https://github.com/hojjat-mokhtarabadi/promptsource
Multitask Prompted Training Enables Zero-Shot Task Generalization
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Multitask Prompted Training Enables Zero-Shot Task Generalization
CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation
ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth
Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning
ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth
Beyond the LUMIR challenge: The pathway to foundational registration models
VSCode: General Visual Salient and Camouflaged Object Detection with 2D Prompt Learning
From Images to Textual Prompts: Zero-shot VQA with Frozen Large Language Models
A Multi-Task BERT Model for Schema-Guided Dialogue State Tracking
Learning the Travelling Salesperson Problem Requires Rethinking Generalization
Learning to Route Among Specialized Experts for Zero-Shot Generalization
Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics
3D Diffuser Actor: Policy Diffusion with 3D Scene Representations
Factored World Models for Zero-Shot Generalization in Robotic Manipulation
Multitask Prompted Training Enables Zero-Shot Task Generalization
Octavius: Mitigating Task Interference in MLLMs via LoRA-MoE
What Can I Do Here? Learning New Skills by Imagining Visual Affordances
Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics
Improving Diffusion Models for Scene Text Editing with Dual Encoders
Towards Practical Multi-Object Manipulation using Relational Reinforcement Learning
Augmentation-Adapted Retriever Improves Generalization of Language Models as Generic Plug-In
Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.