Google at ICLR 2023 – Google AI Weblog

0
160


The Eleventh Worldwide Convention on Studying Representations (ICLR 2023) is being held this week as a hybrid occasion in Kigali, Rwanda. We’re proud to be a Diamond Sponsor of ICLR 2023, a premier convention on deep studying, the place Google researchers contribute in any respect ranges. This 12 months we’re presenting over 100 papers and are actively concerned in organizing and internet hosting various totally different occasions, together with workshops and interactive classes.

In case you’re registered for ICLR 2023, we hope you’ll go to the Google sales space to be taught extra concerning the thrilling work we’re doing throughout subjects spanning illustration and reinforcement studying, principle and optimization, social influence, security and privateness, and functions from generative AI to speech and robotics. Proceed under to search out the numerous methods by which Google researchers are engaged at ICLR 2023, together with workshops, papers, posters and talks (Google affiliations in daring).

Board and Organizing Committee

Board Members embody: Shakir Mohamed, Tara Sainath

Senior Program Chairs embody: Been Kim

Workshop Chairs embody: Aisha Walcott-Bryant, Rose Yu

Variety, Fairness & Inclusion Chairs embody: Rosanne Liu

Excellent Paper awards

Emergence of Maps within the Reminiscences of Blind Navigation Brokers

Erik Wijmans, Manolis Savva, Irfan Essa, Stefan Lee, Ari S. Morcos, Dhruv Batra

DreamFusion: Textual content-to-3D Utilizing 2D Diffusion

Ben Poole, Ajay Jain, Jonathan T. Barron, Ben Mildenhall

Keynote speaker

Realized Optimizers: Why They’re the Future, Why They’re Laborious, and What They Can Do Now


Jascha Sohl-Dickstein

Workshops

Kaggle@ICLR 2023: ML Options in Africa

Organizers embody: Julia Elliott, Phil Culliton, Ray Harvey

Facilitators: Julia Elliot, Walter Reade

Reincarnating Reinforcement Studying (Reincarnating RL)

Organizers embody: Rishabh Agarwal, Ted Xiao, Max Schwarzer

Audio system embody: Sergey Levine

Panelists embody: Marc G. Bellemare, Sergey Levine

Reliable and Dependable Massive-Scale Machine Studying Fashions

Organizers embody: Sanmi Koyejo

Audio system embody: Nicholas Carlini

Physics for Machine Studying (Physics4ML)

Audio system embody: Yasaman Bahri

AI for Agent-Based mostly Modelling Group (AI4ABM)

Organizers embody: Pablo Samuel Castro

Mathematical and Empirical Understanding of Basis Fashions (ME-FoMo)

Organizers embody: Mathilde Caron, Tengyu Ma, Hanie Sedghi

Audio system embody: Yasaman Bahri, Yann Dauphin

Neurosymbolic Generative Fashions 2023 (NeSy-GeMs)

Organizers embody: Kevin Ellis

Audio system embody: Daniel Tarlow, Tuan Anh Le

What Do We Want for Profitable Area Generalization?

Panelists embody: Boqing Gong

The 4th Workshop on Sensible ML for Creating Nations: Studying Below Restricted/Low Useful resource Settings

Keynote Speaker: Adji Bousso Dieng

Machine Studying for Distant Sensing

Audio system embody: Abigail Annkah

Multimodal Illustration Studying (MRL): Perks and Pitfalls

Organizers embody: Petra Poklukar

Audio system embody: Arsha Nagrani

Pitfalls of Restricted Information and Computation for Reliable ML

Organizers embody: Prateek Jain

Audio system embody: Nicholas Carlini, Praneeth Netrapalli

Sparsity in Neural Networks: On Sensible Limitations and Tradeoffs Between Sustainability and Effectivity

Organizers embody: Trevor Gale, Utku Evci

Audio system embody: Aakanksha Chowdhery, Jeff Dean

Time Collection Illustration Studying for Well being

Audio system embody: Katherine Heller

Deep Studying for Code (DL4C)

Organizers embody: Gabriel Orlanski

Audio system embody: Alex Polozov, Daniel Tarlow

Affinity Workshops

Tiny Papers Showcase Day (a DEI initiative)

