https://github.com/declare-lab/wikides
공식 코드WikiDes: A Wikipedia-Based Dataset for Generating Short Descriptions from Paragraphs
Papers with Code 아카이브
Retrieval
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 3
- 평가표
- 11
- 보존된 평가 기록
- 19
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.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/deep-polyu/awesome-graphrag
공식 코드A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models
https://github.com/deep-spin/HFYN
공식 코드Hopfield-Fenchel-Young Networks: A Unified Framework for Associative Memory Retrieval
https://github.com/deep-spin/chunk-based_knn-mt
공식 코드https://github.com/deep-spin/efficient_knn_mt
공식 코드https://github.com/deep-spin/sshn
공식 코드https://github.com/deepaknlp/dls
공식 코드Medical Image Retrieval via Nearest Neighbor Search on Pre-trained Image Features
https://github.com/deepglint/alip
공식 코드ALIP: Adaptive Language-Image Pre-training with Synthetic Caption
https://github.com/deepglint/realsyn
공식 코드RealSyn: An Effective and Scalable Multimodal Interleaved Document Transformation Paradigm
https://github.com/deepglint/rwkv-clip
공식 코드https://github.com/deepglint/unicom
공식 코드Unicom: Universal and Compact Representation Learning for Image Retrieval
https://github.com/deepgraphlearning/protst
공식 코드ProtST: Multi-Modality Learning of Protein Sequences and Biomedical Texts
https://github.com/deeplearnxmu/faithful-rag
공식 코드FaithfulRAG: Fact-Level Conflict Modeling for Context-Faithful Retrieval-Augmented Generation
https://github.com/deeplearnxmu/kgr-4
공식 코드KGR^4: Retrieval, Retrospect, Refine and Rethink for Commonsense Generation
https://github.com/deeplearnxmu/knn-mt-dr
공식 코드Efficient k-Nearest-Neighbor Machine Translation with Dynamic Retrieval
https://github.com/deeplearnxmu/revisedkey-knn-mt
공식 코드https://github.com/deepmind/deepmind-research/tree/master/wikigraphs
공식 코드WikiGraphs: A Wikipedia Text - Knowledge Graph Paired Dataset
https://github.com/deepmind/dynamic-kanerva-machines
공식 코드https://github.com/deepmind/multimodal_transformers
공식 코드Decoupling the Role of Data, Attention, and Losses in Multimodal Transformers
https://github.com/deepmind/svo_probes
공식 코드https://github.com/deepsemantic/image_captioning
공식 코드https://github.com/deepsoftwareanalytics/race
공식 코드https://github.com/deeptibhegde/clip-goes-3d
공식 코드CLIP goes 3D: Leveraging Prompt Tuning for Language Grounded 3D Recognition
https://github.com/deezer/CrossCulturalMusicGenrePerception
공식 코드Modeling the Music Genre Perception across Language-Bound Cultures
https://github.com/deezer/MultilingualMusicGenreEmbedding
공식 코드Multilingual Music Genre Embeddings for Effective Cross-Lingual Music Item Annotation
https://github.com/deezer/cover_song_detection
공식 코드https://github.com/deezer/nlp4musa_melscribe
공식 코드Harnessing High-Level Song Descriptors towards Natural Language-Based Music Recommendation
https://github.com/deezer/sigir2019-2stagesampling
공식 코드Improving Collaborative Metric Learning with Efficient Negative Sampling
https://github.com/deezer/spiky_svd
공식 코드https://github.com/deezer/text2playlist-ecir2025
공식 코드Text2Playlist: Generating Personalized Playlists from Text on Deezer
https://github.com/delcayr/contextrefine-clip
공식 코드ContextRefine-CLIP for EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge 2025
https://github.com/dell-research-harvard/effocr
공식 코드https://github.com/dell-research-harvard/linktransformer
공식 코드LinkTransformer: A Unified Package for Record Linkage with Transformer Language Models
https://github.com/delong-liu-bupt/sen
공식 코드Text-guided Image Restoration and Semantic Enhancement for Text-to-Image Person Retrieval
https://github.com/dengyuhai/ms-ugcml
공식 코드Unsupervised Collaborative Metric Learning with Mixed-Scale Groups for General Object Retrieval
https://github.com/dennlinger/TopicalChange
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.