paper-with-me

홈 › Papers

A Generalization Theory for Zero-Shot Prediction

2025-07-12 · Ronak Mehta, Zaid Harchaoui arxiv

A modern paradigm for generalization in machine learning and AI consists of pre-training a task-agnostic foundation model, generally obtained using self-supervised and multimodal contrastive learning. The resulting representations can be used for prediction on a downstream task for which no labeled data is available. We present a theoretical framework to better understand this approach, called zero-shot prediction. We identify the target quantities that zero-shot prediction aims to learn, or learns in passing, and the key conditional independence relationships that enable its generalization ability.

📄 PDF Abstract BibTeX arXiv:2507.09128

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive Learning

Similar Papers 제목 키워드 기반

Do Vision Language Models Understand Human Engagement in Games?

2026-03-19 · Ziyi Wang, Qizan Guo, Rishitosh Singh, Xiyang Hu arxiv

Inferring human engagement from gameplay video is important for game design and player-experience research, yet it remains unclear whether vision--language models (VLMs) can infer such latent psychological states from vi…

$S^3$: Synonymous Semantic Space for Improving Zero-Shot Generalization of Vision-Language Models

2024-12-06 · Xiaojie Yin, Qilong Wang, Bing Cao, QinGhua Hu

Recently, many studies have been conducted to enhance the zero-shot generalization ability of vision-language models (e.g., CLIP) by addressing the semantic misalignment between image and text embeddings in downstream ta…

zero-shot-classificationZero-shot GeneralizationZero-Shot Learning

Efficient Fine-Tuning of Single-Cell Foundation Models Enables Zero-Shot Molecular Perturbation Prediction

2024-12-18 · Sepideh Maleki, Jan-Christian Huetter, Kangway V. Chuang, David Richmond 외

Predicting transcriptional responses to novel drugs provides a unique opportunity to accelerate biomedical research and advance drug discovery efforts. However, the inherent complexity and high dimensionality of cellular…

Drug DiscoveryZero-shot Generalization

Zero-shot Learning and Knowledge Transfer in Music Classification and Tagging

2019-06-20 · Jeong Choi, Jongpil Lee, Jiyoung Park, Juhan Nam

Music classification and tagging is conducted through categorical supervised learning with a fixed set of labels. In principle, this cannot make predictions on unseen labels. Zero-shot learning is an approach to solve th…

ClassificationGeneral ClassificationMusic ClassificationTransfer Learning+1

LAD: Language Models as Data for Zero-Shot Dialog

2022-07-28 · SIGDIAL (ACL) 2022 9 · Shikib Mehri, Yasemin Altun, Maxine Eskenazi

To facilitate zero-shot generalization in taskoriented dialog, this paper proposes Language Models as Data (LAD). LAD is a paradigm for creating diverse and accurate synthetic data which conveys the necessary structural …

DiversityPredictionslot-fillingSlot Filling+1