Organizers embody: Rosanne Liu

Papers

Evolve Easily, Match Persistently: Studying Clean Latent Dynamics for Advection-Dominated Techniques


Zhong Yi Wan
, Leonardo Zepeda-Nunez, Anudhyan Boral, Fei Sha

Quantifying Memorization Throughout Neural Language Fashions


Nicholas Carlini
, Daphne Ippolito, Matthew Jagielski, Katherine Lee, Florian Tramer, Chiyuan Zhang

Emergence of Maps within the Reminiscences of Blind Navigation Brokers (Excellent Paper Award)


Erik Wijmans
, Manolis Savva, Irfan Essa, Stefan Lee, Ari S. Morcos, Dhruv Batra

Offline Q-Studying on Numerous Multi-task Information Each Scales and Generalizes (see weblog publish)

Aviral Kumar
, Rishabh Agarwal, Xingyang Geng, George Tucker, Sergey Levine

ReAct: Synergizing Reasoning and Performing in Language Fashions (see weblog publish)

Shunyu Yao
*, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik R. Narasimhan, Yuan Cao

Immediate-to-Immediate Picture Modifying with Cross-Consideration Management


Amir Hertz
, Ron Mokady, Jay Tenenbaum, Kfir Aberman, Yael Pritch, Daniel Cohen-Or

DreamFusion: Textual content-to-3D Utilizing 2D Diffusion (Excellent Paper Award)


Ben Poole
, Ajay Jain, Jonathan T. Barron, Ben Mildenhall

A System for Morphology-Process Generalization by way of Unified Illustration and Habits Distillation


Hiroki Furuta
, Yusuke Iwasawa, Yutaka Matsuo, Shixiang Shane Gu

Pattern-Environment friendly Reinforcement Studying by Breaking the Replay Ratio Barrier


Pierluca D’Oro
, Max Schwarzer, Evgenii Nikishin, Pierre-Luc Bacon, Marc G Bellemare, Aaron Courville

Dichotomy of Management: Separating What You Can Management from What You Can’t


Sherry Yang
, Dale Schuurmans, Pieter Abbeel, Ofir Nachum

Quick and Exact: Adjusting Planning Horizon with Adaptive Subgoal Search


Michał Zawalski
, Michał Tyrolski, Konrad Czechowski, Tomasz Odrzygóźdź, Damian Stachura, Piotr Piekos, Yuhuai Wu, Łukasz Kucinski, Piotr Miłos

The Commerce-Off Between Universality and Label Effectivity of Representations from Contrastive Studying


Zhenmei Shi
, Jiefeng Chen, Kunyang Li, Jayaram Raghuram, Xi Wu, Yingyu Liang, Somesh Jha

Sparsity-Constrained Optimum Transport


Tianlin Liu
*, Joan Puigcerver, Mathieu Blondel

Unmasking the Lottery Ticket Speculation: What’s Encoded in a Successful Ticket’s Masks?


Mansheej Paul
, Feng Chen, Brett W. Larsen, Jonathan Frankle, Surya Ganguli, Gintare Karolina Dziugaite

Excessive Q-Studying: MaxEnt RL with out Entropy


Divyansh Garg
, Joey Hejna, Matthieu Geist, Stefano Ermon

Draft, Sketch, and Show: Guiding Formal Theorem Provers with Casual Proofs


Albert Qiaochu Jiang
, Sean Welleck, Jin Peng Zhou, Timothee Lacroix, Jiacheng Liu, Wenda Li, Mateja Jamnik, Guillaume Lample, Yuhuai Wu

SimPer: Easy Self-Supervised Studying of Periodic Targets


Yuzhe Yang
, Xin Liu, Jiang Wu, Silviu Borac, Dina Katabi, Ming-Zher Poh, Daniel McDuff

Socratic Fashions: Composing Zero-Shot Multimodal Reasoning 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 Studying Algorithm Is In-Context Studying? Investigations with Linear Fashions


Ekin Akyurek
*, Dale Schuurmans, Jacob Andreas, Tengyu Ma*, Denny Zhou

Desire Transformer: Modeling Human Preferences Utilizing Transformers for RL


Changyeon Kim
, Jongjin Park, Jinwoo Shin, Honglak Lee, Pieter Abbeel, Kimin Lee

Iterative Patch Choice for Excessive-Decision Picture Recognition


Benjamin Bergner
, Christoph Lippert, Aravindh Mahendran

Open-Vocabulary Object Detection upon Frozen Imaginative and prescient and Language Fashions


Weicheng Kuo
, Yin Cui, Xiuye Gu, AJ Piergiovanni, Anelia Angelova

(Licensed!!) Adversarial Robustness for Free!


