https://github.com/miccunifi/cross-the-gap
공식 코드Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion
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/miccunifi/iamcl2r
공식 코드https://github.com/miccunifi/searle
공식 코드https://github.com/michaeltian108/ca-tride
공식 코드Collapse-Aware Triplet Decoupling for Adversarially Robust Image Retrieval
https://github.com/michaelwilliamtang/golden-retriever
공식 코드https://github.com/michaelwilliamtang/referral-augment
공식 코드https://github.com/michalsr/regions
공식 코드https://github.com/michelebri/multi_agent_document_generation
공식 코드https://github.com/michuanhaohao/AICITY2021_Track2_DMT
공식 코드An Empirical Study of Vehicle Re-Identification on the AI City Challenge
https://github.com/micllordes/elibm25
공식 코드Explain like I am BM25: Interpreting a Dense Model's Ranked-List with a Sparse Approximation
https://github.com/microscopic-image-analysis/bayes-mef
공식 코드Bayesian multi-exposure image fusion for robust high dynamic range ptychography
https://github.com/microsoft/ANCE
공식 코드Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
https://github.com/microsoft/FILM
공식 코드https://github.com/microsoft/KBLaM
공식 코드https://github.com/microsoft/KC/tree/main/papers/TIARA
공식 코드TIARA: Multi-grained Retrieval for Robust Question Answering over Large Knowledge Bases
https://github.com/microsoft/LLM2CLIP
공식 코드LLM2CLIP: Powerful Language Model Unlocks Richer Visual Representation
https://github.com/microsoft/PICa
공식 코드An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA
https://github.com/microsoft/Samba
공식 코드Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling
https://github.com/microsoft/a-clip
공식 코드https://github.com/microsoft/ar2
공식 코드https://github.com/microsoft/bidr
공식 코드Progressively Optimized Bi-Granular Document Representation for Scalable Embedding Based Retrieval
https://github.com/microsoft/codet
공식 코드RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation
https://github.com/microsoft/comphrdoc
공식 코드https://github.com/microsoft/fiber
공식 코드Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone
https://github.com/microsoft/lavender
공식 코드LAVENDER: Unifying Video-Language Understanding as Masked Language Modeling
https://github.com/microsoft/lmops
공식 코드UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluation
https://github.com/microsoft/macaw
공식 코드Macaw: An Extensible Conversational Information Seeking Platform
https://github.com/microsoft/mopq
공식 코드https://github.com/microsoft/ms-marco-web-search
공식 코드MS MARCO Web Search: a Large-scale Information-rich Web Dataset with Millions of Real Click Labels
https://github.com/microsoft/muzic
공식 코드Re-creation of Creations: A New Paradigm for Lyric-to-Melody Generation
https://github.com/microsoft/muzic/tree/main/clamp
공식 코드CLaMP: Contrastive Language-Music Pre-training for Cross-Modal Symbolic Music Information Retrieval
https://github.com/microsoft/pike-rag
공식 코드PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation
https://github.com/microsoft/pycodegpt
공식 코드https://github.com/microsoft/react
공식 코드Learning Customized Visual Models with Retrieval-Augmented Knowledge
https://github.com/microsoft/rebel
공식 코드https://github.com/microsoft/recai
공식 코드Aligning Language Models for Versatile Text-based Item Retrieval
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.