Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

methodology-7

Zero-shot Generalization

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in zero-shot-generalization-7

Trend

Dataset

Best Model

Actions

CALVIN

Libraries

Use these libraries to find zero-shot-generalization-7 models and implementations

Datasets

CALVIN

Subtasks

No subtasks available.

Most implemented papers

Generalization without Systematicity: On the Compositional Skills of Sequence-to-Sequence Recurrent Networks

B. Lake, Marco Baroni•Mon Oct 30 2017

This paper introduces the SCAN domain, consisting of a set of simple compositional navigation commands paired with the corresponding action sequences, and tests the zero-shot generalization capabilities of a variety of recurrent neural networks trained on SCAN with sequence-to-sequence methods.

872

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

Paper Graph

Multitask Prompted Training Enables Zero-Shot Task Generalization

Sheng Shen, Urmish Thakker, Zheng-Xin Yong, Han Wang, Leo Gao, Stella Biderman, Canwen Xu, Colin Raffel, Rachel Bawden, Alexander M. Rush, Zaid Alyafeai, Andrea Santilli, Matteo Manica, Thomas Wang, Lintang Sutawika, Teven Le Scao, M Saiful Bari, Albert Webson, Taewoon Kim, Thomas Wolf, Victor Sanh, Stephen H. Bach, Antoine Chaffin, Arnaud Stiegler, Arun Raja, Manan Dey, S. Sharma, Eliza Szczechla, Gunjan Chhablani, Nihal V. Nayak, Debajyoti Datta, Jonathan D. Chang, Mike Tian-Jian Jiang, Harshit Pandey, Trishala Neeraj, Jos Rozen, Abheesht Sharma, Thibault Févry, Jason Alan Fries, R. Teehan, T. Bers•Thu Oct 14 2021

A system for easily mapping any natural language tasks into a human-readable prompted form and fine-tune a pretrained encoder-decoder model on this multitask mixture covering a wide variety of tasks.

1925 0

Paper Graph

Learning Transferable Cooperative Behavior in Multi-Agent Teams

Sumit Kumar, K. Sycara, Akshat Agarwal•Mon Jun 03 2019

A shared agent-entity graph is proposed, where agents and environmental entities form vertices, and edges exist between the vertices which can communicate with each other, allowing agents to selectively attend to different parts of the environment, while also introducing invariance to the number of agents or entities present in the system as well as permutation invariance.

141 0

Paper Graph

Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset

Xiaoxue Zang, Abhinav Rastogi, Srinivas Sunkara, Raghav Gupta, Pranav Khaitan•Wed Sep 11 2019

This work introduces the the Schema-Guided Dialogue (SGD) dataset, containing over 16k multi-domain conversations spanning 16 domains, and presents a schema-guided paradigm for task-oriented dialogue, in which predictions are made over a dynamic set of intents and slots provided as input.

679 0

Paper Graph

Learning the travelling salesperson problem requires rethinking generalization

Quentin Cappart, T. Laurent, Chaitanya K. Joshi, Louis-Martin Rousseau•Thu Jun 11 2020

This work presents an end-to-end neural combinatorial optimization pipeline that unifies several recent papers in order to identify the inductive biases, model architectures and learning algorithms that promote generalization to instances larger than those seen in training.

155 0

Paper Graph

Convolutional Conditional Neural Processes

Richard E. Turner, W. Bruinsma, Yann Dubois, Andrew Y. K. Foong, Jonathan Gordon, James Requeima•Mon Oct 28 2019

This work introduces the Convolutional Conditional Conditional Neural Process (ConvCNP), a new member of the Neural Process family that models translation equivariance in the data, and demonstrates that any translation-equivariant embedding can be represented using a convolutional deep set.

190 0

Paper Graph

The Scattering Compositional Learner: Discovering Objects, Attributes, Relationships in Analogical Reasoning

Jimmy Ba, Yuhuai Wu, R. Grosse, Honghua Dong•Tue Jul 07 2020

This work proposes the Scattering Compositional Learner (SCL), an architecture that composes neural networks in a sequence that achieves state-of-the-art performance on two RPM datasets, and finds that the compositional representation makes the SCL significantly more robust to test-time domain shifts and greatly improves zero-shot generalization to previously unseen analogies.

75 0

Paper Graph

ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth

Peter Wonka, Shariq Farooq Bhat, R. Birkl, Diana Wofk, Matthias Muller•Wed Feb 22 2023

The ZoeD-M12-NK is the first model that can jointly train on multiple datasets (NYU Depth v2 and KITTI) without a significant drop in performance and achieve unprecedented zero-shot generalization performance to eight unseen datasets from both indoor and outdoor domains.

786 0

Paper Graph

Adding a benchmark result helps the community track progress.

Zero-shot Generalization | State-of-the-Art