conftrace_

task generalization

63 papers

Explore in graph

Co-occurring keywords

few-shot learning (3398) transfer learning (5449) zero-shot learning (3650) large language model (13587) in-context learning (1405) multi-task learning (2575) instruction tuning (838) language model (4599) meta-reinforcement learning (61) instruction following (396)

Papers

Not All Tasks Are Born Equal: Understanding Zero-Shot Generalization ICLR 2023
Auto-Instruct: Automatic Instruction Generation and Ranking for Black-Box Language Models EMNLP 2023
Robustness of Learning from Task Instructions ACL 2023
Meta Omnium: A Benchmark for General-Purpose Learning-To-Learn CVPR 2023
MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations CORL 2023
Combining Parameter-efficient Modules for Task-level Generalisation EACL 2023
Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels ICML 2023
On the Stability-Plasticity Dilemma in Continual Meta-Learning: Theory and Algorithm NIPS 2023
Large-scale Lifelong Learning of In-context Instructions and How to Tackle It ACL 2023
Pre-Training to Learn in Context ACL 2023
Is ChatGPT a General-Purpose Natural Language Processing Task Solver? EMNLP 2023
Parameterizing Non-Parametric Meta-Reinforcement Learning Tasks via Subtask Decomposition NIPS 2023
Task Generalization with Stability Guarantees via Elastic Dynamical System Motion Policies CORL 2023
Subspace Learning for Effective Meta-Learning ICML 2022
On the Limits of Evaluating Embodied Agent Model Generalization Using Validation Sets ACL 2022
Fast inference and transfer of compositional task structures for few-shot task generalization UAI 2022
Quantifying Adaptability in Pre-trained Language Models with 500 Tasks NAACL 2022
Prompt Consistency for Zero-Shot Task Generalization EMNLP 2022
InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning EMNLP 2022
On the Effectiveness of Fine-tuning Versus Meta-reinforcement Learning NIPS 2022
Communicating Natural Programs to Humans and Machines NIPS 2022
BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning CORL 2021
Learning to Generate Task-Specific Adapters from Task Description ACL 2021
LTL2Action: Generalizing LTL Instructions for Multi-Task RL ICML 2021
Improving Generalization in Meta-RL with Imaginary Tasks from Latent Dynamics Mixture NIPS 2021