Papers with Code 아카이브

Zero-shot Generalization

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

0

평가표

1

보존된 평가 기록

5

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/aodongli/zero-shot-ad-via-batch-norm

공식 코드

Zero-Shot Anomaly Detection via Batch Normalization

https://github.com/apple/ml-mdm

공식 코드

Matryoshka Diffusion Models

https://github.com/arcadelab/fastsam3d

공식 코드

FastSAM3D: An Efficient Segment Anything Model for 3D Volumetric Medical Images

https://github.com/arcadelab/fluorosam

공식 코드

FluoroSAM: A Language-aligned Foundation Model for X-ray Image Segmentation

https://github.com/atticusg/NeuralEqualityExperiments

공식 코드

Relational reasoning and generalization using non-symbolic neural networks

https://github.com/audio-agi/audiosep

공식 코드

Separate Anything You Describe

https://github.com/autodeskailab/clip-forge

공식 코드

CLIP-Forge: Towards Zero-Shot Text-to-Shape Generation

https://github.com/autogluon/autogluon

공식 코드

Convolution Meets LoRA: Parameter Efficient Finetuning for Segment Anything Model

https://github.com/automl/CARL

공식 코드

Contextualize Me -- The Case for Context in Reinforcement Learning

https://github.com/autonomousvision/murf

공식 코드

MuRF: Multi-Baseline Radiance Fields

https://github.com/ayushraina10/sgts

공식 코드

Learning to design without prior data: Discovering generalizable design strategies using deep learning and tree search

https://github.com/azshue/TPT

공식 코드

Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models

https://github.com/bartn8/stereoanywhere

공식 코드

Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Fail

https://github.com/beam-labs/denovo

공식 코드

Universal Biological Sequence Reranking for Improved De Novo Peptide Sequencing

https://github.com/bethgelab/frequency_determines_performance

공식 코드

No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance

https://github.com/bigml-cs-ucla/clipcov-data-efficient-clip

공식 코드

Data-Efficient Contrastive Language-Image Pretraining: Prioritizing Data Quality over Quantity

https://github.com/bigscience-workshop/Megatron-DeepSpeed

공식 코드

What Language Model to Train if You Have One Million GPU Hours?

https://github.com/bigscience-workshop/architecture-objective

공식 코드

What Language Model Architecture and Pretraining Objective Work Best for Zero-Shot Generalization?

https://github.com/bigscience-workshop/biomedical

공식 코드

BigBIO: A Framework for Data-Centric Biomedical Natural Language Processing

https://github.com/bigscience-workshop/promptsource

공식 코드

Multitask Prompted Training Enables Zero-Shot Task Generalization

https://github.com/bigscience-workshop/t-zero

공식 코드

Multitask Prompted Training Enables Zero-Shot Task Generalization

https://github.com/bigscience-workshop/xmtf

공식 코드

Crosslingual Generalization through Multitask Finetuning

https://github.com/bmazoure/ctrl_public

공식 코드

Cross-Trajectory Representation Learning for Zero-Shot Generalization in RL

https://github.com/brendenlake/SCAN

공식 코드

Generalization without systematicity: On the compositional skills of sequence-to-sequence recurrent networks

https://github.com/bwittmann/vesselFM

공식 코드

vesselFM: A Foundation Model for Universal 3D Blood Vessel Segmentation

https://github.com/bytedance/GR-MG

공식 코드

GR-MG: Leveraging Partially Annotated Data via Multi-Modal Goal-Conditioned Policy

https://github.com/cake-lab/hybriddepth

공식 코드

HybridDepth: Robust Metric Depth Fusion by Leveraging Depth from Focus and Single-Image Priors

https://github.com/cambridge-mlg/convcnp

공식 코드

Convolutional Conditional Neural Processes

https://github.com/caoyunkang/segment-any-anomaly

공식 코드

Segment Any Anomaly without Training via Hybrid Prompt Regularization

https://github.com/cdb342/egzsl

공식 코드

Evolutionary Generalized Zero-Shot Learning

https://github.com/chaitjo/learning-tsp

공식 코드

Learning the Travelling Salesperson Problem Requires Rethinking Generalization

https://github.com/chiahsuan156/KaggleDBQA

공식 코드

KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers

https://github.com/chlee0801/insta

공식 코드

Instruction Matters: A Simple yet Effective Task Selection for Optimized Instruction Tuning of Specific Tasks

https://github.com/cho-geonwoo/traced

공식 코드

TRACED: Transition-aware Regret Approximation with Co-learnability for Environment Design

https://github.com/chongqingnosubway/prompt-ot

공식 코드

Prompt-OT: An Optimal Transport Regularization Paradigm for Knowledge Preservation in Vision-Language Model Adaptation

https://github.com/chris210634/ice

공식 코드

Image-Caption Encoding for Improving Zero-Shot Generalization

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.