Singh Rawat, Cho-Jui Hsieh, Sanjiv Kumar.
Consecutive Attention for Function Choice
Taisuke Yasuda *, MohammadHossein Bateni, Lin Chen, Matthew Fahrbach, Gang Fu, Vahab Mirrokni.
Sporadic Upcycling: Training Mixture-of-Experts from Thick Checkpoints
Aran Komatsuzaki *, Joan Puigcerver, James Lee-Thorp, Carlos Riquelme, Basil Mustafa, Joshua Ainslie, Yi Tay, Mostafa Dehghani, Neil Houlsby.
Spectral Decay Representation for Support Knowing
Tongzheng Ren, Tianjun Zhang, Lisa Lee, Joseph Gonzalez, Dale Schuurmans, Bo Dai.
Spotlight: Mobile UI Comprehending Utilizing Vision-Language Designs with a Focus ( see post)
Gang Li, Yang Li.
Guidance Intricacy and Its Function in Understanding Distillation
Hrayr Harutyunyan *, Ankit Singh Rawat, Aditya Krishna Menon, Seungyeon Kim, Sanjiv Kumar.
Instructor Assisted Training: An Effective Structure for Understanding Transfer
Manzil Zaheer, Ankit Singh Rawat, Seungyeon Kim, Chong You, Himanshu Jain, Andreas Veit, Rob Fergus, Sanjiv Kumar.
TEMPERA: Test-Time Prompt Modifying through Support Knowing
Tianjun Zhang, Xuezhi Wang, Denny Zhou, Dale Schuurmans, Joseph E. Gonzalez.
UL2: Unifying Language Knowing Paradigms
Yi Tay, Mostafa Dehghani, Vinh Q. Tran, Xavier Garcia, Jason Wei, Xuezhi Wang, Hyung Won Chung, Dara Bahri, Tal Schuster, Steven Zheng, Denny Zhou, Neil Houlsby, Donald Metzler.
* Work done while at Google