https://github.com/yanzhen4/logicol
공식 코드LogiCoL: Logically-Informed Contrastive Learning for Set-based Dense Retrieval
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
A methodology that involves selecting relevant data or examples from a large dataset to support tasks like prediction, learning, or inference. It enhances models by providing context or additional information, often used in systems like retrieval-augmented generation or in-context learning.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
LogiCoL: Logically-Informed Contrastive Learning for Set-based Dense Retrieval
Collaborative Retrieval for Large Language Model-based Conversational Recommender Systems
CapEnrich: Enriching Caption Semantics for Web Images via Cross-modal Pre-trained Knowledge
A Review of Modern Recommender Systems Using Generative Models (Gen-RecSys)
Recall@k Surrogate Loss with Large Batches and Similarity Mixup
Recall@k Surrogate Loss with Large Batches and Similarity Mixup
Stop Pre-Training: Adapt Visual-Language Models to Unseen Languages
English Contrastive Learning Can Learn Universal Cross-lingual Sentence Embeddings
CItruS: Chunked Instruction-aware State Eviction for Long Sequence Modeling
R^2AG: Incorporating Retrieval Information into Retrieval Augmented Generation
X-modaler: A Versatile and High-performance Codebase for Cross-modal Analytics
Cross-view image geo-localization with Panorama-BEV Co-Retrieval Network
Generative Question Refinement with Deep Reinforcement Learning in Retrieval-based QA System
Dense Hierarchical Retrieval for Open-Domain Question Answering
EAGER: Two-Stream Generative Recommender with Behavior-Semantic Collaboration
Towards a Better Understanding Human Reading Comprehension with Brain Signals
RAVENEA: A Benchmark for Multimodal Retrieval-Augmented Visual Culture Understanding
SmoothI: Smooth Rank Indicators for Differentiable IR Metrics
Deep Reinforcement Learning with Task-Adaptive Retrieval via Hypernetwork
Retrieval Guided Unsupervised Multi-domain Image-to-Image Translation
RaLLe: A Framework for Developing and Evaluating Retrieval-Augmented Large Language Models
Unsupervised Dense Retrieval with Relevance-Aware Contrastive Pre-Training
Retrieval-Augmented Multilingual Keyphrase Generation with Retriever-Generator Iterative Training
$BT^2$: Backward-compatible Training with Basis Transformation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.