Nicholas Carlini
, Florian Tramér, Krishnamurthy (Dj) Dvijotham, Leslie Rice, Mingjie Solar, J. Zico Kolter

REPAIR: REnormalizing Permuted Activations for Interpolation Restore


Keller Jordan
, Hanie Sedghi, Olga Saukh, Rahim Entezari, Behnam Neyshabur

Discrete Predictor-Corrector Diffusion Fashions for Picture Synthesis


José Lezama
, Tim Salimans, Lu Jiang, Huiwen Chang, Jonathan Ho, Irfan Essa

Characteristic Reconstruction From Outputs Can Mitigate Simplicity Bias in Neural Networks


Sravanti Addepalli
, Anshul Nasery, Praneeth Netrapalli, Venkatesh Babu R., Prateek Jain

An Precise Poly-time Membership-Queries Algorithm for Extracting a Three-Layer ReLU Community


Amit Daniely
, Elad Granot

Language Fashions Are Multilingual Chain-of-Thought Reasoners


Freda Shi
, Mirac Suzgun, Markus Freitag, Xuezhi Wang, Suraj Srivats, Soroush Vosoughi, Hyung Received Chung, Yi Tay, Sebastian Ruder, Denny Zhou, Dipanjan Das, Jason Wei

Scaling Ahead Gradient with Native Losses


Mengye Ren
*, Simon Kornblith, Renjie Liao, Geoffrey Hinton

Treeformer: Dense Gradient Bushes for Environment friendly Consideration Computation


Lovish Madaan
, Srinadh Bhojanapalli, Himanshu Jain, Prateek Jain

LilNetX: Light-weight Networks with EXtreme Mannequin Compression and Structured Sparsification


Sharath Girish
, Kamal Gupta, Saurabh Singh, Abhinav Shrivastava

DiffusER: Diffusion by way of Edit-Based mostly Reconstruction


Machel Reid
, Vincent J. Hellendoorn, Graham Neubig

Leveraging Unlabeled Information to Monitor Memorization


Mahsa Forouzesh
, Hanie Sedghi, Patrick Thiran

A Combination-of-Professional Strategy to RL-Based mostly Dialogue Administration


Yinlam Chow
, Aza Tulepbergenov, Ofir Nachum, Dhawal Gupta, Moonkyung Ryu, Mohammad Ghavamzadeh, Craig Boutilier

Simple Differentially Personal Linear Regression


Kareem Amin
, Matthew Joseph, Monica Ribero, Sergei Vassilvitskii

KwikBucks: Correlation Clustering with Low cost-Weak and Costly-Robust Alerts


Sandeep Silwal
*, Sara Ahmadian, Andrew Nystrom, Andrew McCallum, Deepak Ramachandran, Mehran Kazemi

Massively Scaling Heteroscedastic Classifiers


Mark Collier
, Rodolphe Jenatton, Basil Mustafa, Neil Houlsby, Jesse Berent, Effrosyni Kokiopoulou

The Lazy Neuron Phenomenon: On Emergence 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 Massive Language Fashions


Andrew Drozdov
, Nathanael Scharli, Ekin Akyurek, Nathan Scales, Xinying Tune, Xinyun Chen, Olivier Bousquet, Denny Zhou

Extraordinarily Easy Activation Shaping for Out-of-Distribution Detection


Andrija Djurisic
, Nebojsa Bozanic, Arjun Ashok, Rosanne Liu

Lengthy Vary Language Modeling by way of Gated State Areas


Harsh Mehta
, Ankit Gupta, Ashok Cutkosky, Behnam Neyshabur

Investigating Multi-task Pretraining and Generalization in Reinforcement Studying


