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/hnanhtuan/selectiveConvFeature
공식 코드https://github.com/hoanganhpham1006/cost
공식 코드Video Dialog as Conversation about Objects Living in Space-Time
https://github.com/hoar012/rap-mllm
공식 코드RAP: Retrieval-Augmented Personalization for Multimodal Large Language Models
https://github.com/hohsiangwu/crossmodal
공식 코드Exploring modality-agnostic representations for music classification
https://github.com/hondamunigeprasannasilva/attack-attention
공식 코드Attacking Attention of Foundation Models Disrupts Downstream Tasks
https://github.com/hongje/hmmn
공식 코드Hierarchical Memory Matching Network for Video Object Segmentation
https://github.com/hoorangyee/lrage
공식 코드https://github.com/hoplee6/sports-qa
공식 코드Sports-QA: A Large-Scale Video Question Answering Benchmark for Complex and Professional Sports
https://github.com/hornhehhf/rr
공식 코드Rethinking with Retrieval: Faithful Large Language Model Inference
https://github.com/hou27/recdap-fkgc
공식 코드https://github.com/houzhijian/conquer
공식 코드CONQUER: Contextual Query-aware Ranking for Video Corpus Moment Retrieval
https://github.com/hpai-bsc/prompt_engine
공식 코드https://github.com/hpclab/toploc_conv_search
공식 코드Efficient Conversational Search via Topical Locality in Dense Retrieval
https://github.com/hqqasw/person-search-PPCC
공식 코드Person Search in Videos with One Portrait Through Visual and Temporal Links
https://github.com/hqsiswiliam/lapdog
공식 코드Learning Retrieval Augmentation for Personalized Dialogue Generation
https://github.com/hritikbansal/videocon
공식 코드VideoCon: Robust Video-Language Alignment via Contrast Captions
https://github.com/hrtang22/MUSE
공식 코드MUSE: Mamba is Efficient Multi-scale Learner for Text-video Retrieval
https://github.com/hsiehjackson/mr.right
공식 코드Mr. Right: Multimodal Retrieval on Representation of ImaGe witH Text
https://github.com/hsinglukliu/puzzle-based_storage_appendix
공식 코드Reinforcement learning for multi-item retrieval in the puzzle-based storage system
https://github.com/hsliu-initial/ctrla
공식 코드CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Control
https://github.com/hsliu-initial/rok
공식 코드Retrieval-Oriented Knowledge for Click-Through Rate Prediction
https://github.com/htconquer/BGAN
공식 코드https://github.com/htconquer/ddh
공식 코드https://github.com/htlsn/igan
공식 코드https://github.com/huangl22/chat3gpp
공식 코드Chat3GPP: An Open-Source Retrieval-Augmented Generation Framework for 3GPP Documents
https://github.com/huangmozhi9527/GMMFormer
공식 코드GMMFormer: Gaussian-Mixture-Model Based Transformer for Efficient Partially Relevant Video Retrieval
https://github.com/huangmozhi9527/conmh
공식 코드Contrastive Masked Autoencoders for Self-Supervised Video Hashing
https://github.com/huangmozhi9527/gmmformer_v2
공식 코드GMMFormer v2: An Uncertainty-aware Framework for Partially Relevant Video Retrieval
https://github.com/huangzichun/dreditor
공식 코드DREditor: An Time-efficient Approach for Building a Domain-specific Dense Retrieval Model
https://github.com/huangzongheng/mathm
공식 코드Modality-Aware Triplet Hard Mining for Zero-shot Sketch-Based Image Retrieval
https://github.com/huawei-lin/DMin
공식 코드DMin: Scalable Training Data Influence Estimation for Diffusion Models
https://github.com/huawei-lin/rapidin
공식 코드Token-wise Influential Training Data Retrieval for Large Language Models
https://github.com/huawei-noah/hebo
공식 코드https://github.com/huenao/debate-augmented-rag
공식 코드Removal of Hallucination on Hallucination: Debate-Augmented RAG
https://github.com/huggingface/gaia
공식 코드GAIA Search: Hugging Face and Pyserini Interoperability for NLP Training Data Exploration
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.