Shot Generalization

Shot generalization in machine learning focuses on enabling models to perform well on tasks with limited or no training examples (few-shot or zero-shot learning). Current research emphasizes improving the robustness and efficiency of these models, particularly through techniques like prompt engineering, meta-learning, and the development of parameter-efficient fine-tuning methods applied to large language models and neural networks. This area is crucial for advancing AI capabilities in data-scarce domains and for creating more adaptable and generalizable AI systems, impacting fields ranging from natural language processing and computer vision to robotics and scientific discovery.

Papers

August 29, 2024

Bootstrap Segmentation Foundation Model under Distribution Shift via Object-Centric Learning
Luyao Tang, Yuxuan Yuan, Chaoqi Chen, Kunze Huang, Xinghao Ding, Yue Huang
Distribution Shift Object Centric Representation Object Centric Learning Improved Generalization Segmentation Foundation Model Shot Generalization Object Perception

August 22, 2024

UNCO: Towards Unifying Neural Combinatorial Optimization through Large Language Model
Xia Jiang, Yaoxin Wu, Yuan Wang, Yingqian Zhang
Large Language Model Combinatorial Optimization Problem Neural Combinatorial Optimization Multi Objective Learning Shot Generalization Gradient Conflict

April 30, 2024

StablePT: Towards Stable Prompting for Few-shot Learning via Input Separation
Xiaoming Liu, Chen Liu, Zhaohan Zhang, Chengzhengxu Li, Longtian Wang, Yu Lan, Chao Shen
Large Language Model Contrastive Learning Soft Prompt Shot Generalization

November 24, 2023

Inferring Latent Class Statistics from Text for Robust Visual Few-Shot Learning
Yassir Bendou, Vincent Gripon, Bastien Pasdeloup, Giulia Lioi, Lukas Mauch, Fabien Cardinaux, Ghouthi Boukli Hacene
LeArning Abstract Text Modality Shot Learning Shot Classification Latent Class Shot Generalization

November 22, 2023

ComPEFT: Compression for Communicating Parameter Efficient Updates via Sparsification and Quantization
Prateek Yadav, Leshem Choshen, Colin Raffel, Mohit Bansal
Language Model Parameter Efficient Fine Tuning Quantization Operator Linear Compression Compositional Generalization Random Sparsification Parameter Update Shot Generalization

September 18, 2023

Investigating Zero- and Few-shot Generalization in Fact Verification
Liangming Pan, Yunxiang Zhang, Min-Yen Kan
Strong Generalization Domain Knowledge Better Zero Fact Verification Shot Generalization Claim Generation

June 30, 2023

Meta-training with Demonstration Retrieval for Efficient Few-shot Learning
Aaron Mueller, Kanika Narang, Lambert Mathias, Qifan Wang, Hamed Firooz
Large Language Model Meta Training Shot Generalization Shot Natural Language Understanding Efficient Few Shot Learning Demonstration Retrieval

May 24, 2023

BUFFET: Benchmarking Large Language Models for Few-shot Cross-lingual Transfer
Akari Asai, Sneha Kudugunta, Xinyan Velocity Yu, Terra Blevins, Hila Gonen, Machel Reid, Yulia Tsvetkov, Sebastian Ruder, Hannaneh Hajishirzi
Multilingual Large Language Model Shot Example Shot Generalization Shot Cross Lingual

April 27, 2023

ActorsNeRF: Animatable Few-shot Human Rendering with Generalizable NeRFs
Jiteng Mu, Shen Sang, Nuno Vasconcelos, Xiaolong Wang
Shot Generalization NeRF Representation

March 22, 2023

Self-supervised Meta-Prompt Learning with Meta-Gradient Regularization for Few-shot Generalization
Kaihang Pan, Juncheng Li, Hongye Song, Jun Lin, Xiaozhong Liu, Siliang Tang
Prompt Tuning Meta Training Shot Generalization Meta Regularization Meta Prompt Learning Prompt Initialization

March 16, 2023

DiGeo: Discriminative Geometry-Aware Learning for Generalized Few-Shot Object Detection
Jiawei Ma, Yulei Niu, Jincheng Xu, Shiyuan Huang, Guangxing Han, Shih-Fu Chang
Class Representation Shot Generalization Shot Benchmark

December 16, 2022

FewFedWeight: Few-shot Federated Learning Framework across Multiple NLP Tasks
Weilong Dong, Xinwei Wu, Junzhuo Li, Shuangzhi Wu, Chao Bian, Deyi Xiong
Multi Task Learning Shot Learning Centralized Learning Cross Task Generalization Shot Generalization One Shot Federated Learning Point Wise Weight

November 15, 2022

MEAL: Stable and Active Learning for Few-Shot Prompting
Abdullatif Köksal, Timo Schick, Hinrich Schütze
Active Learning Shot Learning Shot Classification Shot Generalization Meal Description

October 31, 2022

GPS: Genetic Prompt Search for Efficient Few-shot Learning
Hanwei Xu, Yujun Chen, Yulun Du, Nan Shao, Yanggang Wang, Haiyu Li, Zhilin Yang
Language Model Shot Learning Prompt Tuning Shot Generalization Efficient Few Shot Learning

August 23, 2022

FS-BAN: Born-Again Networks for Domain Generalization Few-Shot Classification
Yunqing Zhao, Ngai-Man Cheung
Classification Code Domain Generalization Domain Shift Generalization Performance Shot Classification Improved Generalization Shot Generalization

May 25, 2022

Fast Inference and Transfer of Compositional Task Structures for Few-shot Task Generalization
Sungryull Sohn, Hyunjae Woo, Jongwook Choi, lyubing qiang, Izzeddin Gur, Aleksandra Faust, Honglak Lee
Formality Transfer Hierarchical Reinforcement Learning Meta Reinforcement Learning Fast Inference Task Graph Task Inference Shot Generalization Task Structure

February 28, 2022

Combining Modular Skills in Multitask Learning
Edoardo M. Ponti, Alessandro Sordoni, Yoshua Bengio, Siva Reddy
Multitask Learning Shot Generalization Latent Skill Modular Skill