Adrien Ali Taiga
, Rishabh Agarwal, Jesse Farebrother, Aaron Courville, Marc G. Bellemare

Studying Low Dimensional State Areas with Overparameterized Recurrent Neural Nets


Edo Cohen-Karlik
, Itamar Menuhin-Gruman, Raja Giryes, Nadav Cohen, Amir Globerson

Weighted Ensemble Self-Supervised Studying


Yangjun Ruan
*, Saurabh Singh, Warren Morningstar, Alexander A. Alemi, Sergey Ioffe, Ian Fischer, Joshua V. Dillon

Calibrating Sequence Probability Improves Conditional Language Technology


Yao Zhao
, Misha Khalman, Rishabh Joshi, Shashi Narayan, Mohammad Saleh, Peter J. Liu

SMART: Sentences as Primary Models for Textual content Analysis


Reinald Kim Amplayo
, Peter J. Liu, Yao Zhao, Shashi Narayan

Leveraging Significance Weights in Subset Choice


Gui Citovsky
, Giulia DeSalvo, Sanjiv Kumar, Srikumar Ramalingam, Afshin Rostamizadeh, Yunjuan Wang*

Proto-Worth Networks: Scaling Illustration Studying with Auxiliary Duties

Jesse Farebrother, Joshua Greaves, Rishabh Agarwal, Charline Le Lan, Ross Goroshin, Pablo Samuel Castro, Marc G. Bellemare

An Extensible Multi-modal Multi-task Object Dataset with Supplies


Trevor Standley
, Ruohan Gao, Daybreak Chen, Jiajun Wu, Silvio Savarese

Measuring Forgetting of Memorized Coaching 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 Fashions Are Additionally Few-Shot Learners


Ajay Patel
, Bryan Li, Mohammad Sadegh Rasooli, Noah Fixed, Colin Raffel, Chris Callison-Burch

Is Consideration All That NeRF Wants?


Mukund Varma T.
, Peihao Wang, Xuxi Chen, Tianlong Chen, Subhashini Venugopalan, Zhangyang Wang

Automating Nearest Neighbor Search Configuration with Constrained Optimization


Philip Solar
, Ruiqi Guo, Sanjiv Kumar

Static Prediction of Runtime Errors by Studying to Execute Applications with Exterior Useful resource Descriptions


David Bieber
, Rishab Goel, Daniel Zheng, Hugo Larochelle, Daniel Tarlow

Composing Ensembles of Pre-trained Fashions by way of Iterative Consensus


Shuang Li
, Yilun Du, Joshua B. Tenenbaum, Antonio Torralba, Igor Mordatch

Λ-DARTS: Mitigating Efficiency Collapse by Harmonizing Operation Choice Amongst Cells


Sajad Movahedi
, Melika Adabinejad, Ayyoob Imani, Arezou Keshavarz, Mostafa Dehghani, Azadeh Shakery, Babak N. Araabi

Blurring Diffusion Fashions


Emiel Hoogeboom
, Tim Salimans

Half-Based mostly Fashions Enhance Adversarial Robustness


Chawin Sitawarin
, Kornrapat Pongmala, Yizheng Chen, Nicholas Carlini, David Wagner

Studying in Temporally Structured Environments


Matt Jones
, Tyler R. Scott, Mengye Ren, Gamaleldin ElSayed, Katherine Hermann, David Mayo, Michael C. Mozer

SlotFormer: Unsupervised Visible Dynamics Simulation with Object-Centric Fashions


Ziyi Wu
, Nikita Dvornik, Klaus Greff, Thomas Kipf, Animesh Garg

Sturdy Algorithms on Adaptive Inputs from Bounded Adversaries


Yeshwanth Cherapanamjeri
, Sandeep Silwal, David P. Woodruff, Fred Zhang, Qiuyi (Richard) Zhang, Samson Zhou

Agnostic Studying of Normal ReLU Activation Utilizing Gradient Descent


Pranjal Awasthi
, Alex Tang, Aravindan Vijayaraghavan

Analog Bits: Producing Discrete Information Utilizing Diffusion Fashions with Self-Conditioning


Ting Chen
, Ruixiang Zhang, Geoffrey Hinton

Any-Scale Balanced Samplers for Discrete House


Haoran Solar
*, Bo Dai, Charles Sutton, Dale Schuurmans, Hanjun Dai

Augmentation with Projection: In the direction of an Efficient and Environment friendly Information Augmentation Paradigm for Distillation


Ziqi Wang
*, Yuexin Wu, Frederick Liu, Daogao Liu, Le Hou, Hongkun Yu, Jing Li, Heng Ji

Past Lipschitz: Sharp Generalization and Extra Danger Bounds for Full-Batch GD


Konstantinos E. Nikolakakis
, Farzin Haddadpour, Amin Karbasi, Dionysios S. Kalogerias

Causal Estimation for Textual content Information with (Obvious) Overlap Violations


Lin Gui
, Victor Veitch

Contrastive Studying Can Discover an Optimum Foundation for Roughly View-Invariant Features


Daniel D. Johnson
, Ayoub El Hanchi, Chris J. Maddison

Differentially Personal Adaptive Optimization with Delayed Preconditioners


Tian Li
, Manzil Zaheer, Ziyu Liu, Sashank Reddi, Brendan McMahan, Virginia Smith

Distributionally Sturdy Submit-hoc Classifiers Below Prior Shifts


Jiaheng Wei
*, Harikrishna Narasimhan, Ehsan Amid, Wen-Sheng Chu, Yang Liu, Abhishek Kumar

Human Alignment of Neural Community Representations


Lukas Muttenthaler
, Jonas Dippel, Lorenz Linhardt, Robert A. Vandermeulen, Simon Kornblith

Implicit Bias in Leaky ReLU Networks Educated on Excessive-Dimensional Information


Spencer Frei
, Gal Vardi, Peter Bartlett, Nathan Srebro, Wei Hu

Koopman Neural Operator Forecaster for Time-Collection with Temporal Distributional Shifts


Rui Wang
*, Yihe Dong, Sercan Ö. Arik, Rose Yu

Latent Variable Illustration for Reinforcement Studying


Tongzheng Ren
, Chenjun Xiao, Tianjun Zhang, Na Li, Zhaoran Wang, Sujay Sanghavi, Dale Schuurmans, Bo Dai

Least-to-Most Prompting Permits Advanced Reasoning in Massive Language Fashions


Denny Zhou
, Nathanael Scharli, Le Hou, Jason Wei, Nathan Scales, Xuezhi Wang, Dale Schuurmans, Claire Cui, Olivier Bousquet, Quoc Le, Ed Chi

Thoughts’s Eye: Grounded Language Mannequin Reasoning By way of Simulation


Ruibo Liu
, Jason Wei, Shixiang Shane Gu, Te-Yen Wu, Soroush Vosoughi, Claire Cui, Denny Zhou, Andrew M. Dai

MOAT: Alternating Cell Convolution and Consideration Brings Robust Imaginative and prescient Fashions


Chenglin Yang
*, Siyuan Qiao, Qihang Yu, Xiaoding Yuan, Yukun Zhu, Alan Yuille, Hartwig Adam, Liang-Chieh Chen

Novel View Synthesis with Diffusion Fashions


Daniel Watson
, William Chan, Ricardo Martin-Brualla, Jonathan Ho, Andrea Tagliasacchi, Mohammad Norouzi

On Accelerated Perceptrons and Past


Guanghui Wang
, Rafael Hanashiro, Etash Guha, Jacob Abernethy

On Compositional Uncertainty Quantification for Seq2seq Graph Parsing


Zi Lin
*, Du Phan, Panupong Pasupat, Jeremiah Liu, Jingbo Shang

On the Robustness of Protected Reinforcement Studying Below Observational Perturbations


Zuxin Liu
, Zijian Guo, Zhepeng Cen, Huan Zhang, Jie Tan, Bo Li, Ding Zhao

On-line Low Rank Matrix Completion


Prateek Jain
, Soumyabrata Pal

Out-of-Distribution Detection and Selective Technology for Conditional Language Fashions


Jie Ren
, Jiaming Luo, Yao Zhao, Kundan Krishna*, Mohammad Saleh, Balaji Lakshminarayanan, Peter J. Liu

PaLI: A Collectively-Scaled Multilingual Language-Picture Mannequin


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 Size Video Technology from Open Area 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. Corridor, Ming-Wei Chang

Pushing the Accuracy-Group Robustness Frontier with Introspective Self-Play


Jeremiah Zhe Liu
, Krishnamurthy Dj Dvijotham, Jihyeon Lee, Quan Yuan, Balaji Lakshminarayanan, Deepak Ramachandran

Re-Imagen: Retrieval-Augmented Textual content-to-Picture Generator

Wenhu Chen
, Hexiang Hu, Chitwan Saharia, William W. Cohen

Recitation-Augmented Language Fashions


Zhiqing Solar
, Xuezhi Wang, Yi Tay, Yiming Yang, Denny Zhou

Regression with Label Differential Privateness


Badih Ghazi
, Pritish Kamath, Ravi Kumar, Ethan Leeman, Pasin Manurangsi, Avinash Varadarajan, Chiyuan Zhang

Revisiting the Entropy Semiring for Neural Speech Recognition


Oscar Chang
, Dongseong Hwang, Olivier Siohan

Sturdy Energetic Distillation


Cenk Baykal
, Khoa Trinh, Fotis Iliopoulos, Gaurav Menghani, Erik Vee

Rating-Based mostly Steady-Time Discrete Diffusion Fashions


Haoran Solar
*, Lijun Yu, Bo Dai, Dale Schuurmans, Hanjun Dai

Self-Consistency Improves Chain of Thought Reasoning in Language Fashions


Xuezhi Wang
, Jason Wei, Dale Schuurmans, Quoc Le, Ed H. Chi, Sharan Narang, Aakanksha Chowdhery, Denny Zhou

Self-Supervision By way of Random Segments with Autoregressive Coding (RandSAC)


Tianyu Hua
, Yonglong Tian, Sucheng Ren, Michalis Raptis, Hold Zhao, Leonid Sigal

Serving Graph Compression for Graph Neural Networks


Si Si
, Felix Yu, Ankit Singh Rawat, Cho-Jui Hsieh, Sanjiv Kumar

Sequential Consideration for Characteristic Choice


Taisuke Yasuda
*, MohammadHossein Bateni, Lin Chen, Matthew Fahrbach, Gang Fu, Vahab Mirrokni

Sparse Upcycling: Coaching Combination-of-Consultants from Dense Checkpoints


Aran Komatsuzaki
*, Joan Puigcerver, James Lee-Thorp, Carlos Riquelme, Basil Mustafa, Joshua Ainslie, Yi Tay, Mostafa Dehghani, Neil Houlsby

Spectral Decomposition Illustration for Reinforcement Studying


Tongzheng Ren
, Tianjun Zhang, Lisa Lee, Joseph Gonzalez, Dale Schuurmans, Bo Dai

Highlight: Cell UI Understanding Utilizing Imaginative and prescient-Language Fashions with a Focus (see weblog publish)

Gang Li
, Yang Li

Supervision Complexity and Its Position in Data Distillation


Hrayr Harutyunyan
*, Ankit Singh Rawat, Aditya Krishna Menon, Seungyeon Kim, Sanjiv Kumar

Trainer Guided Coaching: An Environment friendly Framework for Data Switch


Manzil Zaheer
, Ankit Singh Rawat, Seungyeon Kim, Chong You, Himanshu Jain, Andreas Veit, Rob Fergus, Sanjiv Kumar

TEMPERA: Take a look at-Time Immediate Modifying by way of Reinforcement Studying


Tianjun Zhang
, Xuezhi Wang, Denny Zhou, Dale Schuurmans, Joseph E. Gonzalez

UL2: Unifying Language Studying Paradigms


Yi Tay
, Mostafa Dehghani, Vinh Q. Tran, Xavier Garcia, Jason Wei, Xuezhi Wang, Hyung Received Chung, Dara Bahri, Tal Schuster, Steven Zheng, Denny Zhou, Neil Houlsby, Donald Metzler


* Work executed whereas at Google

LEAVE A REPLY

Please enter your comment!
Please enter your name here